dirtyharrylyl / dj-rn Goto Github PK
View Code? Open in Web Editor NEWAs a part of HAKE project (HAKE-3D). Code for our CVPR2020 paper "Detailed 2D-3D Joint Representation for Human-Object Interaction".
License: Apache License 2.0
dj-rn's People
Contributors
Stargazers
Watchers
Forkers
asurada404 sri9s zhuxuhan liuguoyou zeta1999 dong-jinkim xujinglin ivan-vv metavai xiaojiean yangyuan333 youngrainy lianglilidj-rn's Issues
$ python script/Download_data.py 1_aSwqUPCKHNSkx8WHIaHc3zjM0u50xPi Test_ambiguous.pkl
How do you run this? since I am getting error:
[26744:2271 0:466] 07:33:22 Wed Dec 23 [mona@goku:pts/5 +1] ~/research/code/DJ-RN
$ python script/Download_data.py 1_aSwqUPCKHNSkx8WHIaHc3zjM0u50xPi Test_ambiguous.pkl
script/Download_data.py:45: SyntaxWarning: "is not" with a literal. Did you mean "!="?
if len(sys.argv) is not 3:
word embedding
Hello
Is possible for you to send me the part of your code that used PCA to reduce the dimension of w2v to 128 as stated in the paper?
Error in concat_w2v.py
hello
when run "python script/concat_w2v.py --SMPLX_PATH --GT ./Data/Trainval_GT_HICO_with_idx.pkl --Neg Trainval_Neg_HICO_with_idx.pkl --Test Test_Faster_RCNN_R-50-PFN_2x_HICO_DET_with_idx.pkl"
I have following error:
pc = pickle.load(open(args.SMPLX_PATH + '/object_GT/HICO_train2015_%08d/%03d_feature.pkl' % i, 'rb'))
TypeError: not enough arguments for format string
when I replace this line with "pc = pickle.load(open(args.SMPLX_PATH + '/object_GT/HICO_train2015_%08d/%03d_feature.pkl' % (key, Trainval_GT[key][i][-1]), 'rb'))" I have following error:
FileNotFoundError: [Errno 2] No such file or directory: 'F:/DJ-RN-master/DJ-RN-master/Spatial/object_GT/HICO_train2015_00000004/001_feature.pkl'
This is because in the folder "results\HICO_train2015_00000004" ] : I have 000.pkl, 001.pkl and 002.pkl but in folder "object_GT\HICO_train2015_00000004" I have only 000_feature.pkl and not 001_feature.pkl and 002_feature.pkl.
Did I make a mistake or does the code need to be corrected?
Questions I meet when making your model
Thanks for sharing the great work. I really want to making your model but I meet some problems.
- In step DATA GENERATION--Run SMPLify-X on the dataset with the filtered pose, I need to run SMPLify-X on the dataset but I cannot find the vposer_folder and smplx_parts_segm.pkl which you have mentioned it in another issue in the previous downloading files.
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ... --output_folder ... --visualize="True/False" --model_folder ... --vposer_ckpt VPOSER_FOLDER --part_segm_fn smplx_parts_segm.pkl
2.In step 3D Human-Object Interaction Volume Generation and Visualization--Generation, I cannot run code in the DJ-RN/script/generate_utils.py, about line 260, if ansz>maxz.
Traceback:File ../sympy/core/relational.py, line 384, in __nonzero__, raise TypeError("cannot determine truth value of Relational")
3.In step Extract feature using PointNet---Extract feature, I cannot find any folder or files named model_10000.ckpt ...?
ValueError: operands could not be broadcast together with shapes (10701,) (1489274,)
Hello
When I run "python ./-Results/Generate_detection.py --model <your test output directory, under ./-Results by default>" , I got bellow error:
Traceback (most recent call last):
File "./-Results/Generate_detection.py", line 63, in
mask = inter_det_mask * nis_mask
ValueError: operands could not be broadcast together with shapes (10701,) (1489274,)
It give the error in this line"mask = inter_det_mask * nis_mask"
why?
NaN loss value, stopping! --> File "/home/mona/research/code/smplify-x/smplifyx/fit_single_frame.py", line 366, in fit_single_frame tqdm.write('Camera initialization final loss {:.4f}'.format( TypeError: unsupported format string passed to NoneType.__format__
After processing some images successfully, I got this error. Is there a fix for it?
Processing: ../../data/smplify-x/djrn_test_data/images/HICO_test2015_00000469.jpg
Found Trained Model: ../../data/smplify-x/vposer_v1_0/snapshots/TR00_E096.pt
Camera initialization done after 0.7507
Camera initialization final loss 1283.9620
Stage 000 done after 2.0166 seconds
Stage 001 done after 1.8066 seconds
Stage 002 done after 1.7855 seconds
Stage 003 done after 6.2607 seconds
Stage 004 done after 6.4354 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:18<00:00, 3.66s/it]
Body fitting Orientation 0 done after 18.3112 seconds
Body final loss val = 7074.32373
Orientation: 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:18<00:00, 18.31s/it]
Processing: ../../data/smplify-x/djrn_test_data/images/HICO_test2015_00000470.jpg
Found Trained Model: ../../data/smplify-x/vposer_v1_0/snapshots/TR00_E096.pt
Camera initialization done after 0.9054
Camera initialization final loss 805.9324
Stage 000 done after 2.0088 seconds
Stage 001 done after 0.6831 seconds
Stage 002 done after 2.9054 seconds
Stage 003 done after 7.4240 seconds
Stage 004 done after 1.3566 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:14<00:00, 2.88s/it]
Body fitting Orientation 0 done after 14.3841 seconds
Body final loss val = 1076.25085
Orientation: 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:14<00:00, 14.38s/it]
Found Trained Model: ../../data/smplify-x/vposer_v1_0/snapshots/TR00_E096.pt
Camera initialization done after 0.8964
Camera initialization final loss 10146.6113
Stage 000 done after 2.3258 seconds
Stage 001 done after 1.5916 seconds
Stage 002 done after 3.7246 seconds
Stage 003 done after 13.3136 seconds
Stage 004 done after 3.2600 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:24<00:00, 4.84s/it]
Body fitting Orientation 0 done after 24.2220 seconds
Body final loss val = 196141.98438
Orientation: 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:24<00:00, 24.22s/it]
Processing: ../../data/smplify-x/djrn_test_data/images/HICO_test2015_00000471.jpg
Found Trained Model: ../../data/smplify-x/vposer_v1_0/snapshots/TR00_E096.pt
NaN loss value, stopping!
Camera initialization done after 1.2850
Traceback (most recent call last):
File "smplifyx/main.py", line 272, in <module>
main(**args)
File "smplifyx/main.py", line 245, in main
fit_single_frame(img, keypoints[[person_id]],
File "/home/mona/research/code/smplify-x/smplifyx/fit_single_frame.py", line 366, in fit_single_frame
tqdm.write('Camera initialization final loss {:.4f}'.format(
TypeError: unsupported format string passed to NoneType.__format__
I am running it as follows:
$ cat djrn_fit.sh
export CUDA_VISIBLE_DEVICES=0
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_train_data/ --output_folder ../../data/smplify-x/djrn_train_results --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_test_data/ --output_folder ../../data/smplify-x/djrn_test_results --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
I have:
~/research/data/smplify-x/djrn_train_results/meshes
$ numdir
293
~/research/data/smplify-x/djrn_test_results/meshes
$ numdir
338
Where numdir is:
alias numdir='echo find . -type d | wc -l-1 | bc'
when using human_body_prior module for smplify-x for preprocessing the HICO-DET image dataset I get best_model_fname = sorted(glob.glob(os.path.join(expr_dir, 'snapshots', '*.pt')), key=os.path.getmtime)[-1] IndexError: list index out of range
Could you please have a look at the following error and guide me? Thanks a lot.
