Similarly, update data/ucf101/flow.txt for flow data. Note: we use one file to include x and y part of flow data, so we use {：s} in each line to placehold x or y in the data path. For example, if your flow data are placed like this:

|---tvl1_flow
| |---x
| |--- y
then you can write each line in flow.txt like this:

v_Archery_g01_c06 /data4/zhouhao/dataset/ucf101/tvl1_flow/{:s}/v_Archery_g01_c06 107 2
i.e, use {:s} replace x or y in path. If you are confused, please refer our code to see data loading details.

can anyone tell me how to get the tvl1_flow from? how can i make flow.txt file using it?

----Here we start!----
Output wirtes to output/test-ucf101-rgb-1
Traceback (most recent call last):
File "test.py", line 268, in
main(**vars(p.parse_args()))
File "test.py", line 244, in main
accuracy = true_count / video_size
ZeroDivisionError: division by zero
Exception in thread Thread-1:
Traceback (most recent call last):
File "/data/amax/envs/LEE-tf/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/data/amax/envs/LEE-tf/lib/python2.7/threading.py", line 754, in run
self.__target(*self.__args, **self.__kwargs)
File "/data/amax/LEE/I3D_Finetune-master/lib/feed_queue.py", line 63, in fetch_queue
if self.bridge_queue.empty():
File "", line 2, in empty
File "/data/amax/envs/LEE-tf/lib/python2.7/multiprocessing/managers.py", line 759, in _callmethod
kind, result = conn.recv()
EOFError

Hi, Anyone have worked on multi-gpu training ?
As the dataset becomes large, multi-gpu training becomes crucial.
@vra @AlexHu123 @Rhythmblue Any plan for adding support for multi-gpu or any pointers would be really helpful. Thanks.
Really appreciate your work. Thanks for sharing them with the community.

When I run the finetune.py an error ocurred. Below is the info:

Traceback (most recent call last):
File "finetune.py", line 305, in
main(**vars(p.parse_args()))
File "finetune.py", line 237, in main
feed_dict={dropout_holder: _DROPOUT, is_train_holder: True})
File "/home/liuxuepdf/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/home/liuxuepdf/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/home/liuxuepdf/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/home/liuxuepdf/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: 'NoneType' object is not iterable
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_STRING, DT_STRING], Tout=[DT_FLOAT, DT_INT64], token="pyfunc_0"](arg0, PyFunc/input_1, PyFunc/input_2)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[, ], output_types=[DT_FLOAT, DT_INT64], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Could you please tell me how to solve this error? Thx

(base) junyi@junyi-all-series:/sda1/github/I3D_Finetune$ CUDA_VISIBLE_DEVICES=0 python finetune.py ucf101 rgb 1
2018-07-18 10:12:48.698756: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:05:00.0
totalMemory: 10.91GiB freeMemory: 10.35GiB
2018-07-18 10:12:48.698786: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:05:00.0, compute capability: 6.1)
INFO:tensorflow:Restoring parameters from ./data/checkpoints/rgb_imagenet/model.ckpt
----Here we start!----
Output wirtes to output/finetune-ucf101-rgb-1
2018-07-18 10:13:08.888794: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.61GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-07-18 10:13:08.901823: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.82GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-07-18 10:13:08.974460: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.89GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-07-18 10:13:09.062963: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.54GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-07-18 10:13:09.117757: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.23GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
Epoch1, train accuracy: 0.042
Epoch2, train accuracy: 0.500

Hi,
Thanks a lot for sharing the code!
Could you please sharing your hyper parameter setting on flow? Is data augmnetation only random crop and flip? I cannot reproduce the results on flow.
Thanks a lot!

i3d.py is licensed under Apache License 2.0 - is the rest of the code in this repository being released under the same license as well? Many thanks!

The error infomation is reported as follows:

root@roronoa:~/AI/action_recognition/I3D_Finetune# CUDA_VISIBLE_DEVICES=0 python finetune.py ucf101 rgb 1
2019-03-28 14:58:42.898076: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
INFO:tensorflow:Restoring parameters from ./data/checkpoints/rgb_imagenet/model.ckpt
----Here we start!----
Output wirtes to output/finetune-ucf101-rgb-1
已杀死

pelease allow me submit three questions:
Firstly, I have a GPU named "GeForce GTX 1080" with 8GB size of memory , Is enough to process these frames?
Secondly, when I run "CUDA_VISIBLE_DEVICES=0 python finetune.py ucf101 rgb 1" command in terminal , but as you can see in the error report , GPU is not used , why?
Finally, why the program is killed in the end? Must the "finetune.py" use the GPU?

I realised that the test accuracy is not high, because your RGB training input is [-1,1] range but test input is [0,1] range.

How did the pretrained models trained? With [-1,1] range, or [0,1] range? I think the best is to make it consistent.

Can't find some functions used in test.py. Please provide the code for the following modules.
from zh_lib.dataset import ActionDataset
from zh_lib.load_data import load_info
from zh_lib.feed_queue import FeedQueue
from zh_lib.label_trans import

Hi, i have noticed that there is a

rgb_fc_out = tf.layers.dense(rgb_logits_dropout, _CLASS_NUM[dataset], use_bias=True)

in your test.py. I don't understand about this. This layer looks like have no pretrained parameters, can anybody tell me what the function of this layer is?

It appears that we always call process_video with is_training=True, and therefore each sample of test_dataset has _CLIP_SIZE, not _EACH_VIDEO_TEST_SIZE frames as we would like to have it.

@Rhythmblue @AlexHu123

Hello! I just followed the steps of the project to process the data and try to train, but unfortunately for the UCF101 dataset (I chose two videos for each class) my training accuracy was incredibly low – preferably only five percent! Can someone help me answer my doubts?

