hx173149 / c3d-tensorflow Goto Github PK

Dear author:
when i run this shell script , the terminal remind the errors:
convert_images_to_list.sh: 行 31: jot: 未找到命令
convert_images_to_list.sh: 行 31: ((: > 1 : 语法错误: 需要操作数 (错误符号是 "> 1 ")
can you help me?
Thank you!!

• I have got those files when I run python train_c3d_ucf101.py,who can tell me how should I to use them?

• and I have got this when I run python predict_c3d_ucf101.py,who can tell me what's means of it?

• How do we input videos into the network for behavior recognition?

Hi,@JulioEndara @FrankGu @hx173149 @chuckcho @cc786537662
thank you very much

Thank u for your share. I have some questions that I wrote the codes to convert caffemodel to other file with pickle in python, and I wrote the codes to read the parameters using the file I created. At that time, I found your network architecture is not the same as standard C3D network, like conv3 conv4, and fc layer. Is that your personal change to make network performance better ? How about the result ?

2%|▏ | 29/1261 [00:08<06:00, 3.41it/s]test acc: 0.8620689655172413 test_correct_num: 75 total_v: 87.0
Loading a video clip from F:/UCF-101//Archery/v_Archery_g06_c06...
Loading a video clip from F:/UCF-101//Archery/v_Archery_g07_c04...

Traceback (most recent call last):
File "E:/graduate/action-recognition/code/Random_clip_valid.py", line 197, in
modelpath="./")
File "E:/graduate/action-recognition/code/Random_clip_valid.py", line 184, in test
shuffle=False
File "E:\graduate\action-recognition\code\input_data_v1.py", line 97, in read_clip_and_label
raise EOFError
EOFError

Process finished with exit code 1

Thanks

I have got the problem when I run the code.
Could you please tell me the edition of your tensorflow?
Thanks.

Hi,
In part 'trained models' of ‘readme’, you said ‘the C3D sports1M TF was converted from caffe C3D’.So does it mean that you convert a caffe model to a tensorflow model? It seems to be a hard work and I wonder how you achieve it because I need to do someting closely like this.
Any help much appreciate!

I would like to use this code but not sure if it works with tensorflow 1.1
Does it?
Thanks

i'm reading your code, but the line174
for i in tqdm(range(int(3783 / self.batch_size))):
i don't understand the meaning of '3783', hope for your reply!
Any help much appreciate!~

I read your code , you randomly selected 10 videos rather than loop every video during training 。 I think "input_data.read_clip_and_label()" could do better ， if train from scratch

@hx173149
Did you notice the difference in efficiency between this code and original C3D code?
During testing, the batch size of caffe code can be 30 in GTX, while the batch size for this code is 15. When adding the batch size, the code will report 'Out of Memory' error. Can you tell me you GPU configuration and batch size during training? Thanks!

I cloned your repository, added in the UCF Dataset in the format specified in the list, looks like C3D-tensorflow/database/ucf101/train/ and put the sports1m_finetuning_ucf101.model and sports1m_finetuning_ucf101.model and crop_mean.npy files in the root (in C3D-tensorflow folder).

When I run "python train_c3d_ucf101.py" I get this error:\

I tensorflow/core/common_runtime/simple_placer.cc:819] var_name/wc1/Initializer/random_uniform/shape: /job:localhost/replica:0/task:0/cpu:0
Adam_1/value: /job:localhost/replica:0/task:0/cpu:0
I tensorflow/core/common_runtime/simple_placer.cc:819] Adam_1/value: /job:localhost/replica:0/task:0/cpu:0
global_step/Initializer/Const: /job:localhost/replica:0/task:0/cpu:0
I tensorflow/core/common_runtime/simple_placer.cc:819] global_step/Initializer/Const: /job:localhost/replica:0/task:0/cpu:0
Traceback (most recent call last):
  File "train_c3d_ucf101.py", line 224, in <module>
    tf.app.run()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 30, in run
    sys.exit(main(sys.argv[:1] + flags_passthrough))
  File "train_c3d_ucf101.py", line 221, in main
    run_training()
  File "train_c3d_ucf101.py", line 198, in run_training
    train_images,train_labels = input_data.ReadDataLabelFromFile('list/train.list',FLAGS.batch_size*gpu_num)
AttributeError: 'module' object has no attribute 'ReadDataLabelFromFile'

Do you know what would cause this issue? I also have no GPU, not sure if that would cause an issue.

It looks like input_data has the "ReadDataLabelFromFile_16" but no "ReadDataLabelFromFile". Is there an updated input_data.py file?

Thanks

Hi, do you have the pretrained model on the sport1m? Thanks! :)

I can not use my model(c3d_ucf_model-9999.data-00000-of-00001), when i finished training network.