(smplifyx) [jalal@goku smplify-x]$ ./djrn_fit.sh
Processing: ../../data/smplify-x/djrn_train_data/images/HICO_train2015_00000001.jpg
Traceback (most recent call last):
File "smplifyx/main.py", line 272, in <module>
main(**args)
File "smplifyx/main.py", line 245, in main
fit_single_frame(img, keypoints[[person_id]],
File "/scratch3/research/code/smplify-x/smplifyx/fit_single_frame.py", line 188, in fit_single_frame
vposer, _ = load_vposer(vposer_ckpt, vp_model='snapshot')
File "/scratch3/venv/smplifyx/lib/python3.8/site-packages/human_body_prior/tools/model_loader.py", line 56, in load_vposer
ps, trained_model_fname = expid2model(expr_dir)
File "/scratch3/venv/smplifyx/lib/python3.8/site-packages/human_body_prior/tools/model_loader.py", line 31, in expid2model
best_model_fname = sorted(glob.glob(os.path.join(expr_dir, 'snapshots', '*.pt')), key=os.path.getmtime)[-1]
IndexError: list index out of range
Processing: ../../data/smplify-x/djrn_test_data/images/HICO_test2015_00000002.jpg
Traceback (most recent call last):
File "smplifyx/main.py", line 272, in <module>
main(**args)
File "smplifyx/main.py", line 245, in main
fit_single_frame(img, keypoints[[person_id]],
File "/scratch3/research/code/smplify-x/smplifyx/fit_single_frame.py", line 188, in fit_single_frame
vposer, _ = load_vposer(vposer_ckpt, vp_model='snapshot')
File "/scratch3/venv/smplifyx/lib/python3.8/site-packages/human_body_prior/tools/model_loader.py", line 56, in load_vposer
ps, trained_model_fname = expid2model(expr_dir)
File "/scratch3/venv/smplifyx/lib/python3.8/site-packages/human_body_prior/tools/model_loader.py", line 31, in expid2model
best_model_fname = sorted(glob.glob(os.path.join(expr_dir, 'snapshots', '*.pt')), key=os.path.getmtime)[-1]
IndexError: list index out of range
The script is:
(smplifyx) [jalal@goku smplify-x]$ cat ./djrn_fit.sh
export CUDA_VISIBLE_DEVICES=0
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_train_data/ --output_folder ../../data/smplify-x/djrn_train_results --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_test_data/ --output_folder ../../data/smplify-x/djrn_test_results --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
and
(smplifyx) [jalal@goku smplify-x]$ ls ../../data/smplify-x/djrn_train_data/images/HICO_train2015_00000001.jpg
-rwxr-xr-x. 1 jalal cs-grad 63K May 21 17:29 ../../data/smplify-x/djrn_train_data/images/HICO_train2015_00000001.jpg
Example input/output for running step 4 and 5 of Data Generation
Could you please provide clear input and output examples for running step 4 and 5 of Data Generation in README.md?
For example, I am not sure what is exactly the "pose used for SMPLIify-X"?
python script/assign_pose_GT.py --pose <path to your pose used for SMPLify-X> --res <path to your SMPLify-X result>
I am also not sure at all how to "Run SMPLify-X on the dataset with the filtered pose" as in step 4. Could you please provide step-to-step guide on how to do this?
Thanks a lot.
The size of features extracted
In the "python Feature_extraction.py --input_list script/vertex_path_GT.txt --model_path ../Feature_extraction/model_10000.ckpt" step, what is the size of extracted feature?
How to improve the iCAN performance?
Hi, in the readme file, you provide the iCAN result as follows,
iCAN (BMVC2018) 19.61 17.29 20.30 22.10 20.46 22.59
However, in the paper, the result of iCAN is,
iCAN 14.84 10.45 17.03 13.42 17.18 12.17 17.46 15.65.
Would u mind provide the details of your new iCAN result?
python script/filter_pose.py --ori openpose/openpose_hico_train --fil filtered_results/openpose_hico_train yields no results
could you please guide me what's the reason no result is yielded? previously running this in another machine actually yielded results
(djrn) [jalal@goku DJ-RN]$ python script/filter_pose.py --ori openpose/openpose_hico_train --fil filtered_results/openpose_hico_train
(djrn) [jalal@goku DJ-RN]$ ls filtered_results/openpose_hico_train/
total 0
drwxr-xr-x. 3 jalal cs-grad 33 May 20 20:41 ..
drwxr-xr-x. 2 jalal cs-grad 6 May 20 20:41 .
Error cpu:0
Hello
when running "python Feature_extraction.py --input_list script/vertex_path_GT.txt --model_path ../Feature_extraction/model_10000.ckpt"
I have many errors about Cpu:0 such as:
2020-12-22 23:24:43.600425: I tensorflow/core/common_runtime/placer.cc:54] transform_net1/tconv2/bn/cond/ExponentialMovingAverage: (NoOp): /job:localhost/replica:0/task:0/device:CPU:0
2020-12-22 23:24:43.600431: I tensorflow/core/common_runtime/placer.cc:54] transform_net1/tconv2/bn/cond/control_dependency: (Identity): /job:localhost/replica:0/task:0/device:CPU:0
smplify-x sometimes fails and sometimes doesn't fail on certain images
So, when I run the fit code in batch among all test images of hico-det, it fails for HICO_test2015_00001000.jpg image however, if I run it separately on it, it doesn't. I am very confused by what is happening and how to fix it.
(smplifyx) [jalal@goku smplify-x]$ ./djrn_fit_fail_test.sh
Processing: ../../data/smplify-x/djrn_test_data_00001000/images/HICO_test2015_00001000.jpg
Found Trained Model: ../../data/smplify-x/vposer_v1_0/snapshots/TR00_E096.pt
/scratch3/research/code/smplify-x/smplifyx/optimizers/lbfgs_ls.py:238: UserWarning: This overload of add_ is deprecated:
add_(Number alpha, Tensor other)
Consider using one of the following signatures instead:
add_(Tensor other, *, Number alpha) (Triggered internally at /pytorch/torch/csrc/utils/python_arg_parser.cpp:1005.)