When running the test code via CUDA_VISIBLE_DEVICES=0 python test.py ucf101 rgb 1, the number of frames in multiple entries in the data/ucf101/rgb.txt file does not match with the flow and rgb frames downloaded from https://github.com/feichtenhofer/twostreamfusion, resulting in the test code halting at various frames. This issue states that these sources were used for testing. For example, FileNotFoundError: [Errno 2] No such file or directory: /jpegs_256/v_Bowling_g05_c07/frame000113.jpg'
In all cases where the error occurs, 1-3 frames are missing. Was there another version of the ucf101 rgb and flow frames used during testing? Please advise.

when i try to preload /data/checkpoints/rgb_scratch_kin600
NotFoundError (see above for traceback): Key RGB/inception_i3d/Conv3d_1a_7x7/batch_norm/beta not found in checkpoint
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
[[Node: save/RestoreV2_188/_87 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_169_save/RestoreV2_188", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]

hey there i am facing a problem while running this code using python3?
Following is the error i am getting::

CUDA_VISIBLE_DEVICES=0 python3 finetune.py ucf101 rgb 1

WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
  If you depend on functionality not listed there, please file an issue.

WARNING:tensorflow:From finetune.py:67: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, use
tf.py_function, which takes a python function which manipulates tf eager
tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
an ndarray (just call tensor.numpy()) but having access to eager tensors
means tf.py_functions can use accelerators such as GPUs as well as
being differentiable using a gradient tape.

WARNING:tensorflow:From /home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/data/ops/iterator_ops.py:358: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /home/kt-gpu2/I3D_Finetune/i3d.py:466: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use rate instead of keep_prob. Rate should be set to rate = 1 - keep_prob.
WARNING:tensorflow:From finetune.py:164: dense (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dense instead.
WARNING:tensorflow:From /home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
2019-06-21 10:00:14.026572: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-06-21 10:00:14.027276: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x108608f0 executing computations on platform CUDA. Devices:
2019-06-21 10:00:14.027313: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): GeForce GTX 1060 6GB, Compute Capability 6.1
2019-06-21 10:00:14.051709: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3392080000 Hz
2019-06-21 10:00:14.052425: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x108c9540 executing computations on platform Host. Devices:
2019-06-21 10:00:14.052466: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): ,
2019-06-21 10:00:14.052661: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties:
name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.7085
pciBusID: 0000:01:00.0
totalMemory: 5.93GiB freeMemory: 5.59GiB
2019-06-21 10:00:14.052688: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0
2019-06-21 10:00:14.053806: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-06-21 10:00:14.053831: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0
2019-06-21 10:00:14.053843: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N
2019-06-21 10:00:14.053963: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5425 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0, compute capability: 6.1)
WARNING:tensorflow:From /home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from ./data/checkpoints/rgb_imagenet/model.ckpt
----Here we start!----
Output wirtes to output/finetune-ucf101-rgb-1
2019-06-21 10:00:38.094397: I tensorflow/stream_executor/dso_loader.cc:152] successfully opened CUDA library libcublas.so.10.0 locally
2019-06-21 10:00:38.313329: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.313554: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.313737: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.313908: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.314015: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.314833: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.315202: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.315623: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.316223: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.316574: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.316712: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.316893: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.317196: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.318366: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.319143: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.319225: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.319289: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.319359: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.319773: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.320081: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.320165: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.321204: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.321324: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.321419: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.321539: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.321618: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.322982: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.323504: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.323633: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.323859: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.323959: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.324091: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.324178: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.324518: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.326011: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.326203: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.326359: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.326454: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.326676: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.326851: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2019-06-21 10:00:38.327013: W tensorflow/core/framework/op_kernel.cc:1389] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

Traceback (most recent call last):
File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call
return fn(*args)
File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

 [[{{node PyFunc}}]]
 [[{{node IteratorGetNext}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "finetune.py", line 293, in
main(**vars(p.parse_args()))
File "finetune.py", line 232, in main
feed_dict={dropout_holder: _DROPOUT, is_train_holder: True})
File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run
run_metadata)
File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/home/kt-gpu2/.local/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 207, in call
ret = func(*args)

File "finetune.py", line 75, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/kt-gpu2/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/kt-gpu2/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

 [[{{node PyFunc}}]]
 [[node IteratorGetNext (defined at finetune.py:140) ]]

code_zip.zip

please explain variables:
_CLIP_SIZE
_EACH_VIDEO_TEST_SIZE
_FRAME_SIZE

Can anyone share the script for creating rgb.txt and flow.txt? thanks.

hello,when i use your pre-trained model(rgb_0.946) to test ucf-101 split1, its accuracy is around 0.91!

Can you tell me the accuracy of the reproduction in HMDB51?

please.

Is there somewhere I can download data for training in the already correct format? (with flow files, and RGB files, and the corresponding txt files). I'd like to go through the code line by line, but need some data to run and understand it.

Thanks!

Thank you for your excellent work, my question is how to save .h5 or .npz classfication score files as shown in https://github.com/rohitgirdhar/ActionVLAD/tree/master/data/hmdb51/final_logits or https://github.com/youjiangxu/seqvlad-pytorch/tree/master/logits/hmdb51, thank you so much for you kind help, looking forward to your reply, thanks a lot.

Hi,

I am puzzled about the differences between pre_rgb.txt and rgb.txt

Thank you!
Chris

Hi,
I'm trying to reproduce the results reported in the paper (and this repository) with the I3D model trained with only RGB on UCF-101 (split 1) .
When I run test.py with the checkpoint provided in this repository (finetuned on UCF-101 RGB), I get a score of 89.4 . The authors of this repository report 94.7 .
Do you have any idea why is there a discrepancy in the scores?