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /home/xxx/xxx/C3D-tensorflow-master/models111/3d_ucf_model-9999.data-00000-of-00001
[[Node: save/RestoreV2_2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_2/tensor_names, save/RestoreV2_2/shape_and_slices)]]

I find that in train_c3d_ucf101.py dropout is 0.5, while in predict_c3d_ucf101.py dropout is 0.6, can you explain why ? @hx173149

Thank you for sharing the model. I'm a green hand in ucf101 , I don't know what is the crop_mean.npy file in input_data.py? And the download link has failed. How can I get this file?

Is there any pre-trained model in VGG/ResNet-like framework?

I tried to run predict_c3d_ucf101.py and it needs './sports1m_finetuning_ucf101.model'. But I cannot find it.
Do I need to train to get the model?

Thanks for sharing this code.
Always error when downloading crop_mean.npy from dropbox, so i want to write it by myself, As its name shows, i think it represents a mean, RGB?But i don't kown how to compute. Hope your help.

If I have trained this model with two kinds of dataset (RGB and opticalflow) and saved to 2 separate models: model1 and model2
Now I want to fuse 2 these networks (using average fusion method) for classification, how to do it?
Any one have coded this part

I am new in this area. So, i need your help.
The steps i followed :

1. i created dataset folder which has the UCF 101 videos but i opened just one folder with named "walk" under the dataset folder. And there are only 2 videos under this walk folder to test the model.
   The path is like this ../C3D-tensorflow-master/database/UCF101/walk
2. I followed the all steps on the README.
   the test.list file as following.
   /home/zeynep/Desktop/C3D-tensorflow-master/database/UCF101/walk/v_ApplyEyeMakeup_g01_c01 0
   /home/zeynep/Desktop/C3D-tensorflow-master/database/UCF101/walk/v_ApplyEyeMakeup_g01_c02 1
3. Then i tried to run predict_c3d_ucf101.py code, i got the error as following.

Number of test videos=2
Traceback (most recent call last):
  File "predict_c3d_ucf101.py", line 154, in <module>
    tf.app.run()
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "predict_c3d_ucf101.py", line 151, in main
    run_test()
  File "predict_c3d_ucf101.py", line 110, in run_test
    logits = tf.concat(0, logits)
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1043, in concat
    dtype=dtypes.int32).get_shape(
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 676, in convert_to_tensor
    as_ref=False)
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 741, in internal_convert_to_tensor
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 113, in _constant_tensor_conversion_function
    return constant(v, dtype=dtype, name=name)
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 102, in constant
    tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 374, in make_tensor_proto
    _AssertCompatible(values, dtype)
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 302, in _AssertCompatible
    (dtype.name, repr(mismatch), type(mismatch).__name__))
TypeError: Expected int32, got list containing Tensors of type '_Message' instead.

By the way, i installed the tensorflow with CPU not GPU.
When i change the from gpu_num = 2 to gpu_num = 0 , the error like this

Number of test videos=2
Traceback (most recent call last):
  File "predict_c3d_ucf101.py", line 154, in <module>
    tf.app.run()
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "predict_c3d_ucf101.py", line 151, in main
    run_test()
  File "predict_c3d_ucf101.py", line 110, in run_test
    logits = tf.concat(0, logits)
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1044, in concat
    ).assert_is_compatible_with(tensor_shape.scalar())
  File "/home/zeynep/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/tensor_shape.py", line 732, in assert_is_compatible_with
    raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (0,) and () are incompatible

What should i do to solve this problem and to got the result ?

While training the process stops and I'm getting a "tensorflow terminate called after throwing an instance of 'std::bad_alloc'" error.

Is this due to lack of sufficient memory?

How much memory is needed to train on the full UCF-101 dataset?

thanks

What is the format of input images? RGB or BGR?

I used your code in my own dataset. Your code works well when gpu_num=1. But when I set gpu_num=2, I get an error:

Traceback (most recent call last):
File "train_c3d_ucf101.py", line 344, in
tf.app.run()
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train_c3d_ucf101.py", line 341, in main
run_training()
File "train_c3d_ucf101.py", line 202, in run_training
labels_placeholder[gpu_index * FLAGS.batch_size:(gpu_index + 1) * FLAGS.batch_size]
File "train_c3d_ucf101.py", line 97, in tower_loss
loss_averages_op = loss_averages.apply(losses + [total_loss])
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/moving_averages.py", line 375, in apply
colocate_with_primary=(var.op.type in ["Variable", "VariableV2"]))
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/slot_creator.py", line 174, in create_zeros_slot
colocate_with_primary=colocate_with_primary)
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/slot_creator.py", line 149, in create_slot_with_initializer
dtype)
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/slot_creator.py", line 66, in _create_slot_var
validate_shape=validate_shape)
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1049, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 948, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 356, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 341, in _true_getter
use_resource=use_resource)
File "/mnt/xfs1/home/zhangyifan/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 671, in _get_single_variable
"VarScope?" % name)
ValueError: Variable IVA-research_1/var_name/weight_loss/loss/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

I am really confused, could you please help me ? @hx173149 @FrankGu

I used the /c3d_ucf101_finetune_whole_iter_20000_TF.model and followed the guidance to generate the test list on UCF101. Then, I only changed the gpu_num into 1 to match my computer and ran the predict_c3d_ucf101.py. However, the accuracy is terrible. I got 1.3% accuracy (32/3261).