p.data.add_(step_size, update[offset:offset + numel].view_as(p.data))
Camera initialization done after 0.9238
Camera initialization final loss 575.2435
Stage 000 done after 2.8637 seconds
Stage 001 done after 0.4564 seconds
Stage 002 done after 6.1315 seconds
Stage 003 done after 18.8520 seconds
Stage 004 done after 25.0695 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:53<00:00, 10.68s/it]
Body fitting Orientation 0 done after 53.3851 seconds
Body final loss val = 2082.48096
Orientation: 50%|█████████████████████████████████████████▌ | 1/2 [00:53<00:53, 53.39s/it]/scratch3/venv/smplifyx/lib/python3.8/site-packages/smplx/body_models.py:271: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
param[:] = torch.tensor(params_dict[param_name])
Stage 000 done after 4.2677 seconds
Stage 001 done after 0.4241 seconds
Stage 002 done after 7.9165 seconds
Stage 003 done after 20.4528 seconds
Stage 004 done after 21.4049 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:54<00:00, 10.90s/it]
Body fitting Orientation 1 done after 54.4810 seconds
Body final loss val = 2081.42847
Orientation: 100%|███████████████████████████████████████████████████████████████████████████████████| 2/2 [01:47<00:00, 53.94s/it]
Found Trained Model: ../../data/smplify-x/vposer_v1_0/snapshots/TR00_E096.pt
Camera initialization done after 1.1827
Camera initialization final loss 3.5034
Stage 000 done after 1.4251 seconds
Stage 001 done after 0.2998 seconds
Stage 002 done after 0.7215 seconds
Stage 003 done after 5.4210 seconds
Stage 004 done after 4.5305 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:12<00:00, 2.48s/it]
Body fitting Orientation 0 done after 12.4083 seconds
Body final loss val = 177.26837
Orientation: 50%|█████████████████████████████████████████▌ | 1/2 [00:12<00:12, 12.41s/it]/scratch3/venv/smplifyx/lib/python3.8/site-packages/smplx/body_models.py:271: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
param[:] = torch.tensor(params_dict[param_name])
Stage 000 done after 4.9444 seconds
Stage 001 done after 0.4744 seconds
Stage 002 done after 1.0594 seconds
Stage 003 done after 6.2616 seconds
Stage 004 done after 0.9128 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:13<00:00, 2.73s/it]
Body fitting Orientation 1 done after 13.6635 seconds
Body final loss val = 277.39865
Orientation: 100%|███████████████████████████████████████████████████████████████████████████████████| 2/2 [00:26<00:00, 13.04s/it]
Found Trained Model: ../../data/smplify-x/vposer_v1_0/snapshots/TR00_E096.pt
Camera initialization done after 1.1597
Camera initialization final loss 4.8399
Stage 000 done after 0.4743 seconds
Stage 001 done after 0.4020 seconds
Stage 002 done after 1.4820 seconds
Stage 003 done after 8.3911 seconds
Stage 004 done after 5.7249 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:16<00:00, 3.30s/it]
Body fitting Orientation 0 done after 16.4828 seconds
Body final loss val = 87.92973
Stage 000 done after 1.3672 seconds
Stage 001 done after 0.3005 seconds
Stage 002 done after 1.9238 seconds
Stage 003 done after 4.8648 seconds
Stage 004 done after 8.3106 seconds
Stage: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:16<00:00, 3.36s/it]
Body fitting Orientation 1 done after 16.7777 seconds
Body final loss val = 89.72486
Orientation: 100%|███████████████████████████████████████████████████████████████████████████████████| 2/2 [00:33<00:00, 16.63s/it]
Processing the data took: 00 hours, 02 minutes, 55 seconds
Additionally, the results look like the following where in three folders, namely 000, 001, and 002 are created for meshes folder of results for this specific input image. I am not sure what they correspond to?
(smplifyx) [jalal@goku results_djrn_test_data_00001000]$ pwd
/scratch3/research/data/smplify-x/results_djrn_test_data_00001000
(smplifyx) [jalal@goku results_djrn_test_data_00001000]$ tree .
.
├── conf.yaml
├── images
│ └── HICO_test2015_00001000
│ ├── 000
│ ├── 001
│ └── 002
├── meshes
│ └── HICO_test2015_00001000
│ ├── 000.obj
│ ├── 001.obj
│ └── 002.obj
└── results
└── HICO_test2015_00001000
├── 000.pkl
├── 001.pkl
└── 002.pkl
9 directories, 7 files
Here's the image:
The script is:
(smplifyx) [jalal@goku smplify-x]$ pwd
/scratch3/research/code/smplify-x
(smplifyx) [jalal@goku smplify-x]$ cat djrn_fit_fail_test.sh
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_test_data_00001000/ --output_folder ../../data/smplify-x/results_djrn_test_data_00001000 --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
Previously, the same image failed with this error: "NaN loss value"
I get that one of the obj files shown in MeshLab is the lady holding a kite but what about the other two obj files?
In which file, is concatenated the word embedding and 18 point clouds of part set?
In the feature extraction step(Extract feature using PointNet), in which file, is concatenated the word embedding and 18 point clouds of part set?. That is part" 4.2. 3D Feature Extraction ( for the feature of part set, we concatenate it with PCA
reduced word embedding )"of your article?
Would you mind to provide 3d features extracted by SMPL-X?
Hi, Thanks for your work. Since the project has used many 3D features extracted by SMPL-X, would you mind provide the features that you have extracted like 2d pose pickle file? I guess it would be easy to follow you work.
Could you please share the results of running smplify-x on the hico-det dataset?
In order to reproduce the results, could you please share the smplify-x results for hico-det images?
When I run smplify-x on the dataset, for some images I get NaN loss so it stops.
It would be great if you could share your own results.
Run SMPLify-X on the dataset with the filtered pose.
For example, here's one such image:
hico_test2015_00001000.jpg
model:vposer TR00_E096.pt
NaN loss value
the value of loss is NaN
At the time of training, in the step "python tools/Train_HICO_DET_DJR.py --model --num_iteration 400000 "o, the value of loss in all of the images in NaN. why????
using -Result for folder name seems to cause some problems in Linux
while I can access the -Result folder from the GUI, I cannot $ cd into it. I suggest using a different name for the folder name.
[156225:2271 0:620] 05:05:43 Thu Dec 24 [mona@goku:pts/11 +1] ~/research/code/DJ-RN
$ cd -Results/
bash: cd: -R: invalid option
cd: usage: cd [-L|[-P [-e]] [-@]] [dir]
- in Linux commands is usually reserved for flags and args and that's why cd command is confused.
what is the number of Restore_flag?
I have two questions.
what is the number of Restore_flag?Based on the iCAN method, I put the number= 5.
when I run python tools/Test_HICO_DET_DJR.py --model --iteration 400000 " I have following error
ValueError: Dimensions must be equal, but are 17 and 1228 for 'attention_3D/MatMul' (op: 'MatMul') with input shapes: [?,17], [1228,17].
iles part-w2v.pkl and obj-w2v.pk
Hello
How are files part-w2v.pkl and obj-w2v.pk created and can you explain what they are? At this stage, different parts of the body are not identified? For example, what are the the fingers of hands?
What constitutes an ambiguous HOI?
Could you be a bit more specific about what constitutes an ambiguous HOI? For example, in the image below, I am not sure why is it ambiguous?
Thanks a bunch,
Mona
there is not merge_for_ambi.py
hello
I want to implement your code.