Can we finetune any custom dataset using kinetics-600-rgb-scratch pretrained model ? Can anyone confirm this? @vra

Can you show me the codes of your extracting RGB and optical frames?

My code ability is bad, and i can find the corresponding code,who can share me a link? Thank you very much.

Hi, Thanks a lot for your excellent work.
I have been trying to train UCF101 from scratch without Kinetics or ImageNet pretrained these days using your code. But something's wrong with the test accuracy.
When I trained about 33 epoches, the loss is around 0.1, train accuracy is around 93.6%, test accuracy is around 58%. But when i run 'test.py', the accuracy is only about 8% which is very weird.
I think the test data should be the same in your code 'finetune.py' and 'test.py', but accuracy is quite different. Or is there anything i've been always missing.
My only change to your code is changing 'saver.restore(sess, _CHECKPOINT_PATHS[train_data.mode+'_imagenet'])' line 211 in 'finetune.py' to '#saver.restore(sess, _CHECKPOINT_PATHS[train_data.mode+'_imagenet'])' for learning from scratch.
Please share your thoughts with me, or anyone faced same problem, please let me know.

input to reshape is a tensor with 409600 values, but the requested shape is 3072

Hi – I'm trying to finetune with two classes.
Even running the while loop for a single iteration causes the program to take >60GB of memory, which causes

terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
/var/spool/PBS/mom_priv/jobs/1224593.pbs.SC: line 7: 13498 Aborted (core dumped) python finetune.py ucf101 rgb 1

I'm running python2 with sonnet v1.23, the frame size for my jpeg sequences are 224 and they consist of 200 frames. Any ideas on how to fix?

Demo_Transfer_rgb.py [-h] dataset_name data_tag
python Demo_Transfer_rgb.py need two arguments dataset_name data_tag

I've extracted the images of RGB and flow to the local path, but how do I create the corresponding TXT file? anyone who can share the script?Thank you very much!

MY WORK UCF101 RBG-->90.1 O-F-->83.3
WHEN I TRAIN THE I3D NETWORK AT THE OPTICAL-FLOW PART, USING THE PRE TRAINED IMAGENET MODEL, 40 EPOCHES LATER, IT ACHIEVES ACC AT 83.3%. WHETHER THE HYPERPARAMETERS SHOULD BE CHANGED BEFORE I USE DIFFERENT INPUTS (MOTION & APPEARENCE) ? IF NOT, WHAT'S THE PROBABLE PROBLEM OCUURED DURING MY WORKS?

IT'S UNBELIEVABLE WHEN I USE THE SAME GPU, 1080TI, AND THE FRAME NUM SHOULD BE DECRASED TO 32. OTHERWISE, IT MINGT SHOW WARNINGS, REQUIRE MORE THAN 2.61G MEMORY TO ACHIEVE NORMAL PERFORMANCE.

Hello Rhythmblue

I am traying to use your pretrained models in UCF101.
In this site I found 2 links to the models (google drive and the other in Baidu)
The google drive version is in you trash, can you restore one more time please ?

Regards, Reinier

2018-09-13 04:56:39.376762: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.61GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.

volatile GPU-Util is very low,where can I adjust in the codes to reduce memory.

Hello, sorry to disturb you~ here are some questions when running the projects:

1. When I run the test.py on ucf101 mixed 1, i got only 0.6756 accuracy while rgb model is 0.89, and flow model is 0.95.

2. Also I found that test.py #196, "input_label=np.array([label]).reshape(-1)", the input_label sometimes is not matched to the video when testing, e.g. v_ApplyEyeMakeup_g07_c07, prediction and video name are 'ApplyEyeMakeup', but input_label changed to ApplyLipstick's index.
   so I change the code
   video_label = rgb_data.Videos[i].label
   video_label = flow_data.Videos[i].label
   input_label=np.array([video_label]).reshape(-1)

but the accuracy is not improved.

InvalidArgumentError (see above for traceback): buffer_size must be greater than zero.
[[Node: ShuffleDataset = ShuffleDataset[_class=["loc:@iterator"], output_shapes=[[]], output_types=[DT_FLOAT], reshuffle_each_iteration=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](TensorSliceDataset, buffer_size, buffer_size, buffer_size)]]

The result in training are as follows:
step: 1540, loss: 1.3989, accuracy: 0.588 (13.88 sec/batch)
step: 1560, loss: 1.2763, accuracy: 0.625 (12.85 sec/batch)
step: 1580, loss: 2.9938, accuracy: 0.613 (12.66 sec/batch)
step: 1600, loss: 1.3215, accuracy: 0.700 (1.01 sec/batch)
step: 1620, loss: 0.4965, accuracy: 0.713 (17.85 sec/batch)
step: 1640, loss: 1.4940, accuracy: 0.688 (4.32 sec/batch)
step: 1660, loss: 0.4554, accuracy: 0.613 (5.13 sec/batch)
step: 1680, loss: 1.0088, accuracy: 0.662 (6.21 sec/batch)
step: 1700, loss: 0.1014, accuracy: 0.700 (5.01 sec/batch)
step: 1720, loss: 0.2080, accuracy: 0.713 (6.62 sec/batch)
step: 1740, loss: 1.7426, accuracy: 0.725 (3.81 sec/batch)
step: 1760, loss: 1.6926, accuracy: 0.738 (12.97 sec/batch)
step: 1780, loss: 0.3962, accuracy: 0.688 (18.84 sec/batch)
step: 1800, loss: 1.0156, accuracy: 0.738 (3.54 sec/batch)
step: 1820, loss: 0.4570, accuracy: 0.713 (11.37 sec/batch)
step: 1840, loss: 0.1834, accuracy: 0.750 (1.00 sec/batch)
step: 1860, loss: 1.3550, accuracy: 0.600 (5.51 sec/batch)
step: 1880, loss: 0.1034, accuracy: 0.812 (4.54 sec/batch)
step: 1900, loss: 3.2641, accuracy: 0.750 (2.22 sec/batch)
step: 1920, loss: 2.3116, accuracy: 0.637 (13.77 sec/batch)
step: 1940, loss: 0.4947, accuracy: 0.775 (17.61 sec/batch)
step: 1960, loss: 1.2279, accuracy: 0.613 (1.03 sec/batch)
step: 1980, loss: 1.3556, accuracy: 0.650 (1.05 sec/batch)

