Comments (2)
I got this error as well. I'm reinstalling again (after reinstalling Miniconda) but I remember getting similar errors. My thoughts now is that the ./fetch_data.sh doesn't actually download the required file. I'm going to manually download it to /4D-Humans and then run "tar -xvf hmr2_data.tar.gz" and see what happens. I think it might work based on the output so far:
PS M:\AIStuff\4D-Humans> tar -xvf hmr2_data.tar.gz
x logs/train/multiruns/hmr2/
x logs/train/multiruns/hmr2/0/
x logs/train/multiruns/hmr2/0/model_config.yaml
x logs/train/multiruns/hmr2/0/checkpoints/
x logs/train/multiruns/hmr2/0/checkpoints/epoch=35-step=1000000.ckpt
x logs/train/multiruns/hmr2/0/dataset_config.yaml
x data/
x data/SMPL_to_J19.pkl
x data/smpl_mean_params.npz
x data/smpl/
x data/smpl/SMPL_MALE.pkl
x data/smpl/SMPL_FEMALE.pkl
x data/smpl/SMPL_NEUTRAL.pkl
EDIT: I think manually downloading the file from "https://people.eecs.berkeley.edu/~shubham-goel/projects/4DHumans/hmr2_data.tar.gz" into your /4D-Humans dir is the correct solution. Once downloaded, open terminal or cmd or whatever and run tar -xvf hmr2_data.tar.gz
Finally, you can run python demo.py --img_folder example_data/images --out_folder demo_out --batch_size=48 --side_view and wait a few moments for it to do its thing and then check \4D-Humans\demo_out
Here's my full terminal output (after doing the above and activating the venv) for reference:
(4D-humans) PS M:\AIStuff\4D-Humans> python demo.py --img_folder example_data/images --out_folder demo_out --batch_size=48 --side_view
Lightning automatically upgraded your loaded checkpoint from v1.8.1 to v2.0.2. To apply the upgrade to your files permanently, run `python -m pytorch_lightning.utilities.upgrade_checkpoint --file M:\AIStuff\4D-Humans\logs\train\multiruns\hmr2\0\checkpoints\epoch=35-step=1000000.ckpt`
WARNING: You are using a SMPL model, with only 10 shape coefficients.
model_final_f05665.pkl: 2.77GB [00:43, 63.5MB/s]
C:\ProgramData\Miniconda3\envs\4D-humans\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\TensorShape.cpp:3484.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
downsampling_factor=11.122115135192871
(4D-humans) PS M:\AIStuff\4D-Humans>
from 4d-humans.
Yes, the extraction was the problem. I was using command line 7zip.
For Windows you must use the tar command to extract it fully.
tar -xvf hmr2_data.tar.gz
Then the script runs fine.
from 4d-humans.
Related Issues (20)
- Multi gpu training HOT 1
- Visualization of the reconstructed human mesh HOT 2
- Unable to download hmr2_data.tar.gz HOT 2
- A colab error about tracking HOT 2
- The meaning of 'NUM_TRAIN_SAMPLES', 'NUM_TEST_SAMPLES' and the question of the discriminator.
- PHALP tracker taking lot of CPU utilization HOT 1
- Can not import expand_bbox_to_aspect_ratio from hmr2.datasets.utills HOT 1
- about the training data,do you use EFT fits or what? HOT 6
- how about using smpl 49 keypoints(like spin did) instead of your smpl 44 keypoints? will the result be worse? HOT 2
- Is it easy to train this work with 4 V100 24G or 8 3090 24G? (no A100) HOT 1
- Error of downloading training dataset HOT 1
- Is there any specific reason for choosing Detectron2 as human detection model? HOT 1
- Using 4 V100-16, and set batchsize=1, torch.cuda.OutOfMemoryError:
- Have you tried to use a smaller backbone? HOT 1
- use SMPLX model with hands and feet? HOT 2
- Pseudo labels generation
- evaluation datasets image HOT 3
- download problem of hmr2.0a_model.tar.gz HOT 4
- Training data preprocessing
- Why is loss not divided by the batch size? HOT 1
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.
from 4d-humans.