I run "Generate_Ambiguous_HOI.sh". In last line there is "python script/merge_for_ambi.py" but there is not any file "merge_for_ambi.py" in script folder.
line 45 of script/Download_data.py should change from `is not` to `!=`
https://github.com/DirtyHarryLYL/DJ-RN/blob/master/script/Download_data.py
throws errors:
(djrn) [jalal@goku DJ-RN]$ python script/Download_data.py 1l48pyX-9FWFMNuokdbBp6KshKSDBihAe Feature_extraction.tar
script/Download_data.py:45: SyntaxWarning: "is not" with a literal. Did you mean "!="?
if len(sys.argv) is not 3:
How is the gt_hoi_py2.pkl file created
Hello, how is the gt_hoi_py2.pkl file created? In what part of codes is it created and what is it?
There is not the folder HICO_train2015_00000149 in spatial_configuration_Neg folder
Hello
In run of python script/concat_w2v.py --SMPLX_PATH --GT ./Data/Trainval_GT_HICO_with_idx.pkl --Neg Trainval_Neg_HICO_with_idx.pkl --Test Test_Faster_RCNN_R-50-PFN_2x_HICO_DET_with_idx.pkl, I got following error:
Traceback (most recent call last):
File "script/concat_w2v.py", line 76, in
pc = pickle.load(open(args.SMPLX_PATH + '/spatial_configuration_Neg/HICO_train2015_%08d/%03d_feature.pkl' % (key, i), 'rb'))
FileNotFoundError: [Errno 2] No such file or directory: '/home/spatial_configuration_Neg/HICO_train2015_00000149/000_feature.pkl'
There is not the folder HICO_train2015_00000149 in spatial_configuration_Neg folder but there is in results(pkl files) folder!!
How to run the demo code for my own images?
I am interested in running the Demo.ipynb for my own images. However, I am not sure where to create these .pkl files?
[812147:3298 0:1481] 04:37:55 Thu Dec 31 [mona@goku:pts/1 +1] ~/research/code/DJ-RN
$ fd hbox.pkl
script/demo/hbox.pkl
9201/31772MB
[812147:3298 0:1482] 04:38:01 Thu Dec 31 [mona@goku:pts/1 +1] ~/research/code/DJ-RN
$ rg hbox.pkl
script/test.py
18:hbox = pickle.load(open('demo/hbox.pkl', 'rb'))
script/Demo.ipynb
59: "hbox = pickle.load(open('demo/hbox.pkl', 'rb'))\n",
and:
[812147:3298 0:1482] 04:38:01 Thu Dec 31 [mona@goku:pts/1 +1] ~/research/code/DJ-RN
$ rg hbox.pkl
script/test.py
18:hbox = pickle.load(open('demo/hbox.pkl', 'rb'))
script/Demo.ipynb
59: "hbox = pickle.load(open('demo/hbox.pkl', 'rb'))\n",
9201/31772MB
[812147:3298 0:1483] 04:38:09 Thu Dec 31 [mona@goku:pts/1 +1] ~/research/code/DJ-RN
$ rg *pkl
script/Download_result.sh
7:python script/Download_data.py 10nUe9ruH7ZPTEh8WuV7lRCrRMCGFocKz ./-Results/400000_DJR_ambiguous.pkl.tar.gz
9:tar -xvzf 400000_DJR_ambiguous.pkl.tar.gz
10:rm -rf 400000_DJR_ambiguous.pkl.tar.gz
README.md
224:`python ./-Results/Evaluate_ambiguous.py ./-Results/400000_DJR_ambiguous.pkl DJR_ambiguous/`
9201/31772MB
How do you create them for custom images and not coco images? (imagine these custom images have COCO objects).
We have the following in one of the Demo.ipynb cells:
args = Arguments(gender='male', smplx_path='/home/mona/research/code/DJ-RN/models/smplx/')
obj_name = 'keyboard'
result = pickle.load(open('demo/result.pkl', 'rb'))
hbox = pickle.load(open('demo/hbox.pkl', 'rb'))
obox = pickle.load(open('demo/obox.pkl', 'rb'))
mesh = 'demo/human.obj'
img = 'demo/sample.jpg'
what is the expected result for this line of code `point_align_vis(result, obox, 'demo/object.obj', img)` in Demo.ipynb?
After running this cell, a config.obj is dumped which I visualized it with meshlab. However, I am not sure where object.obj is supposed to come from or if it should be shared by you and what's the relation of it to config.obj to object.obj?
errors in bash script
[128][mona.goku: DJ-RN]$ bash script/Generate_Ambiguous_HOI.sh
script/Generate_Ambiguous_HOI.sh: line 2: $'\r': command not found
script/Generate_Ambiguous_HOI.sh: line 3: cd: $'Data\r': No such file or directory
script/Generate_Ambiguous_HOI.sh: line 4: $'\r': command not found
script/Download_data.py:45: SyntaxWarning: "is not" with a literal. Did you mean "!="?
if len(sys.argv) is not 3:
^CTraceback (most recent call last):
File "script/Download_data.py", line 52, in <module>
download_file_from_google_drive(file_id, destination)
File "script/Download_data.py", line 40, in download_file_from_google_drive
save_response_content(response, destination)
File "script/Download_data.py", line 27, in save_response_content
f.write(chunk)
KeyboardInterrupt
The file generate_3D_obj_GT.py
Hello, it is possible to upload the correct files
I do not think file generate_3D_obj_GT.py is correct. When I run it, for example for image "HICO_train2015_00000001", there is a file 000.pkl in the results folder of --res, but when I run generate_3D_obj_GT.py, it has a value of -1 in the openpose index. Can you please look at it and rewrite it?
correction in the file ult.py
Hello
You did not specify the second argument in line 261 of file ult.py(pc.append(pickle.load(open(config.cfg.SMPLX_PATH + '/object_GT/HICO_train2015_%08d/%03d_feature.pkl' % i, 'rb'))[None, ...])) .
I changed it to "pc.append(pickle.load(open(config.cfg.Spatial + '/object_GT/HICO_train2015_%08d/%03d_feature.pkl' % (image_id, i), 'rb'))[None, ...])"
I told you to correct it too
A long and inexhaustible output in feature extraction
Hello
when I run "python Feature_extraction.py --input_list script/vertex_path_GT.txt --model_path ../Feature_extraction/model_10000.ckpt"
Some of my output is as follows and its execution is very long and does not end. is it correct?