the data in rgb.txt，It's disordered ：

v_HighJump_g25_c04 /media/zoro/ZORO/UCF-101-FRAME/HighJump/v_HighJump_g25_c04 96 39
v_HighJump_g25_c05 /media/zoro/ZORO/UCF-101-FRAME/HighJump/v_HighJump_g25_c05 96 39
v_RopeClimbing_g19_c05 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g19_c05 164 74
v_YoYo_g12_c04 /media/zoro/ZORO/UCF-101-FRAME/YoYo/v_YoYo_g12_c04 171 100
v_RopeClimbing_g13_c02 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g13_c02 77 74
v_RopeClimbing_g13_c03 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g13_c03 77 74
v_RopeClimbing_g13_c01 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g13_c01 77 74
v_RopeClimbing_g13_c06 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g13_c06 98 74
v_RopeClimbing_g13_c07 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g13_c07 84 74
v_RopeClimbing_g13_c04 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g13_c04 89 74
v_RopeClimbing_g13_c05 /media/zoro/ZORO/UCF-101-FRAME/RopeClimbing/v_RopeClimbing_g13_c05 77 74
v_IceDancing_g04_c02 /media/zoro/ZORO/UCF-101-FRAME/IceDancing/v_IceDancing_g04_c02 249 43
v_IceDancing_g04_c03 /media/zoro/ZORO/UCF-101-FRAME/IceDancing/v_IceDancing_g04_c03 255 43
v_IceDancing_g04_c01 /media/zoro/ZORO/UCF-101-FRAME/IceDancing/v_IceDancing_g04_c01 255 43
v_IceDancing_g04_c06 /media/zoro/ZORO/UCF-101-FRAME/IceDancing/v_IceDancing_g04_c06 261 43
v_HighJump_g25_c02 /media/zoro/ZORO/UCF-101-FRAME/HighJump/v_HighJump_g25_c02 120 39
v_IceDancing_g04_c04 /media/zoro/ZORO/UCF-101-FRAME/IceDancing/v_IceDancing_g04_c04 250 43
v_IceDancing_g04_c05 /media/zoro/ZORO/UCF-101-FRAME/IceDancing/v_IceDancing_g04_c05 249 43
v_Fencing_g25_c01 /media/zoro/ZORO/UCF-101-FRAME/Fencing/v_Fencing_g25_c01 123 27
v_HighJump_g25_c03 /media/zoro/ZORO/UCF-101-FRAME/HighJump/v_HighJump_g25_c03 85 39
v_PlayingTabla_g03_c05 /media/zoro/ZORO/UCF-101-FRAME/PlayingTabla/v_PlayingTabla_g03_c05 254 65
v_CricketShot_g16_c02 /media/zoro/ZORO/UCF-101-FRAME/CricketShot/v_CricketShot_g16_c02 100 23
v_CricketShot_g16_c03 /media/zoro/ZORO/UCF-101-FRAME/CricketShot/v_CricketShot_g16_c03 98 23
v_ThrowDiscus_g19_c01 /media/zoro/ZORO/UCF-101-FRAME/ThrowDiscus/v_ThrowDiscus_g19_c01 68 92
v_CricketShot_g16_c01 /media/zoro/ZORO/UCF-101-FRAME/CricketShot/v_CricketShot_g16_c01 104 23
v_CricketShot_g16_c06 /media/zoro/ZORO/UCF-101-FRAME/CricketShot/v_CricketShot_g16_c06 57 23
v_CricketShot_g16_c07 /media/zoro/ZORO/UCF-101-FRAME/CricketShot/v_CricketShot_g16_c07 50 23
v_CricketShot_g16_c04 /media/zoro/ZORO/UCF-101-FRAME/CricketShot/v_CricketShot_g16_c04 73 23
v_CricketShot_g16_c05 /media/zoro/ZORO/UCF-101-FRAME/CricketShot/v_CricketShot_g16_c05 47 23
v_SoccerPenalty_g04_c02 /media/zoro/ZORO/UCF-101-FRAME/SoccerPenalty/v_SoccerPenalty_g04_c02 72 84
v_CleanAndJerk_g08_c03 /media/zoro/ZORO/UCF-101-FRAME/CleanAndJerk/v_CleanAndJerk_g08_c03 110 20
v_CleanAndJerk_g08_c02 /media/zoro/ZORO/UCF-101-FRAME/CleanAndJerk/v_CleanAndJerk_g08_c02 107 20
v_CleanAndJerk_g08_c01 /media/zoro/ZORO/UCF-101-FRAME/CleanAndJerk/v_CleanAndJerk_g08_c01 236 20
v_CleanAndJerk_g08_c04 /media/zoro/ZORO/UCF-101-FRAME/CleanAndJerk/v_CleanAndJerk_g08_c04 278 20
v_Typing_g19_c01 /media/zoro/ZORO/UCF-101-FRAME/Typing/v_Typing_g19_c01 213 94
v_LongJump_g07_c02 /media/zoro/ZORO/UCF-101-FRAME/LongJump/v_LongJump_g07_c02 171 50
v_LongJump_g07_c03 /media/zoro/ZORO/UCF-101-FRAME/LongJump/v_LongJump_g07_c03 102 50
v_LongJump_g07_c01 /media/zoro/ZORO/UCF-101-FRAME/LongJump/v_LongJump_g07_c01 123 50
v_LongJump_g07_c04 /media/zoro/ZORO/UCF-101-FRAME/LongJump/v_LongJump_g07_c04 82 50
v_LongJump_g07_c05 /media/zoro/ZORO/UCF-101-FRAME/LongJump/v_LongJump_g07_c05 118 50
v_BodyWeightSquats_g18_c03 /media/zoro/ZORO/UCF-101-FRAME/BodyWeightSquats/v_BodyWeightSquats_g18_c03 211 14
v_Surfing_g24_c01 /media/zoro/ZORO/UCF-101-FRAME/Surfing/v_Surfing_g24_c01 249 87
v_HorseRace_g20_c02 /media/zoro/ZORO/UCF-101-FRAME/HorseRace/v_HorseRace_g20_c02 327 40