Solution:
Do Remember to comment the line that does transpose operation

This is my first iterations. Is normal? (I keep all parameters as original code except batch_size)
Step 0: 61.349 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Step 1: 60.673 sec
Step 2: 60.542 sec
Step 3: 60.960 sec
Step 4: 60.619 sec
Step 5: 60.658 sec
Step 6: 60.709 sec
Step 7: 60.616 sec
Step 8: 60.445 sec
Step 9: 60.547 sec
Step 10: 60.527 sec
Training Data Eval:
accuracy: 0.90000
Validation Data Eval:
accuracy: 1.00000
Step 11: 60.612 sec
Step 12: 60.600 sec
Step 13: 61.529 sec
Step 14: 60.945 sec
Step 15: 60.388 sec
Step 16: 60.548 sec
Step 17: 60.278 sec
Step 18: 60.645 sec
Step 19: 60.625 sec
Step 20: 61.114 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 0.80000

Hi. Thanks for your amazing work. This code is a great help for me. I trained this network in UCF101 data set. However I got a training accuracy of nearly 98% and test accuracy of 33%. Do you know what caused the overfitting? Also, can you share how you transfer the caffe model to tensorflow mode? Thanks!

Thanks for your excellent work! When I trained the model at around 10000 iters, the batch acc of training set is ~96%, but the batch acc of val set is ~ 29%, what's wrong? the training list and val list is the list i used for training in CNN which works well.

When I want to use the sports1m_finetuning_ucf101.model when training on the UCF-101 data set, I receive the following error:

NotFoundError (see above for traceback): Tensor name "var_name/bc3a/Adam" not found in checkpoint files ./sports1m_finetuning_ucf101.model
         [[Node: save/RestoreV2_86 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_86/tensor_names, save/RestoreV2_86/shape_and_slices)]]
         [[Node: save/RestoreV2_9/_5 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_793_save/RestoreV2_9", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]

Python running on Windows 10:
Python 3.5.2 |Anaconda 4.2.0 (64-bit)| (default, Jul 5 2016, 11:41:13) [MSC v.1900 64 bit (AMD64)]
tensorflow-gpu (0.12.0rc0)

Thanks!

Hi,

First of all, thank you for sharing your code. It's a great help for my work.
I was wondering whether we need to subtract volume_mean (or mean_value) from input video frames?
It seems like the original Caffe-based implementation do apply mean substraction.

What are your thoughts on this? Do you think this will impact the accuracy?
Thank you for your help.

If I want to train a new model on another dateset, shall I have to calculate the crop_mean.npy, then replace your file, train and test? I saw the crop_mean.npy's size is (16, 112, 112, 3) and type is float, Is it just a sum and then divide the image query number? Do you have the python script or other function to calculate the mean value， can you share it to me ? my email is [email protected], thank you very much.

I trained directly on UCF101 split1. Attached is how the training/validation accuracy plots looks like. As can be seen, the last model weights at step 4999 gives 45% for the validation-set accuracy. When running the prediction script using the weights at step 4999 and calculating the accuracy = sum correct / (sum correct + sum incorrect), I get 26.8% where correct means that the true label is the same as the actual label taken from the prediction script output.

Why is there a difference?

I’m trying to run the file “train_c3d_ucf101.py”,
but always appear the error messange.

/usr/local/lib/python2.7/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
2018-01-26 17:22:17.583579: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-01-26 17:22:17.583618: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-01-26 17:22:17.583638: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2018-01-26 17:22:17.583657: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2018-01-26 17:22:17.583662: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
Traceback (most recent call last):
  File "train_c3d_ucf101.py", line 261, in <module>
    tf.app.run()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "train_c3d_ucf101.py", line 258, in main
    run_training()
  File "train_c3d_ucf101.py", line 223, in run_training
    labels_placeholder: train_labels
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 789, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 975, in _run
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (20, 0) for Tensor u'Placeholder:0', which has shape '(20, 16, 112, 112, 3)'

I was download on https://github.com/hx173149/C3D-tensorflow at 01/19/2018,
and the test environment is
python = 2.7
tensorflow = 1.4.1
I also install athena-jot and Pillow

Hi,
I am new in this area as i mentioned before. I am trying to apply fine tuning to this model.
In pre-trained model there are 101 classes but i want to change it to 2 classes by applying fine tuning, but when i restore the model ( saver.restore(sess, model_filename) ) i have encountered error something like this " InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [2] rhs shape= [101] "
I guess, i shouldn't restore the out layer from the pretrained model. Am i wrong? If i am wrong what
should i do to solve this problem? If i am right, how can i restore the model without out layer?