2021-01-01 06:17:17.013778: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tconv3/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tconv3/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013796: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tconv3/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/Reshape/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013815: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/Reshape/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/weights/Initializer/random_uniform/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013832: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/weights/Initializer/random_uniform/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/weights/Initializer/random_uniform/min: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013859: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/weights/Initializer/random_uniform/min: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/weights/Initializer/random_uniform/max: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013876: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/weights/Initializer/random_uniform/max: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/weight_loss/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013894: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/weight_loss/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013910: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013928: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/Const_1: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013946: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/Const_1: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/moments/mean/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013964: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/moments/mean/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/moments/variance/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013982: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/moments/variance/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/transform_net2/tfc1/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.013999: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/transform_net2/tfc1/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/transform_net2/tfc1/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014016: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/transform_net2/tfc1/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/cond/ExponentialMovingAverage/decay: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014034: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/cond/ExponentialMovingAverage/decay: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014049: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014066: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc1/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014084: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc1/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/weights/Initializer/random_uniform/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014101: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/weights/Initializer/random_uniform/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/weights/Initializer/random_uniform/min: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014117: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/weights/Initializer/random_uniform/min: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/weights/Initializer/random_uniform/max: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014134: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/weights/Initializer/random_uniform/max: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/weight_loss/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014152: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/weight_loss/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014169: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014186: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/Const_1: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014204: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/Const_1: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/moments/mean/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014222: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/moments/mean/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/moments/variance/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014241: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/moments/variance/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/transform_net2/tfc2/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014258: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/transform_net2/tfc2/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/transform_net2/tfc2/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014275: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/transform_net2/tfc2/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/cond/ExponentialMovingAverage/decay: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014294: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/cond/ExponentialMovingAverage/decay: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014311: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014327: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/tfc2/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014345: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/tfc2/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/transform_feat/weights/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014361: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/transform_feat/weights/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/transform_feat/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014377: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/transform_feat/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/transform_feat/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014396: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/transform_feat/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
transform_net2/Reshape_1/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014414: I tensorflow/core/common_runtime/placer.cc:927] transform_net2/Reshape_1/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
ExpandDims_1/dim: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014432: I tensorflow/core/common_runtime/placer.cc:927] ExpandDims_1/dim: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/weights/Initializer/random_uniform/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014448: I tensorflow/core/common_runtime/placer.cc:927] conv3/weights/Initializer/random_uniform/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/weights/Initializer/random_uniform/min: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014465: I tensorflow/core/common_runtime/placer.cc:927] conv3/weights/Initializer/random_uniform/min: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/weights/Initializer/random_uniform/max: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014480: I tensorflow/core/common_runtime/placer.cc:927] conv3/weights/Initializer/random_uniform/max: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/weight_loss/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014496: I tensorflow/core/common_runtime/placer.cc:927] conv3/weight_loss/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014513: I tensorflow/core/common_runtime/placer.cc:927] conv3/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014543: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/Const_1: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014562: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/Const_1: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/moments/mean/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014580: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/moments/mean/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/moments/variance/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014598: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/moments/variance/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/conv3/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014614: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/conv3/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/conv3/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014631: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/conv3/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/cond/ExponentialMovingAverage/decay: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014649: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/cond/ExponentialMovingAverage/decay: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014665: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014681: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv3/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014699: I tensorflow/core/common_runtime/placer.cc:927] conv3/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/weights/Initializer/random_uniform/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014716: I tensorflow/core/common_runtime/placer.cc:927] conv4/weights/Initializer/random_uniform/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/weights/Initializer/random_uniform/min: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014733: I tensorflow/core/common_runtime/placer.cc:927] conv4/weights/Initializer/random_uniform/min: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/weights/Initializer/random_uniform/max: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014749: I tensorflow/core/common_runtime/placer.cc:927] conv4/weights/Initializer/random_uniform/max: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/weight_loss/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014768: I tensorflow/core/common_runtime/placer.cc:927] conv4/weight_loss/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014784: I tensorflow/core/common_runtime/placer.cc:927] conv4/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014801: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/Const_1: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014819: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/Const_1: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/moments/mean/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014836: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/moments/mean/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/moments/variance/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014865: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/moments/variance/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/conv4/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014882: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/conv4/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/conv4/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014899: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/conv4/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/cond/ExponentialMovingAverage/decay: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014917: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/cond/ExponentialMovingAverage/decay: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014933: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014949: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv4/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014967: I tensorflow/core/common_runtime/placer.cc:927] conv4/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/weights/Initializer/random_uniform/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.014983: I tensorflow/core/common_runtime/placer.cc:927] conv5/weights/Initializer/random_uniform/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/weights/Initializer/random_uniform/min: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015000: I tensorflow/core/common_runtime/placer.cc:927] conv5/weights/Initializer/random_uniform/min: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/weights/Initializer/random_uniform/max: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015016: I tensorflow/core/common_runtime/placer.cc:927] conv5/weights/Initializer/random_uniform/max: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/weight_loss/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015035: I tensorflow/core/common_runtime/placer.cc:927] conv5/weight_loss/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015051: I tensorflow/core/common_runtime/placer.cc:927] conv5/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015069: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/Const_1: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015086: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/Const_1: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/moments/mean/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015104: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/moments/mean/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/moments/variance/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015122: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/moments/variance/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/conv5/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros/shape_as_tensor: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015139: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/conv5/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros/shape_as_tensor: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/conv5/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015156: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/conv5/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/conv5/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros/shape_as_tensor: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015174: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/conv5/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros/shape_as_tensor: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/conv5/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015191: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/conv5/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/cond/ExponentialMovingAverage/decay: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015210: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/cond/ExponentialMovingAverage/decay: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015225: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015242: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv5/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015260: I tensorflow/core/common_runtime/placer.cc:927] conv5/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
Tile/multiples: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015278: I tensorflow/core/common_runtime/placer.cc:927] Tile/multiples: (Const)/job:localhost/replica:0/task:0/device:CPU:0
concat/axis: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015296: I tensorflow/core/common_runtime/placer.cc:927] concat/axis: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/weights/Initializer/random_uniform/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015313: I tensorflow/core/common_runtime/placer.cc:927] conv6/weights/Initializer/random_uniform/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/weights/Initializer/random_uniform/min: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015329: I tensorflow/core/common_runtime/placer.cc:927] conv6/weights/Initializer/random_uniform/min: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/weights/Initializer/random_uniform/max: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015345: I tensorflow/core/common_runtime/placer.cc:927] conv6/weights/Initializer/random_uniform/max: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/weight_loss/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015363: I tensorflow/core/common_runtime/placer.cc:927] conv6/weight_loss/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015378: I tensorflow/core/common_runtime/placer.cc:927] conv6/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015396: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/Const_1: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015413: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/Const_1: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/moments/mean/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015432: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/moments/mean/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/moments/variance/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015450: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/moments/variance/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/conv6/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015467: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/conv6/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/conv6/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015483: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/conv6/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/cond/ExponentialMovingAverage/decay: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015502: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/cond/ExponentialMovingAverage/decay: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015517: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015547: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv6/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015565: I tensorflow/core/common_runtime/placer.cc:927] conv6/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/weights/Initializer/random_uniform/shape: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015582: I tensorflow/core/common_runtime/placer.cc:927] conv7/weights/Initializer/random_uniform/shape: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/weights/Initializer/random_uniform/min: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015598: I tensorflow/core/common_runtime/placer.cc:927] conv7/weights/Initializer/random_uniform/min: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/weights/Initializer/random_uniform/max: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015614: I tensorflow/core/common_runtime/placer.cc:927] conv7/weights/Initializer/random_uniform/max: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/weight_loss/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015632: I tensorflow/core/common_runtime/placer.cc:927] conv7/weight_loss/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/biases/Initializer/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015648: I tensorflow/core/common_runtime/placer.cc:927] conv7/biases/Initializer/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015666: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/Const_1: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015683: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/Const_1: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/moments/mean/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015700: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/moments/mean/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/moments/variance/reduction_indices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015718: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/moments/variance/reduction_indices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/conv7/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015735: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/conv7/bn/moments/Squeeze/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/conv7/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015752: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/conv7/bn/moments/Squeeze_1/ExponentialMovingAverage/Initializer/zeros: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/cond/ExponentialMovingAverage/decay: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015771: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/cond/ExponentialMovingAverage/decay: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015787: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/cond/ExponentialMovingAverage/AssignMovingAvg/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015804: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/cond/ExponentialMovingAverage/AssignMovingAvg_1/sub/x: (Const)/job:localhost/replica:0/task:0/device:CPU:0
conv7/bn/batchnorm/add/y: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015821: I tensorflow/core/common_runtime/placer.cc:927] conv7/bn/batchnorm/add/y: (Const)/job:localhost/replica:0/task:0/device:CPU:0
save/Const: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015837: I tensorflow/core/common_runtime/placer.cc:927] save/Const: (Const)/job:localhost/replica:0/task:0/device:CPU:0
save/SaveV2/tensor_names: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015864: I tensorflow/core/common_runtime/placer.cc:927] save/SaveV2/tensor_names: (Const)/job:localhost/replica:0/task:0/device:CPU:0
save/SaveV2/shape_and_slices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015882: I tensorflow/core/common_runtime/placer.cc:927] save/SaveV2/shape_and_slices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
save/RestoreV2/tensor_names: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015900: I tensorflow/core/common_runtime/placer.cc:927] save/RestoreV2/tensor_names: (Const)/job:localhost/replica:0/task:0/device:CPU:0
save/RestoreV2/shape_and_slices: (Const): /job:localhost/replica:0/task:0/device:CPU:0
2021-01-01 06:17:17.015916: I tensorflow/core/common_runtime/placer.cc:927] save/RestoreV2/shape_and_slices: (Const)/job:localhost/replica:0/task:0/device:CPU:0
Your repo bash scripts are not working in Ubuntu 20.04 (e.g. script/Download_HICO-DET.sh)
[26744:2271 0:477] 01:56:09 Thu Dec 24 [mona@goku:pts/5 +1] ~/research/code/DJ-RN
$ bash script/Download_HICO-DET.sh
script/Download_data.py:45: SyntaxWarning: "is not" with a literal. Did you mean "!="?