https://github.com/USTC-Video-Understanding/I3D_Finetune/blob/master/Demo_Transfer_rgb.py#L139
Hi,
I think the last fc layer may should not use an activation unit.
If the output of fc layer is all negative, after the ReLU unit, it would be all zero.
In this case, top_k_op = tf.nn.in_top_k(fc_out, label_holder, 1) will always return True.

Thank your for your interesting code.

I tried to reproduce the experimental results, and I found that in testing phrase, there are only 3755 samples when I do 'python test.py ucf101 rgb 1'. Actually, it should have 3783 samples.

Could you explain why they are different? Or maybe I make some mistakes.

Thank you again.

Hello,
thank you for the work. Is there an easy way to train the Models on my own Dataset, and some new Classes? I have tried it with 9 Classes(created _Classnum), but I get 2 Errors:

python3 finetune.py ucf9 rgb 1
/usr/local/lib/python3.5/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/contrib/learn/python/learn/datasets/base.py:198: retry (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Use the retry module or similar alternatives.
2018-06-12 16:28:40.489353: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2018-06-12 16:28:40.576145: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-06-12 16:28:40.576407: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1344] Found device 0 with properties:
name: GeForce GTX 960M major: 5 minor: 0 memoryClockRate(GHz): 1.176
pciBusID: 0000:01:00.0
totalMemory: 3.95GiB freeMemory: 3.42GiB
2018-06-12 16:28:40.576421: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1423] Adding visible gpu devices: 0
2018-06-12 16:28:41.162533: I tensorflow/core/common_runtime/gpu/gpu_device.cc:911] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-06-12 16:28:41.162570: I tensorflow/core/common_runtime/gpu/gpu_device.cc:917] 0
2018-06-12 16:28:41.162575: I tensorflow/core/common_runtime/gpu/gpu_device.cc:930] 0: N
2018-06-12 16:28:41.162758: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3151 MB memory) -> physical GPU (device: 0, name: GeForce GTX 960M, pci bus id: 0000:01:00.0, compute capability: 5.0)
INFO:tensorflow:Restoring parameters from ./data/checkpoints/rgb_imagenet/model.ckpt
----Here we start!----
Output wirtes to output/finetune-ucf9-rgb-1
2018-06-12 16:29:14.904305: W tensorflow/core/framework/op_kernel.cc:1261] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/script_ops.py", line 147, in call
ret = func(*args)

File "finetune.py", line 73, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/chris/Desktop/Action/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/chris/Desktop/Action/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

2018-06-12 16:29:14.904819: W tensorflow/core/framework/op_kernel.cc:1261] Invalid argument: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/script_ops.py", line 147, in call
ret = func(*args)

File "finetune.py", line 73, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/chris/Desktop/Action/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/chris/Desktop/Action/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "finetune.py", line 291, in
main(**vars(p.parse_args()))
File "finetune.py", line 230, in main
feed_dict={dropout_holder: _DROPOUT, is_train_holder: True})
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 905, in run
run_metadata_ptr)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1140, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1321, in _do_run
run_metadata)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: 'NoneType' object is not iterable
Traceback (most recent call last):

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/script_ops.py", line 147, in call
ret = func(*args)

File "finetune.py", line 73, in process_video
clip_seq, label_seq = data.next_batch(1, _CLIP_SIZE)

File "/home/chris/Desktop/Action/I3D_Finetune/lib/action_dataset.py", line 33, in next_batch
self.videos[self.perm[i]].get_frames(frame_num, data_augment=data_augment))

File "/home/chris/Desktop/Action/I3D_Finetune/lib/video_3d.py", line 41, in get_frames
frames.extend(self.load_img((i-1)%self.total_frame_num+1))

TypeError: 'NoneType' object is not iterable

 [[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_STRING, DT_STRING], Tout=[DT_FLOAT, DT_INT64], token="pyfunc_0"](arg0, PyFunc/input_1, PyFunc/input_2)]]
 [[Node: IteratorGetNext = IteratorGetNext[output_shapes=[<unknown>, <unknown>], output_types=[DT_FLOAT, DT_INT64], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator)]]
 [[Node: IteratorGetNext/_467 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_141_IteratorGetNext", tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]

The First Error appears a dozen times. The second only two times.
I can't find whats the problem here. Maybe u can help me.