Can you help me ?

The error :
-- By the way, fine_tuning.py is the same with the train code in this project. İ just change the name.
1. Traceback (most recent call last):
2. File "fine_tuning.py", line 285, in
3. tf.app.run()
4. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
5. _sys.exit(main(_sys.argv[:1] + flags_passthrough))
6. File "fine_tuning.py", line 282, in main
7. run_training()
8. File "fine_tuning.py", line 221, in run_training
9. saver.restore(sess, model_filename)
10. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1560, in restore
11. {self.saver_def.filename_tensor_name: save_path})
12. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
13. run_metadata_ptr)
14. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1124, in _run
15. feed_dict_tensor, options, run_metadata)
16. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
17. options, run_metadata)
18. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
19. raise type(e)(node_def, op, message)
20. tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [2] rhs shape= [101]
21. [[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@var_name/bout"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/cpu:0"](var_name/bout, save/RestoreV2_10)]]
22.
23. Caused by op u'save/Assign_10', defined at:
24. File "fine_tuning.py", line 285, in
25. tf.app.run()
26. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
27. _sys.exit(main(_sys.argv[:1] + flags_passthrough))
28. File "fine_tuning.py", line 282, in main
29. run_training()
30. File "fine_tuning.py", line 211, in run_training
31. saver = tf.train.Saver(weights.values() + biases.values())
32. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1140, in init
33. self.build()
34. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1172, in build
35. filename=self._filename)
36. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 688, in build
37. restore_sequentially, reshape)
38. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 419, in _AddRestoreOps
39. assign_ops.append(saveable.restore(tensors, shapes))
40. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 155, in restore
41. self.op.get_shape().is_fully_defined())
42. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/state_ops.py", line 274, in assign
43. validate_shape=validate_shape)
44. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/gen_state_ops.py", line 43, in assign
45. use_locking=use_locking, name=name)
46. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
47. op_def=op_def)
48. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
49. original_op=self._default_original_op, op_def=op_def)
50. File "/home/hp/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1204, in init
51. self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
52.
53. InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [2] rhs shape= [101]
54. [[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@var_name/bout"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/cpu:0"](var_name/bout, save/RestoreV2_10)]]
55.

Hello,

I am trying to reproduce the results of yours. I get an error while training.

(venv) naina@naina-K401UQK:~/Desktop/internship/tensorflowC3D/C3D-tensorflow$ python train_c3d.py
/home/naina/semi/venv/lib/python2.7/site-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
2018-01-28 02:17:34.213275: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-01-28 02:17:34.300876: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-01-28 02:17:34.301330: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce 940MX major: 5 minor: 0 memoryClockRate(GHz): 1.2415
pciBusID: 0000:01:00.0
totalMemory: 1.96GiB freeMemory: 768.56MiB
2018-01-28 02:17:34.301356: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce 940MX, pci bus id: 0000:01:00.0, compute capability: 5.0)
Train the model from scratch
Traceback (most recent call last):
File "train_c3d.py", line 342, in
tf.app.run()
File "/home/naina/semi/venv/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train_c3d.py", line 338, in main
run_training()
File "train_c3d.py", line 262, in run_training
labels_placeholder: train_labels})
File "/home/naina/semi/venv/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/home/naina/semi/venv/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1096, in _run
% (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (10, 0) for Tensor u'Placeholder:0', which has shape '(?, 16, 128, 128, 3)'

Can you please suggest what could be the problem?

Thanks for authors' code.
When I run train_c3d_ucf101.py to train the network, Error shows that

ValueError: Cannot feed value of shape (10,0) for Tensor u 'Placeholder:0', which has shape '(10,16,112,112,3)'

And this is Traceback

I don't know how to solve this problem, could you tell me?

Hi, @hx173149
Thank you for sharing the wonderful work!
It seems that you don't follow the official splits, you just make the training/testing ratio 3:1.
Am I right?
Thanks.

Thank you very much for your contribution on C3D.

Is it possible to provide some information about UCF101 Training from scratch instead of finetuning? It would be very helpful to provide a graph or at least some numerical data that shows the test accuracy/loss on each epoch so that we can compare our on-going training.

Thanks.