if len(sys.argv) is not 3:
^CTraceback (most recent call last):
File "script/Download_data.py", line 52, in <module>
download_file_from_google_drive(file_id, destination)
File "script/Download_data.py", line 40, in download_file_from_google_drive
save_response_content(response, destination)
File "script/Download_data.py", line 25, in save_response_content
for chunk in response.iter_content(CHUNK_SIZE):
File "/home/mona/anaconda3/lib/python3.8/site-packages/requests/models.py", line 751, in generate
for chunk in self.raw.stream(chunk_size, decode_content=True):
File "/home/mona/anaconda3/lib/python3.8/site-packages/urllib3/response.py", line 571, in stream
for line in self.read_chunked(amt, decode_content=decode_content):
File "/home/mona/anaconda3/lib/python3.8/site-packages/urllib3/response.py", line 766, in read_chunked
chunk = self._handle_chunk(amt)
File "/home/mona/anaconda3/lib/python3.8/site-packages/urllib3/response.py", line 710, in _handle_chunk
value = self._fp._safe_read(amt)
File "/home/mona/anaconda3/lib/python3.8/http/client.py", line 612, in _safe_read
data = self.fp.read(amt)
File "/home/mona/anaconda3/lib/python3.8/socket.py", line 669, in readinto
return self._sock.recv_into(b)
File "/home/mona/anaconda3/lib/python3.8/ssl.py", line 1241, in recv_into
return self.read(nbytes, buffer)
File "/home/mona/anaconda3/lib/python3.8/ssl.py", line 1099, in read
return self._sslobj.read(len, buffer)
KeyboardInterrupt
~/anaconda3/lib/python3.8/site-packages/sympy/core/relational.py in __nonzero__(self) def __nonzero__(self): --> raise TypeError("cannot determine truth value of Relational") __bool__ = __nonzero__ TypeError: cannot determine truth value of Relational
[2275:2264 0:874] 04:39:04 Mon Dec 28 [mona@goku:pts/0 +1] ~/research/code/DJ-RN
$ jupyter notebook script/Demo.ipynb
[I 16:39:29.474 NotebookApp] JupyterLab extension loaded from /home/mona/anaconda3/lib/python3.8/site-packages/jupyterlab
[I 16:39:29.474 NotebookApp] JupyterLab application directory is /home/mona/anaconda3/share/jupyter/lab
[I 16:39:29.476 NotebookApp] Serving notebooks from local directory: /home/mona/research/code/DJ-RN/script
[I 16:39:29.476 NotebookApp] Jupyter Notebook 6.1.4 is running at:
[I 16:39:29.476 NotebookApp] http://localhost:8888/?token=ed04804c4785efa549ed6b7f373fe606fa2badb1e25d8f75
[I 16:39:29.476 NotebookApp] or http://127.0.0.1:8888/?token=ed04804c4785efa549ed6b7f373fe606fa2badb1e25d8f75
[I 16:39:29.476 NotebookApp] Use Control-C to stop this server and shut down all kernels (twice to skip confirmation).
[C 16:39:29.493 NotebookApp]
To access the notebook, open this file in a browser:
file:///home/mona/.local/share/jupyter/runtime/nbserver-11549-open.html
Or copy and paste one of these URLs:
http://localhost:8888/?token=ed04804c4785efa549ed6b7f373fe606fa2badb1e25d8f75
or http://127.0.0.1:8888/?token=ed04804c4785efa549ed6b7f373fe606fa2badb1e25d8f75
[I 16:39:32.152 NotebookApp] Kernel started: 5871d55e-f252-4110-b43e-a313913be130, name: python3
When I run the following cell:
list_hoi, order_obj_list, obj_para_dict = get_order_obj()
htri = trimesh.load(mesh)
vertice = np.array(htri.vertices,dtype=np.float32)
joints = get_joints(args, torch.FloatTensor(torch.from_numpy(vertice.reshape(1,-1,3))))
shoulder_len = np.linalg.norm(joints[16] - joints[17])
radius = obj_para_dict[obj_name]['ratio'] * shoulder_len
gamma_min = obj_para_dict[obj_name]['gamma_min']
gamma_max = obj_para_dict[obj_name]['gamma_max']
otri, _ = get_param(result, hbox, obox, htri, img, radius, gamma_min, gamma_max)
config = htri + otri
ansp = rotate(joints - joints[0])
vertices = np.array(config.vertices)
vertices = vertices - joints[0]
vertices = rotate_mul(vertices, ansp)
config = trimesh.Trimesh(vertices=vertices, faces=config.faces)
_ = config.export('demo/config.obj')
I get this error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-7-1f1789b8332d> in <module>
7 gamma_min = obj_para_dict[obj_name]['gamma_min']
8 gamma_max = obj_para_dict[obj_name]['gamma_max']
----> 9 otri, _ = get_param(result, hbox, obox, htri, img, radius, gamma_min, gamma_max)
10 config = htri + otri
11 ansp = rotate(joints - joints[0])
~/research/code/DJ-RN/script/generate_utils.py in get_param(result, hbox, obox, htri, img, radius, gamma_min, gamma_max)
246 y2D = (-ansy + _t2) / (ansz + _t3) * _focal_length
247 x2D = (-ansx + _t1) / (ansz + _t3) * _focal_length
--> 248 if (((y2D >= obox[1]) and (y2D <= obox[3])) or ((y2D <= obox[1]) and (y2D >= obox[3]))):
249 idx = i
250
~/anaconda3/lib/python3.8/site-packages/sympy/core/relational.py in __nonzero__(self)
382
383 def __nonzero__(self):
--> 384 raise TypeError("cannot determine truth value of Relational")
385
386 __bool__ = __nonzero__
TypeError: cannot determine truth value of Relational
Please let me know if you have any suggestions.
which SMPLX should I download? Does it work also with 2020 version that has FLAME blendshapes?
