search

hx173149 / C3D-tensorflow

C3D is a modified version of BVLC tensorflow to support 3D ConvNets.
MIT License
588 stars 265 forks source link

weight.values,bias.values error #98

Open abhisheksurya578 opened 5 years ago

abhisheksurya578 commented 5 years ago

Hi @hx173149 @gudongfeng @chuckcho @cc786537662

File "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 171, in run_training varlist1 = list(set(weights.values() + biases.values()) - set(varlist2)) TypeError: unsupported operand type(s) for +: 'dict_values' and 'dict_values'

highway007 commented 5 years ago

Hi ,change to: varlist1 = list( set(list(weights.values()) + list(biases.values())) - set(varlist2) ) and see if it work

abhisheksurya578 commented 5 years ago

Hello

Thanks the issue is resolved now.But 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?

highway007 commented 5 years ago

@abhisheksurya578 Can you post the whole terminal output? And I think this issue is something about py3 and py2 .Authers's code was base on py2 , however you did this on py3 . (Right? You can run it on py3 after changed some code also)

abhisheksurya578 commented 5 years ago

thanks for responding @highway007 , @hx173149 /home/ltroot/PycharmProjects/C3D/venv/bin/python /home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py 2019-03-18 05:26:10.050805: 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. 2019-03-18 05:26:10.050833: 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. 2019-03-18 05:26:10.050838: 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. 2019-03-18 05:26:10.050843: 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. 2019-03-18 05:26:10.050848: 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 "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 262, in tf.app.run() File "/home/ltroot/PycharmProjects/C3D/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 259, in main run_training() File "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 224, in run_training labels_placeholder: train_labels File "/home/ltroot/PycharmProjects/C3D/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 789, in run run_metadata_ptr) File "/home/ltroot/PycharmProjects/C3D/venv/lib/python3.5/site-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 'Placeholder:0', which has shape '(20, 16, 112, 112, 3)' help me to resolve this

abhisheksurya578 commented 5 years ago

Traceback (most recent call last): File "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 262, in tf.app.run() File "/home/ltroot/PycharmProjects/C3D/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 259, in main run_training() File "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 224, in run_training labels_placeholder: train_labels File "/home/ltroot/PycharmProjects/C3D/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 789, in run run_metadata_ptr) File "/home/ltroot/PycharmProjects/C3D/venv/lib/python3.5/site-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 'Placeholder:0', which has shape '(20, 16, 112, 112, 3)' help me to resolve this

highway007 commented 5 years ago

@abhisheksurya578 So did you run the demo with your own dataset? Can you show me lines of your train.list?

abhisheksurya578 commented 5 years ago

No I haven't tried on my own dataset.I have used ucf-101 and your train.list and test.list from git repository.

On Thu, Mar 21, 2019 at 3:56 PM highway007 notifications@github.com wrote:

@abhisheksurya578 https://github.com/abhisheksurya578 So did you run the demo with your own dataset? Can you show me lines of your train.list?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/hx173149/C3D-tensorflow/issues/98#issuecomment-475177765, or mute the thread https://github.com/notifications/unsubscribe-auth/As_iWkaUx8tzoBE-RpG-6X6tjflX4HG-ks5vY15vgaJpZM4boaTy .

highway007 commented 5 years ago

@abhisheksurya578 My list isn't for ucf101,you should run ./list/**** like the readme to get it.(you should download the ucf101 dataset also.

abhisheksurya578 commented 5 years ago

Our Train.list

/ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g08_c01 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g08_c02 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g08_c03 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g08_c04 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g08_c05 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g09_c01 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g09_c02 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g09_c03 0

our Test.list

/ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c01 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c02 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c03 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c04 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c05 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c06 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g02_c01 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g02_c02 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g02_c03 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g02_c04 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g03_c01 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g03_c02 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g03_c03 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g03_c04 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g03_c05 0 /ds_data/ucfimgs/ApplyEyeMakeup/v_ApplyEyeMakeup_g03_c06 0

We tried running convert_videos to imgs.sh but we end up with following error./list/convert_video_to_images.sh: line 25: ffmpeg: command not foundrm: cannot remove 'ds_data/UCF-101//.avi': No such file or directory

Inside the UCF-101 dataset every video file got erased and only folder structure exists.

If we tried with existing train.list and test.list by modifying path inside train.list and test.list paths.

2019-03-21 13:37:33.719790: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): , WARNING:tensorflow:From /root/PycharmProjects/c3d/venv/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. Traceback (most recent call last): File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 261, in tf.app.run() File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 258, in main run_training() File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 223, in run_training labels_placeholder: train_labels File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 929, in run run_metadata_ptr) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1128, in _run str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (20, 0) for Tensor 'Placeholder:0', which has shape '(20, 16, 112, 112, 3)'

On Thu, 21 Mar 2019 at 5:39 PM, highway007 notifications@github.com wrote:

@abhisheksurya578 https://github.com/abhisheksurya578 My list isn't for ucf101,you should run ./list/**** like the readme to get it.(you should download the ucf101 dataset also.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/hx173149/C3D-tensorflow/issues/98#issuecomment-475204789, or mute the thread https://github.com/notifications/unsubscribe-auth/As_iWkIcB1jWxQ-BKvj_d6y-gDnCpoCAks5vY3Z0gaJpZM4boaTy .