I have trained my own model use your code, thank you for your share.
now the rate is waving only in a little scale, but I havent got the learning rate parameter，
could you tell me how can I change the learning rate ?
what is your original learning rate parameter in your train?

Hi，

I have used this C3D model to train a classifier, but, I get some problem that I cannot run this code：
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:0c:00.0)
E tensorflow/stream_executor/cuda/cuda_driver.cc:1177] could not synchronize on CUDA context: CUDA_ERROR_MISALIGNED_ADDRESS :: No stack trace available
E tensorflow/stream_executor/cuda/cuda_event.cc:49] Error polling for event status: failed to query event: CUDA_ERROR_MISALIGNED_ADDRESS
F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:198] Unexpected Event status: 1
F tensorflow/core/common_runtime/gpu/gpu_util.cc:370] GPU sync failed
Aborted (core dumped)

I find that the usage of the card is 100%.

May I ask which card you used to run this code？

Can you share your code about converting sport1m caffe model to its tensorflow version?　I tried to use this code https://github.com/ethereon/caffe-tensorflow, which did not support the video data layer. Thanks. @hx173149 @chuckcho

Hi

Thanks for providing the tensorflow version of C3D.
You mention Top-1 accuracy of 72.6% on validation, while they report 85.2% in the paper (on test). How come the performance is so much lower? Is there such a big difference between validation and test? Or can it be explained with other reasons?

I wanted to load the pretrained model which is in the form of a .model file. However as far as I know saved models in tensorflow are in the form of .meta files and can be loaded by tf.train.save_meta_files(). Can someone please let me know how can I load the graph from this model?

2018-04-12 10:47:08.094678: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-04-12 10:47:08.094730: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-04-12 10:47:08.094744: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2018-04-12 10:47:08.094758: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2018-04-12 10:47:08.094772: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2018-04-12 10:47:08.352114: I tensorflow/core/common_runtime/gpu/gpu_device.cc:887] Found device 0 with properties:
name: GeForce GTX TITAN X
major: 5 minor: 2 memoryClockRate (GHz) 1.2155
pciBusID 0000:03:00.0
Total memory: 11.92GiB
Free memory: 222.94MiB
2018-04-12 10:47:08.352169: I tensorflow/core/common_runtime/gpu/gpu_device.cc:908] DMA: 0
2018-04-12 10:47:08.352181: I tensorflow/core/common_runtime/gpu/gpu_device.cc:918] 0: Y
2018-04-12 10:47:08.352205: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX TITAN X, pci bus id: 0000:03:00.0)
2018-04-12 10:47:21.296425: W tensorflow/core/common_runtime/bfc_allocator.cc:273] Allocator (GPU_0_bfc) ran out of memory trying to allocate 27.00MiB. Current allocation summary follows.
2018-04-12 10:47:21.296492: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (256): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296501: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (512): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296510: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1024): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296518: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2048): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296527: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4096): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296537: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8192): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296546: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16384): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296555: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (32768): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296563: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (65536): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296571: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (131072): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296579: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (262144): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296587: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (524288): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296596: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1048576): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296604: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2097152): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296613: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4194304): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296621: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8388608): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296631: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16777216): Total Chunks: 1, Chunks in use: 0 22.94MiB allocated for chunks. 13.50MiB client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296640: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (33554432): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296648: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (67108864): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296657: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (134217728): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296665: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (268435456): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.296673: I tensorflow/core/common_runtime/bfc_allocator.cc:660] Bin for 27.00MiB was 16.00MiB, Chunk State:
2018-04-12 10:47:21.296689: I tensorflow/core/common_runtime/bfc_allocator.cc:666] Size: 22.94MiB | Requested Size: 13.50MiB | in_use: 0, prev: Size: 256B | Requested Size: 4B | in_use: 1
2018-04-12 10:47:21.296698: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0000 of size 1280
2018-04-12 10:47:21.296705: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0500 of size 256
2018-04-12 10:47:21.296711: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0600 of size 256
2018-04-12 10:47:21.296717: I tensorflow/core/common_runtime/bfc_allocator.cc:687] Free at 0x420a3c0700 of size 24049920
2018-04-12 10:47:21.296722: I tensorflow/core/common_runtime/bfc_allocator.cc:693] Summary of in-use Chunks by size:
2018-04-12 10:47:21.296730: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 2 Chunks of size 256 totalling 512B
2018-04-12 10:47:21.296738: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 1280 totalling 1.2KiB
2018-04-12 10:47:21.296745: I tensorflow/core/common_runtime/bfc_allocator.cc:700] Sum Total of in-use chunks: 1.8KiB
2018-04-12 10:47:21.296757: I tensorflow/core/common_runtime/bfc_allocator.cc:702] Stats:
Limit: 24051712
InUse: 1792
MaxInUse: 24051712
NumAllocs: 20
MaxAllocSize: 24049920