Hey there all,

I am using Anaconda 4.10.3 and trying to run I3D_Fine on macOS, but I am getting conflicts error when executing the command:
conda create -n env_sonnet "tensorflow<2" "dm-sonnet<2" "tensorflow-probability==0.7.0"
The error says:
**Collecting package metadata (current_repodata.json): done
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: /
Found conflicts! Looking for incompatible packages.
This can take several minutes. Press CTRL-C to abort.
failed

UnsatisfiableError: The following specifications were found to be incompatible with each other:

Output in format: Requested package -> Available versions

Package tensorflow conflicts for:
dm-sonnet[version='<2'] -> tensorflow-probability[version='<0.7'] -> tensorflow[version='>=1.11.0']
dm-sonnet[version='<2'] -> tensorflow[version='>=1.5.0|>=1.8.0']
tensorflow[version='<2']
tensorflow-probability==0.7.0 -> tensorflow[version='>=1.14.0']

Package tensorflow-probability conflicts for:
tensorflow-probability==0.7.0
dm-sonnet[version='<2'] -> tensorflow-probability[version='<0.7']

Package numpy-base conflicts for:
tensorflow[version='<2'] -> numpy[version='>=1.13.3'] -> numpy-base[version='1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.11.3|1.14.3|1.14.3|1.14.3|1.14.3|1.14.3|1.14.3|1.14.4|1.14.4|1.14.4|1.14.4|1.14.4|1.14.4|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.3|1.15.3|1.15.3|1.15.3|1.15.3|1.15.3|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.2|1.16.2|1.16.2|1.16.2|1.16.2|1.16.2|1.16.3|1.16.3|1.16.3|1.16.3|1.16.3|1.16.3|1.16.4|1.16.4|1.16.4|1.16.4|1.16.4|1.16.4|1.16.5|1.16.5|1.16.5|1.16.5|1.16.5|1.16.5|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.17.2.|1.17.3.|1.17.4.|1.18.1.|1.18.5.|1.19.1|1.19.1|1.19.1|1.19.1|1.19.1|1.19.1|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.20.1|1.20.1|1.20.1|1.20.1|1.20.1|1.20.1|1.20.2|1.20.2|1.20.2|1.20.2|1.20.2|1.20.2|1.20.3|1.20.3|1.20.3|1.20.3|1.20.3|1.20.3|1.21.2|1.17.0|1.17.0|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|1.9.3|>=1.9.3,<2.0a0',build='py37h9797aa9_6|py36h9797aa9_6|py36ha9ae307_6|py37h9797aa9_7|py37ha9ae307_7|py35h9797aa9_7|py35ha9ae307_7|py36h9797aa9_7|py27h9797aa9_7|py27ha9ae307_7|py27h9797aa9_7|py37h9797aa9_7|py36h9797aa9_7|py27ha9ae307_7|py37ha9ae307_7|py27h9797aa9_8|py36ha9ae307_8|py37ha9ae307_8|py37h9797aa9_8|py35ha9ae307_8|py37he97cb71_9|py36h8a80b8c_9|py36he97cb71_9|py37h42e5f7b_10|py36h8a80b8c_10|py27h8a80b8c_10|py35h8a80b8c_10|py27ha711998_10|py36ha711998_10|py37ha711998_11|py27h6575580_11|py36h6575580_12|py37ha711998_12|py36ha711998_12|py27ha711998_12|py38ha711998_12|py38ha711998_13|py38ha711998_15|py36ha711998_0|py36h7ef55bc_1|py35h479e554_1|py27h479e554_1|py36ha9ae307_0|py35h9797aa9_0|py27h9797aa9_1|py37ha9ae307_1|py27ha9ae307_1|py36ha9ae307_1|py27h9797aa9_2|py37ha9ae307_2|py36h9797aa9_3|py37h9797aa9_3|py27ha9ae307_3|py37ha9ae307_3|py27ha9ae307_4|py27h9797aa9_4|py37ha9ae307_4|py35ha711998_4|py35h8a80b8c_4|py27ha711998_4|py38h6575580_4|py36ha711998_5|py36h6575580_5|py37ha711998_5|py27he97cb71_0|py37h8a80b8c_0|py27h8a80b8c_0|py36h8a80b8c_0|py37he97cb71_0|py35h8a80b8c_0|py37h42e5f7b_0|py36h8a80b8c_0|py35h42e5f7b_0|py27h42e5f7b_0|py27h8a80b8c_0|py37h8a80b8c_0|py35h8a80b8c_0|py36ha711998_0|py37ha711998_0|py37h8a80b8c_0|py35h8a80b8c_0|py37ha711998_0|py36h8a80b8c_0|py27h8a80b8c_0|py36ha711998_0|py35ha711998_0|py36ha711998_1|py37h8a80b8c_1|py37h8a80b8c_0|py37ha711998_0|py36ha711998_0|py27h8a80b8c_0|py36h8a80b8c_0|py27h8a80b8c_0|py37h8a80b8c_0|py36ha711998_0|py37ha711998_0|py36h6575580_0|py37ha711998_0|py36ha711998_0|py37h6575580_1|py36ha711998_1|py36h6575580_1|py36ha711998_0|py37ha711998_0|py27h6575580_0|py37h6575580_0|py37h6575580_1|py27ha711998_1|py36h6575580_1|py36ha711998_0|py37ha711998_0|py27h6575580_0|py37h6575580_0|py36ha711998_0|py37h6575580_0|py37ha711998_0|py36ha711998_0|py37ha711998_0|py37h6575580_0|py37ha711998_0|py36ha711998_0|py27h6575580_0|py37ha711998_0|py36ha711998_0|py27ha711998_0|py39hd037223_1|py39hd037223_3|py36hd037223_3|py37hd037223_3|py38hd037223_