Could you please comment if both versions are compatible with yours?
The 3D coordinates of the center of the sphere and the points of the human body are in the same coordinate?
Thanks again,
The 3D coordinates of the center of the sphere and the points of the human body are in the same coordinate? I mean are they using the global coordinates? I want to use their relative distance from each other
No image gets dumped in the subfolders of "images" folder when running smplifyx/main.py on HICO-DET train images
Thanks a lot for maintaining this great and very useful HOI GitHub Repo.
Do you expect to have some images saved in the images directory? for me it creates the subdirectories such as 000 but nothing is saved while obj in meshes folder and pkl files in result folder is saved. Thanks a lot for any feedback.
Here's an example output of result directory:
(smplifyx) [jalal@goku djrn_train_results]$ tree .
.
├── conf.yaml
├── images
│ ├── HICO_train2015_00000001
│ │ └── 000
│ ├── HICO_train2015_00000004
│ │ ├── 000
│ │ ├── 001
│ │ └── 002
│ ├── HICO_train2015_00000005
│ │ └── 000
│ ├── HICO_train2015_00000006
│ │ └── 000
│ └── HICO_train2015_00000009
│ ├── 000
│ └── 001
├── meshes
│ ├── HICO_train2015_00000001
│ │ └── 000.obj
│ ├── HICO_train2015_00000004
│ │ ├── 000.obj
│ │ ├── 001.obj
│ │ └── 002.obj
│ ├── HICO_train2015_00000005
│ │ └── 000.obj
│ ├── HICO_train2015_00000006
│ │ └── 000.obj
│ └── HICO_train2015_00000009
│ └── 000.obj
└── results
├── HICO_train2015_00000001
│ └── 000.pkl
├── HICO_train2015_00000004
│ ├── 000.pkl
│ ├── 001.pkl
│ └── 002.pkl
├── HICO_train2015_00000005
│ └── 000.pkl
├── HICO_train2015_00000006
│ └── 000.pkl
└── HICO_train2015_00000009
└── 000.pkl
26 directories, 15 files
I ran this code:
$ python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_train_data/ --output_folder ../../data/smplify-x/djrn_train_results --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
Request for vertex_path_GT.txt file or the exact procedure for recreating it
I am running one of the steps in the README.md:
python Feature_extraction.py --input_list script/vertex_path_GT.txt --model_path ../Feature_extraction/model_10000.ckpt
and it requires a file that isn't in script folder.
Could you please share these files:
vertex_path_GT.txt
vertex_path_Neg.txt
vertex_path_Test.txt
features with size 1228*256
In step "python script/concat_w2v.py --SMPLX_PATH --GT ./Data/Trainval_GT_HICO_with_idx.pkl --Neg Trainval_Neg_HICO_with_idx.pkl --Test Test_Faster_RCNN_R-50-PFN_2x_HICO_DET_with_idx.pkl, the size of some features in negative samples does not change, ie they do not have a size of 1228 x 384 and they have a size of 1228 x 256, as in image \HICO_train2015_00000057
where is transfer_py3-py2.py
Hello
In "Transfer the results to fit in Python 2.7" step: python script/transfer_py3-py2.py --res
I dont see any transfer_py3-py2.py in script folder. where is this file?
For obj_index=10 the scores matrix have no value
Hello
when I run "python ./-Results/Generate_detection.py --model /home/DJ-RN-master/-Results/400000_DJR"
I have this error:
Traceback (most recent call last):
File "./-Results/Generate_detection.py", line 27, in
scores[obj_index] = np.concatenate(scores[obj_index], axis=0)
File "<array_function internals>", line 6, in concatenate
ValueError: need at least one array to concatenate
For obj_index=10 the scores matrix have no value. What do I do?
According to this output, how do I know where the coordinates of the elbow are?
Hello
According to this output, how do I know where the coordinates of the elbow are?
$ python script/filter_pose.py --ori openpose --fil filtered_results/ yields no result
After I run step 3, nothing happens. Could you please let me know what you expect to happen in the filtered_result folder that I have made?
416/31773MB
[94060:2271 0:603] 04:17:23 Thu Dec 24 [mona@goku:pts/9 +1] ~/research/code/DJ-RN
$ python script/filter_pose.py --ori openpose --fil filtered_results/
416/31773MB
[94060:2271 0:604] 04:17:28 Thu Dec 24 [mona@goku:pts/9 +1] ~/research/code/DJ-RN
$ ls filtered_results/
total 8.0K
drwxrwxr-x 14 mona mona 4.0K Dec 24 16:17 ..
drwxrwxr-x 2 mona mona 4.0K Dec 24 16:17 .
415/31773MB
[94060:2271 0:605] 04:17:33 Thu Dec 24 [mona@goku:pts/9 +1] ~/research/code/DJ-RN
$ ls openpose
total 3.2M
drwxrwsr-x 2 mona mona 624K Sep 16 2019 openpose_hico_test
drwxrwsr-x 2 mona mona 2.5M Nov 7 2019 openpose_hico_train
drwxrwxr-x 4 mona mona 4.0K Dec 24 14:39 .
drwxrwxr-x 14 mona mona 4.0K Dec 24 16:17 ..
How are the files part-w2v.pkl and obj-w2v.pk created
Hello
How are the files part-w2v.pkl and obj-w2v.pk created and can you explain what they are? At this stage, different parts of the body are not identified? For example, what are the specifics of the fingers?
How did you speed up running SPMLify-X on > 33K images?
I am in step 4, creating SMPLify-X results which is pretty much slow (no matter if I run it on a GPU with 4 or 12G memory).
Could you please share any tip how long did it take you or how did you speed it up? Currently the code doesn't seem to have any batch_size supported and uses at max 2G of memory.
vchoutas/smplify-x#78
27125+6823 = 33948 images
FYI, after nearly 2 hours, I only got to process 100 images.
[88339:3149 0:2078] 07:04:29 Mon Jan 11 [mona@goku:pts/2 +1] ~/research/data/smplify-x/djrn_train_data/images
$ ls *.jpg | wc -l
27125
1329/31772MB
[88339:3149 0:2079] 07:04:39 Mon Jan 11 [mona@goku:pts/2 +1] ~/research/data/smplify-x/djrn_train_data/images
$ cd ../../djrn_test_data/images/
1354/31772MB
[88339:3149 0:2080] 07:04:57 Mon Jan 11 [mona@goku:pts/2 +1] ~/research/data/smplify-x/djrn_test_data/images
$ ls *.jpg | wc -l
6823
How can I get the GT and Neg data?