2018-04-12 10:47:21.296769: W tensorflow/core/common_runtime/bfc_allocator.cc:277] *___________________________________________________________________________________________________
2018-04-12 10:47:21.300202: W tensorflow/core/common_runtime/bfc_allocator.cc:273] Allocator (GPU_0_bfc) ran out of memory trying to allocate 27.00MiB. Current allocation summary follows.
2018-04-12 10:47:21.300224: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (256): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300234: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (512): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300242: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1024): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300250: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2048): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300258: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4096): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300266: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8192): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300274: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16384): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300282: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (32768): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300290: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (65536): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300298: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (131072): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300308: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (262144): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300315: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (524288): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300323: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1048576): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300331: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2097152): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300340: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4194304): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300348: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8388608): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300358: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16777216): Total Chunks: 1, Chunks in use: 0 22.94MiB allocated for chunks. 13.50MiB client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300368: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (33554432): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300378: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (67108864): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300385: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (134217728): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300394: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (268435456): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.300403: I tensorflow/core/common_runtime/bfc_allocator.cc:660] Bin for 27.00MiB was 16.00MiB, Chunk State:
2018-04-12 10:47:21.300414: I tensorflow/core/common_runtime/bfc_allocator.cc:666] Size: 22.94MiB | Requested Size: 13.50MiB | in_use: 0, prev: Size: 256B | Requested Size: 4B | in_use: 1
2018-04-12 10:47:21.300422: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0000 of size 1280
2018-04-12 10:47:21.300429: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0500 of size 256
2018-04-12 10:47:21.300436: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0600 of size 256
2018-04-12 10:47:21.300442: I tensorflow/core/common_runtime/bfc_allocator.cc:687] Free at 0x420a3c0700 of size 24049920
2018-04-12 10:47:21.300449: I tensorflow/core/common_runtime/bfc_allocator.cc:693] Summary of in-use Chunks by size:
2018-04-12 10:47:21.300457: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 2 Chunks of size 256 totalling 512B
2018-04-12 10:47:21.300465: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 1280 totalling 1.2KiB
2018-04-12 10:47:21.300475: I tensorflow/core/common_runtime/bfc_allocator.cc:700] Sum Total of in-use chunks: 1.8KiB
2018-04-12 10:47:21.300483: I tensorflow/core/common_runtime/bfc_allocator.cc:702] Stats:
Limit: 24051712
InUse: 1792
MaxInUse: 24051712
NumAllocs: 20
MaxAllocSize: 24049920

2018-04-12 10:47:21.300492: W tensorflow/core/common_runtime/bfc_allocator.cc:277] *___________________________________________________________________________________________________
2018-04-12 10:47:21.302355: W tensorflow/core/common_runtime/bfc_allocator.cc:273] Allocator (GPU_0_bfc) ran out of memory trying to allocate 27.00MiB. Current allocation summary follows.
2018-04-12 10:47:21.302386: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (256): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302394: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (512): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302402: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1024): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302412: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2048): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302420: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4096): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302428: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8192): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302436: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16384): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302444: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (32768): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302453: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (65536): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302461: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (131072): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302469: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (262144): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302476: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (524288): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302484: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1048576): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302492: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2097152): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302500: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4194304): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302508: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8388608): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302520: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16777216): Total Chunks: 1, Chunks in use: 0 22.94MiB allocated for chunks. 13.50MiB client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302528: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (33554432): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302536: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (67108864): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302545: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (134217728): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302553: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (268435456): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.302564: I tensorflow/core/common_runtime/bfc_allocator.cc:660] Bin for 27.00MiB was 16.00MiB, Chunk State:
2018-04-12 10:47:21.302576: I tensorflow/core/common_runtime/bfc_allocator.cc:666] Size: 22.94MiB | Requested Size: 13.50MiB | in_use: 0, prev: Size: 256B | Requested Size: 4B | in_use: 1
2018-04-12 10:47:21.302584: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0000 of size 1280
2018-04-12 10:47:21.302589: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0500 of size 256
2018-04-12 10:47:21.302596: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0600 of size 256
2018-04-12 10:47:21.302600: I tensorflow/core/common_runtime/bfc_allocator.cc:687] Free at 0x420a3c0700 of size 24049920
2018-04-12 10:47:21.302607: I tensorflow/core/common_runtime/bfc_allocator.cc:693] Summary of in-use Chunks by size:
2018-04-12 10:47:21.302613: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 2 Chunks of size 256 totalling 512B
2018-04-12 10:47:21.302620: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 1280 totalling 1.2KiB
2018-04-12 10:47:21.302627: I tensorflow/core/common_runtime/bfc_allocator.cc:700] Sum Total of in-use chunks: 1.8KiB
2018-04-12 10:47:21.302635: I tensorflow/core/common_runtime/bfc_allocator.cc:702] Stats:
Limit: 24051712
InUse: 1792
MaxInUse: 24051712
NumAllocs: 20
MaxAllocSize: 24049920