3|py39h4850c68_3|py36h4850c68_3|py36h68fea81_0|py38h68fea81_0|py37hcfb5961_0|py36hcfb5961_0|py37hcfb5961_0|py38h68fea81_0|py39h3a452eb_0|py39h585ceec_0|py37h3a452eb_0|py39h3a452eb_0|py38h585ceec_0|py37hbbe2e76_0|py38hbbe2e76_0|py38he0bd621_0|py37he0bd621_0|py37hbbe2e76_0|py38hbbe2e76_0|py37he0bd621_0|py38he0bd621_0|py37hbbe2e76_0|py37he0bd621_0|py38hbbe2e76_0|py310he490955_0|py310h4c014f7_0|py39he0bd621_0|py38he0bd621_0|py39hbbe2e76_0|py39he0bd621_0|py39hbbe2e76_0|py39he0bd621_0|py39hbbe2e76_0|py38h3a452eb_0|py37h585ceec_0|py39hde55871_0|py37h68fea81_0|py36h68fea81_0|py38hcfb5961_0|py38hcfb5961_0|py36hcfb5961_0|py37h68fea81_0|py37h4850c68_3|py38h4850c68_3|py39h7ca7dfd_1|py27h6575580_0|py38ha711998_0|py38h6575580_0|py37h6575580_0|py36h6575580_0|py37h6575580_0|py36h6575580_0|py27ha711998_0|py36h6575580_0|py27h6575580_0|py27ha711998_0|py36h6575580_0|py27h6575580_0|py27ha711998_0|py36h6575580_0|py27ha711998_0|py37ha711998_1|py27h6575580_1|py36ha711998_1|py36h6575580_0|py27ha711998_0|py27h6575580_1|py37ha711998_1|py27ha711998_1|py36h6575580_0|py27h6575580_0|py37h6575580_0|py27ha711998_0|py27h6575580_0|py37h6575580_0|py27ha711998_0|py36h8a80b8c_0|py27ha711998_0|py36h8a80b8c_1|py27h8a80b8c_1|py37ha711998_1|py27ha711998_1|py27ha711998_0|py35ha711998_0|py27ha711998_0|py36h42e5f7b_0|py35he97cb71_0|py36he97cb71_0|py37h6575580_5|py27h6575580_5|py27ha711998_5|py38ha711998_4|py27h8a80b8c_4|py36h8a80b8c_4|py37h8a80b8c_4|py37ha711998_4|py36ha711998_4|py35ha9ae307_4|py35h9797aa9_4|py37h9797aa9_4|py36h9797aa9_4|py36ha9ae307_4|py27h9797aa9_3|py36ha9ae307_3|py27ha9ae307_2|py36ha9ae307_2|py36h9797aa9_2|py37h9797aa9_2|py37h9797aa9_1|py36h9797aa9_1|py35ha9ae307_0|py27ha9ae307_0|py27h9797aa9_0|py36h9797aa9_0|py36ha9ae307_0|py35ha9ae307_0|py36h9797aa9_0|py27ha9ae307_0|py35h9797aa9_0|py27h9797aa9_0|py35h7ef55bc_1|py27h7ef55bc_1|py36h479e554_1|py36h6575580_0|py38h6575580_15|py38h6575580_14|py38ha711998_14|py38h6575580_13|py38h6575580_12|py37h6575580_12|py27h6575580_12|py36h6575580_11|py37h6575580_11|py36ha711998_11|py27ha711998_11|py37ha711998_10|py35ha711998_10|py36h42e5f7b_10|py37h8a80b8c_10|py35h42e5f7b_10|py27h42e5f7b_10|py35he97cb71_9|py27he97cb71_9|py35h8a80b8c_9|py27h8a80b8c_9|py37h8a80b8c_9|py35h9797aa9_8|py36h9797aa9_8|py27ha9ae307_8|py36ha9ae307_7|py36ha9ae307_7|py37ha9ae307_6|py27ha9ae307_6|py27h9797aa9_6']
tensorflow-probability==0.7.0 -> numpy[version='>=1.13.3'] -> numpy-base[version='1.14.3|1.14.3|1.14.3|1.14.3|1.14.3|1.14.3|1.14.4|1.14.4|1.14.4|1.14.4|1.14.4|1.14.4|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.5|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.14.6|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.0|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.1|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.2|1.15.3|1.15.3|1.15.3|1.15.3|1.15.3|1.15.3|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.15.4|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.0|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.1|1.16.2|1.16.2|1.16.2|1.16.2|1.16.2|1.16.2|1.16.3|1.16.3|1.16.3|1.16.3|1.16.3|1.16.3|1.16.4|1.16.4|1.16.4|1.16.4|1.16.4|1.16.4|1.16.5|1.16.5|1.16.5|1.16.5|1.16.5|1.16.5|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.16.6|1.17.2.|1.17.3.|1.17.4.|1.18.1.|1.18.5.|1.19.1|1.19.1|1.19.1|1.19.1|1.19.1|1.19.1|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.19.2|1.20.1|1.20.1|1.20.1|1.20.1|1.20.1|1.20.1|1.20.2|1.20.2|1.20.2|1.20.2|1.20.2|1.20.2|1.20.3|1.20.3|1.20.3|1.20.3|1.20.3|1.20.3|1.21.2|1.17.0|1.17.0',build='py36ha711998_0|py36h7ef55bc_1|py35h479e554_1|py27h479e554_1|py36ha9ae307_0|py35h9797aa9_0|py27h9797aa9_1|py37ha9ae307_1|py27ha9ae307_1|py36ha9ae307_1|py27h9797aa9_2|py37ha9ae307_2|py36h9797aa9_3|py37h9797aa9_3|py27ha9ae307_3|py37ha9ae307_3|py27ha9ae307_4|py27h9797aa9_4|py37ha9ae307_4|py35ha711998_4|py35h8a80b8c_4|py27ha711998_4|py38h6575580_4|py36ha711998_5|py36h6575580_5|py37ha711998_5|py27he97cb71_0|py37h8a80b8c_0|py27h8a80b8c_0|py36h8a80b8c_0|py37he97cb71_0|py35h8a80b8c_0|py37h42e5f7b_0|py36h8a80