Would you like to explain about the GT and Neg data in step5 of Data generation. In the previous steps, I only get the dataset divided into train and test. Thank you very much!
about the openpose results fed into the smpl-x model
Thanks for sharing the great work, but I meet some problems with the openpose results:
- what are the formats/dimensions of the 2D parameters theta_b^2D,theta_h^2D, ..? Are they the coordinates of the corresponding keypoints? And are there any conversions before feeding them into the smpl-x model ?
- could you provide the corresponding codes or instruction for running the step 4 in the data generation? Run SMPLify-X on the dataset with the filtered pose.
- this question may not be so relevant to this work. Is it possible to get the 3D joint locations from the smpl-x model?
Data generation Run OpenPose for the images in the dataset.
Data generation
Run OpenPose for the images in the dataset.
Alphapose ?
How should I exactly run the script/assign_pose_GT.py script?
How do you run the following script for both train and test portions of HICO-DET dataset since, in step 4, I had to run it separately for the train and test portion?
The script/assign_pose_GT.py dumps the results into a file called Data/Trainval_GT_HICO_with_idx.pkl
$ python script/assign_pose_GT.py --pose ../../data/smplify-x/djrn_test_data/ --res ../../data/smplify-x/djrn_test_results
Do you only run it on the train portion of the hico_det dataset? I ask because I ran it on the test portion of the hico_det dataset and didn't get an error however the following lines of the script perhaps hint we should run it on the train portion?
Previously, I ran the following two scripts in step 4 of data processing:
For train portion of HICO-DET:
export CUDA_VISIBLE_DEVICES=0
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_train_data/ --output_folder ../../data/smplify-x/djrn_train_results --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
For test portion of HICO-DET:
python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder ../../data/smplify-x/djrn_test_data/ --output_folder ../../data/smplify-x/djrn_test_results --visualize="False" --model_folder ../../data/smplify-x/models_smplx_v1_1/models/smplx/SMPLX_NEUTRAL.npz --vposer_ckpt ../../data/smplify-x/vposer_v1_0 --part_segm_fn ../../data/smplify-x/smplx_parts_segm.pkl
Additionally, if you could please provide some comments on what this script does at a higher level? That would be very helpful.
if os.path.exists(os.path.join(args.pose, 'HICO_train2015_%08d_keypoints.json' % key)):
f = json.load(open(os.path.join(args.pose, 'HICO_train2015_%08d_keypoints.json' % key)))
for i in range(len(f['people'])):
tmp = np.array(f['people'][i]['pose_keypoints_2d'])
if not os.path.exists(os.path.join(args.res, 'results/HICO_train2015_%08d/%03d.pkl' % (key, i))):
continue
body_pose = tmp.reshape(-1, 3)[body25_to_coco, :2]
tmp_sum = np.sum(body_pose, axis=1)
sel = np.where(tmp_sum > 0)[0]
body_pose = body_pose[sel, :]
for j in range(len(data[key])):
if data[key][j][5] is not None:
alphapose = np.array(data[key][j][5]).reshape(-1, 3)[sel, :2]
dis = calc_mse(body_pose, alphapose)
if (used[j] < 0 and dis < 500) or (dis < used[j]):
used[j] = dis
data[key][j][-1] = i
pickle.dump(data, open('Data/Trainval_GT_HICO_with_idx.pkl', 'wb'), protocol=2)
the point clouds file
Thanks for your pretty code Detailed 2D-3D Joint Representation for Human-Object Interaction.
I do not have a GPU and I can not get point clouds with my PC and it is not possible for me to run step 4 of "Data generation" phase. My possibilities are limited.
I want point clouds of humans and objects. Were you able to generate the point clouds with low space?
point_align_vis(result, obox, 'demo/object.obj', img) File "/home/mona/research/code/DJ-RN/script/generate_utils.py", line 114, in point_align_vis with open(mesh) as f: FileNotFoundError: [Errno 2] No such file or directory: 'demo/object.obj'
When I run the test.py that I have placed in script folder, I get the following error. Could you please share the object.obj?
[719535:3298 0:1345] 11:30:08 Wed Dec 30 [mona@goku:pts/17 +1] ~/research/code/DJ-RN/script
$ python test.py
Traceback (most recent call last):
File "test.py", line 43, in <module>
point_align_vis(result, obox, 'demo/object.obj', img)
File "/home/mona/research/code/DJ-RN/script/generate_utils.py", line 114, in point_align_vis
with open(mesh) as f:
FileNotFoundError: [Errno 2] No such file or directory: 'demo/object.obj'
In the demo folder, there is no object.obj file:
[719535:3298 0:1342] 11:29:22 Wed Dec 30 [mona@goku:pts/17 +1] ~/research/code/DJ-RN
$ ls script/demo/
total 1.8M
-rw-rw-r-- 1 mona mona 304K Dec 23 19:16 sample.jpg
-rw-rw-r-- 1 mona mona 1.2K Dec 23 19:16 result.pkl
-rw-rw-r-- 1 mona mona 188 Dec 23 19:16 obox.pkl
-rw-rw-r-- 1 mona mona 713K Dec 23 19:16 human.obj
-rw-rw-r-- 1 mona mona 188 Dec 23 19:16 hbox.pkl
drwxrwxr-x 2 mona mona 4.0K Dec 23 19:16 .
drwxrwxr-x 5 mona mona 4.0K Dec 30 23:27 ..
-rw-rw-r-- 1 mona mona 727K Dec 30 23:27 config.obj
Here's the test.py which is basically your jupyter notebook:
$ cat test.py
import os
import os.path as osp
import numpy as np
import pickle
import trimesh
import torch
from generate_utils import get_order_obj, get_joints, get_param, point_align_vis, rotate, rotate_mul
class Arguments():
def __init__(self, gender, smplx_path):
self.gender = gender
self.smplx_path = smplx_path
args = Arguments(gender='male', smplx_path='/home/mona/research/code/DJ-RN/models/smplx/')
obj_name = 'keyboard'
result = pickle.load(open('demo/result.pkl', 'rb'))
hbox = pickle.load(open('demo/hbox.pkl', 'rb'))
obox = pickle.load(open('demo/obox.pkl', 'rb'))
mesh = 'demo/human.obj'
img = 'demo/sample.jpg'
list_hoi, order_obj_list, obj_para_dict = get_order_obj()
htri = trimesh.load(mesh)
vertice = np.array(htri.vertices,dtype=np.float32)
joints = get_joints(args, torch.FloatTensor(torch.from_numpy(vertice.reshape(1,-1,3))))
shoulder_len = np.linalg.norm(joints[16] - joints[17])
radius = obj_para_dict[obj_name]['ratio'] * shoulder_len
gamma_min = obj_para_dict[obj_name]['gamma_min']
gamma_max = obj_para_dict[obj_name]['gamma_max']
otri, _ = get_param(result, hbox, obox, htri, img, radius, gamma_min, gamma_max)
config = htri + otri
ansp = rotate(joints - joints[0])
vertices = np.array(config.vertices)
vertices = vertices - joints[0]
vertices = rotate_mul(vertices, ansp)
config = trimesh.Trimesh(vertices=vertices, faces=config.faces)
_ = config.export('demo/config.obj')
point_align_vis(result, hbox, 'demo/human.obj', img)
point_align_vis(result, obox, 'demo/object.obj', img)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.