2018-04-12 10:47:21.302644: W tensorflow/core/common_runtime/bfc_allocator.cc:277] *___________________________________________________________________________________________________
2018-04-12 10:47:21.911379: W tensorflow/core/common_runtime/bfc_allocator.cc:273] Allocator (GPU_0_bfc) ran out of memory trying to allocate 64.00MiB. Current allocation summary follows.
2018-04-12 10:47:21.911405: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (256): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911414: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (512): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911421: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1024): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911428: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2048): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911436: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4096): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911444: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8192): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911453: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16384): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911463: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (32768): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911473: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (65536): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911482: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (131072): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911492: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (262144): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911500: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (524288): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911508: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1048576): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911517: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2097152): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911525: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4194304): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911533: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8388608): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911545: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16777216): Total Chunks: 1, Chunks in use: 0 22.94MiB allocated for chunks. 13.50MiB client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911554: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (33554432): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911564: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (67108864): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911572: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (134217728): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911580: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (268435456): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.911589: I tensorflow/core/common_runtime/bfc_allocator.cc:660] Bin for 64.00MiB was 64.00MiB, Chunk State:
2018-04-12 10:47:21.911596: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0000 of size 1280
2018-04-12 10:47:21.911604: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0500 of size 256
2018-04-12 10:47:21.911611: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0600 of size 256
2018-04-12 10:47:21.911619: I tensorflow/core/common_runtime/bfc_allocator.cc:687] Free at 0x420a3c0700 of size 24049920
2018-04-12 10:47:21.911626: I tensorflow/core/common_runtime/bfc_allocator.cc:693] Summary of in-use Chunks by size:
2018-04-12 10:47:21.911634: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 2 Chunks of size 256 totalling 512B
2018-04-12 10:47:21.911642: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 1280 totalling 1.2KiB
2018-04-12 10:47:21.911649: I tensorflow/core/common_runtime/bfc_allocator.cc:700] Sum Total of in-use chunks: 1.8KiB
2018-04-12 10:47:21.911659: I tensorflow/core/common_runtime/bfc_allocator.cc:702] Stats:
Limit: 24051712
InUse: 1792
MaxInUse: 24051712
NumAllocs: 20
MaxAllocSize: 24049920

2018-04-12 10:47:21.911669: W tensorflow/core/common_runtime/bfc_allocator.cc:277] *___________________________________________________________________________________________________
2018-04-12 10:47:21.924118: W tensorflow/core/common_runtime/bfc_allocator.cc:273] Allocator (GPU_0_bfc) ran out of memory trying to allocate 128.00MiB. Current allocation summary follows.
2018-04-12 10:47:21.924160: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (256): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924177: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (512): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924194: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1024): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924211: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2048): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924227: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4096): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924242: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8192): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924257: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16384): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924272: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (32768): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924287: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (65536): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924302: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (131072): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924317: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (262144): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924332: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (524288): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924347: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (1048576): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924362: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (2097152): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924377: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (4194304): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924392: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (8388608): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924412: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (16777216): Total Chunks: 1, Chunks in use: 0 22.94MiB allocated for chunks. 13.50MiB client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924428: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (33554432): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924443: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (67108864): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924458: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (134217728): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924473: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (268435456): Total Chunks: 0, Chunks in use: 0 0B allocated for chunks. 0B client-requested for chunks. 0B in use in bin. 0B client-requested in use in bin.
2018-04-12 10:47:21.924491: I tensorflow/core/common_runtime/bfc_allocator.cc:660] Bin for 128.00MiB was 128.00MiB, Chunk State:
2018-04-12 10:47:21.924505: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0000 of size 1280
2018-04-12 10:47:21.924517: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0500 of size 256
2018-04-12 10:47:21.924530: I tensorflow/core/common_runtime/bfc_allocator.cc:678] Chunk at 0x420a3c0600 of size 256
2018-04-12 10:47:21.924541: I tensorflow/core/common_runtime/bfc_allocator.cc:687] Free at 0x420a3c0700 of size 24049920
2018-04-12 10:47:21.924552: I tensorflow/core/common_runtime/bfc_allocator.cc:693] Summary of in-use Chunks by size:
2018-04-12 10:47:21.924564: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 2 Chunks of size 256 totalling 512B
2018-04-12 10:47:21.924580: I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 1280 totalling 1.2KiB
2018-04-12 10:47:21.924594: I tensorflow/core/common_runtime/bfc_allocator.cc:700] Sum Total of in-use chunks: 1.8KiB
2018-04-12 10:47:21.924610: I tensorflow/core/common_runtime/bfc_allocator.cc:702] Stats:
Limit: 24051712
InUse: 1792
MaxInUse: 24051712
NumAllocs: 20
MaxAllocSize: 24049920