b8c_0|py35h42e5f7b_0|py27h42e5f7b_0|py27h8a80b8c_0|py37h8a80b8c_0|py35h8a80b8c_0|py36ha711998_0|py37ha711998_0|py37h8a80b8c_0|py35h8a80b8c_0|py37ha711998_0|py36h8a80b8c_0|py27h8a80b8c_0|py36ha711998_0|py35ha711998_0|py36ha711998_1|py37h8a80b8c_1|py37h8a80b8c_0|py37ha711998_0|py36ha711998_0|py27h8a80b8c_0|py36h8a80b8c_0|py27h8a80b8c_0|py37h8a80b8c_0|py36ha711998_0|py37ha711998_0|py36h6575580_0|py37ha711998_0|py36ha711998_0|py37h6575580_1|py36ha711998_1|py36h6575580_1|py36ha711998_0|py37ha711998_0|py27h6575580_0|py37h6575580_0|py37h6575580_1|py27ha711998_1|py36h6575580_1|py36ha711998_0|py37ha711998_0|py27h6575580_0|py37h6575580_0|py36ha711998_0|py37h6575580_0|py37ha711998_0|py36ha711998_0|py37ha711998_0|py37h6575580_0|py37ha711998_0|py36ha711998_0|py27h6575580_0|py37ha711998_0|py36ha711998_0|py27ha711998_0|py39hd037223_1|py39hd037223_3|py36hd037223_3|py37hd037223_3|py38hd037223_3|py39h4850c68_3|py36h4850c68_3|py36h68fea81_0|py38h68fea81_0|py37hcfb5961_0|py36hcfb5961_0|py37hcfb5961_0|py38h68fea81_0|py39h3a452eb_0|py39h585ceec_0|py37h3a452eb_0|py39h3a452eb_0|py38h585ceec_0|py37hbbe2e76_0|py38hbbe2e76_0|py38he0bd621_0|py37he0bd621_0|py37hbbe2e76_0|py38hbbe2e76_0|py37he0bd621_0|py38he0bd621_0|py37hbbe2e76_0|py37he0bd621_0|py38hbbe2e76_0|py310he490955_0|py310h4c014f7_0|py39he0bd621_0|py38he0bd621_0|py39hbbe2e76_0|py39he0bd621_0|py39hbbe2e76_0|py39he0bd621_0|py39hbbe2e76_0|py38h3a452eb_0|py37h585ceec_0|py39hde55871_0|py37h68fea81_0|py36h68fea81_0|py38hcfb5961_0|py38hcfb5961_0|py36hcfb5961_0|py37h68fea81_0|py37h4850c68_3|py38h4850c68_3|py39h7ca7dfd_1|py27h6575580_0|py38ha711998_0|py38h6575580_0|py37h6575580_0|py36h6575580_0|py37h6575580_0|py36h6575580_0|py27ha711998_0|py36h6575580_0|py27h6575580_0|py27ha711998_0|py36h6575580_0|py27h6575580_0|py27ha711998_0|py36h6575580_0|py27ha711998_0|py37ha711998_1|py27h6575580_1|py36ha711998_1|py36h6575580_0|py27ha711998_0|py27h6575580_1|py37ha711998_1|py27ha711998_1|py36h6575580_0|py27h6575580_0|py37h6575580_0|py27ha711998_0|py27h6575580_0|py37h6575580_0|py27ha711998_0|py36h8a80b8c_0|py27ha711998_0|py36h8a80b8c_1|py27h8a80b8c_1|py37ha711998_1|py27ha711998_1|py27ha711998_0|py35ha711998_0|py27ha711998_0|py36h42e5f7b_0|py35he97cb71_0|py36he97cb71_0|py37h6575580_5|py27h6575580_5|py27ha711998_5|py38ha711998_4|py27h8a80b8c_4|py36h8a80b8c_4|py37h8a80b8c_4|py37ha711998_4|py36ha711998_4|py35ha9ae307_4|py35h9797aa9_4|py37h9797aa9_4|py36h9797aa9_4|py36ha9ae307_4|py27h9797aa9_3|py36ha9ae307_3|py27ha9ae307_2|py36ha9ae307_2|py36h9797aa9_2|py37h9797aa9_2|py37h9797aa9_1|py36h9797aa9_1|py35ha9ae307_0|py27ha9ae307_0|py27h9797aa9_0|py36h9797aa9_0|py36ha9ae307_0|py35ha9ae307_0|py36h9797aa9_0|py27ha9ae307_0|py35h9797aa9_0|py27h9797aa9_0|py35h7ef55bc_1|py27h7ef55bc_1|py36h479e554_1|py36h6575580_0']The following specifications were found to be incompatible with your system:

• feature:/osx-64::__osx==10.15.7=0
• feature:|@/osx-64::__osx==10.15.7=0

Your installed version is: 10.15.7

Note that strict channel priority may have removed packages required for satisfiability.**

I need to run I3D on my own custom dataset, but I am stuck here.

if I want to use multi GPUs to train ,what should I do?

Hi, thanks for your great work!
I noticed that you used the equation 2*(x/255) - 1 to make the image data in the range -1 to 1. And the official i3d seems contains no image preprocessing code although there is a issue discussing this question but it seems no one knows how to transform the demo images to match data in ".npy" file. So why to use this equation to transform the images? Can using this equation match data in ".npy" file?

On running CUDA_VISIBLE_DEVICES=0 python finetune.py ucf101 flow 2 , the video got stuck in the process. I tried with test lists 1, 2, 3 but it's getting stuck at the different videos. It is working fine with the only optical flow but when ran only RGB or mixed loop just get stuck after some time. I suspect there is something with RGB code.
FYI: I tried with 2 different sets of RGB frames and the RBG list is valid enough.