2018-04-12 10:47:21.924628: W tensorflow/core/common_runtime/bfc_allocator.cc:277] *___________________________________________________________________________________________________
Traceback (most recent call last):
File "train_c3d_ucf101.py", line 261, in
tf.app.run()
File "/home/lyynew/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train_c3d_ucf101.py", line 258, in main
run_training()
File "train_c3d_ucf101.py", line 204, in run_training
sess.run(init)
File "/home/lyynew/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/home/lyynew/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/home/lyynew/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/home/lyynew/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Dst tensor is not initialized.
[[Node: cond_6/Switch_1/_157 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_390_cond_6/Switch_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]]

Hi
I run your code train_c3d_ucf101.py and predict_c3d_ucf101.py, both of them have a ValueError
ValueError: Cannot feed value of shape (10, 0) for Tensor u'Placeholder:0', which has shape '(10, 16, 112, 112, 3)'. And I find in train_c3d_ucf101.py, this error happend in line 232
sess.run(train_op, feed_dict={ images_placeholder: train_images, labels_placeholder: train_labels })
Do you have any idea why it failed? I use tensorflow 0.11.

Hello everyone,

I have a question about training this model with different dataset.

When i finetune the c3d model with UCF101 data, there is no problem. But when i change the dataset i have got this error that loss is Nan Value.

I tried some ways to handle this problem which did not solve it.

1. changed the learning rate
2. changed batch size
3. tried with small test and train split ( with #num : 3)

For instance, these are steps of training same model with different dataset.
Learning rates and batch size are same with original as this model. Just dataset is changed.

('Step : ', 31)
------------------------------------------------------------------
 TRAIN DATA READING  ...
Training Data Eval:
accuracy: 0.00000
(' Loss : ', array([ 2.60935736,  2.62928033,  2.65052104,  2.6719377 ,  2.69320059,
        2.7358048 ,  2.73551226,  2.73502755,  3.95449066,  3.61877584,
        2.61726952,  2.60790229,  2.60790229,  2.60790229,  2.60790229,
        2.60790229,  2.60790229,  2.60790229,  2.60790229,  2.60790229,
        2.60790229,  2.60790229], dtype=float32))
 TEST DATA READING  ...
Validation Data Eval:
accuracy: 0.00000
('Step : ', 32)
------------------------------------------------------------------
 TRAIN DATA READING  ...
Training Data Eval:
accuracy: 0.10000
(' Loss : ', array([ 3.21029162,  3.2302146 ,  3.25145531,  3.27287173,  3.29413438,
        3.33673644,  3.33644032,  3.33594394,  4.55498886,  4.21940422,
        3.21820426,  3.20883656,  3.20883656,  3.20883656,  3.20883656,
        3.20883656,  3.20883656,  3.20883656,  3.20883656,  3.20883656,
        3.20883656,  3.20883656], dtype=float32))
 TEST DATA READING  ...
Validation Data Eval:
accuracy: 0.20000
('Step : ', 33)
------------------------------------------------------------------
 TRAIN DATA READING  ...
Training Data Eval:
accuracy: 0.30000
(' Loss : ', array([ 2.50483251,  2.52475548,  2.54599619,  2.56741214,  2.58867455,
        2.63127494,  2.63097525,  2.63046718,  3.84910154,  3.51364231,
        2.51274562,  2.50337744,  2.50337744,  2.50337744,  2.50337744,
        2.50337744,  2.50337744,  2.50337744,  2.50337744,  2.50337744,
        2.50337744,  2.50337744], dtype=float32))
 TEST DATA READING  ...
Validation Data Eval:
accuracy: 0.00000
('Step : ', 34)
------------------------------------------------------------------
 TRAIN DATA READING  ...
Training Data Eval:
accuracy: 0.00000
(' Loss : ', array([ nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,
        nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan], dtype=float32))
 TEST DATA READING  ...
Validation Data Eval:
accuracy: 0.00000

Where should be the problem ?
Why does not this model work with different dataset ?
Any suggestion?
Thank you.

Hi,
I was just wondering how many iterations are necessary to train this network. I am not using the pre-trained model and training on the UCF-101 dataset with 16 frames.
In issue #2, an accuracy of over 90% was reached after 10 000, however for me, I am still at 0% training and validation accuracy after 3000 iterations.
How many iterations should I run?

Hi,

The accuracy at the first 300 step is 0.1000 or 0.0500. Is this normal or is there something wrong?

Thank you