highway007 commented 5 years ago

@abhisheksurya578 hi, you should make sure that ./list/convert_video_to_images.sh *** 5 is the same name with your ucf101 file.It is a issue that path in your list is different from path in error.suggest you check file name carefully.

abhisheksurya578 commented 5 years ago

Hello I’m done with running video to img and img to list.sh files.But while running train.py I’m facing this issue

tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): , WARNING:tensorflow:From /root/PycharmProjects/c3d/venv/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. Traceback (most recent call last): File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 261, in tf.app.run() File "/root/PycharmProjects/c3d/venv/lib/python3.5/site- packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 258, in main run_training() File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 223, in run_training labels_placeholder: train_labels File "/root/PycharmProjects/c3d/venv/lib/python3.5/site- packages/tensorflow/python/client/session.py", line 929, in run run_metadata_ptr) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1128, in _run str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (20, 0) for Tensor 'Placeholder:0', which has shape '(20, 16, 112, 112, 3)

On Fri, 22 Mar 2019 at 7:23 AM, highway007 notifications@github.com wrote:

@abhisheksurya578 https://github.com/abhisheksurya578 hi, you should make sure that ./list/convert_video_to_images.sh *** 5 is the same name with your ucf101 file.It is a issue that path in your list is different from path in error.suggest you check file name carefully.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/hx173149/C3D-tensorflow/issues/98#issuecomment-475466420, or mute the thread https://github.com/notifications/unsubscribe-auth/As_iWl0NXm1Euvrn7BdpLA---OQvtBlaks5vZDeXgaJpZM4boaTy .

highway007 commented 5 years ago

@abhisheksurya578 Can you see the images from the path in your train.list?

abhisheksurya578 commented 5 years ago

No I can just see the image paths not images

On Fri, 22 Mar 2019 at 5:31 PM, highway007 notifications@github.com wrote:

@abhisheksurya578 https://github.com/abhisheksurya578 Can you see the images from the path in your train.list?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/hx173149/C3D-tensorflow/issues/98#issuecomment-475594630, or mute the thread https://github.com/notifications/unsubscribe-auth/As_iWv6ylWTR56E-cA2b2rGsCQnNQnMkks5vZMYDgaJpZM4boaTy .

highway007 commented 5 years ago

@abhisheksurya578 if you run video to img and img to list.sh successfully,you can see images with the path in train.list.

abhisheksurya578 commented 5 years ago

Yeah I successfully ran video to img and img to list.sh but I’m facing the issue

On Fri, 22 Mar 2019 at 5:37 PM, highway007 notifications@github.com wrote:

@abhisheksurya578 https://github.com/abhisheksurya578 if you run video to img and img to list.sh successfully,you can see images with the path in train.list.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/hx173149/C3D-tensorflow/issues/98#issuecomment-475596415, or mute the thread https://github.com/notifications/unsubscribe-auth/As_iWnwXY4buYAmak757eia2SmCbJ9yXks5vZMdrgaJpZM4boaTy .

highway007 commented 5 years ago

@abhisheksurya578 There must be some error when you run .sh :(

abhisheksurya578 commented 5 years ago

Hello ,

i have successfully trained UCF for 101 classes.But I just wanna train for 16 classes.I have changed the parameter no of classes to 16.It worked when i make use_pretrain=FALSE. If i use sports_1m fine tune model weights I got the following error. How to use sports1m for 16 classes and Is there any parameter we need to change for 16 classes.

Use standard file APIs to check for files with this prefix. Traceback (most recent call last): File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call return fn(*args) File "/root/PycharmProjects/c3d/venv/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 "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [4096,16] rhs shape= [4096,101] [[{{node save/Assign_21}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 1276, in restore {self.saver_def.filename_tensor_name: save_path}) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 929, in run run_metadata_ptr) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1152, in _run feed_dict_tensor, options, run_metadata) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run run_metadata) File "/root/PycharmProjects/c3d/venv/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: Assign requires shapes of both tensors to match. lhs shape= [4096,16] rhs shape= [4096,101] [[node save/Assign_21 (defined at /home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py:197) ]]

Caused by op 'save/Assign_21', defined at: File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 261, in tf.app.run() File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 258, in main run_training() File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 197, in run_training saver = tf.train.Saver(list(weights.values()) + list(biases.values())) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 832, in init self.build() File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 844, in build self._build(self._filename, build_save=True, build_restore=True) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 881, in _build build_save=build_save, build_restore=build_restore) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 513, in _build_internal restore_sequentially, reshape) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 354, in _AddRestoreOps assign_ops.append(saveable.restore(saveable_tensors, shapes)) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saving/saveable_object_util.py", line 73, in restore self.op.get_shape().is_fully_defined()) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/ops/state_ops.py", line 223, in assign validate_shape=validate_shape) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/ops/gen_state_ops.py", line 64, in assign use_locking=use_locking, name=name) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op op_def=op_def) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1801, in init self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [4096,16] rhs shape= [4096,101] [[node save/Assign_21 (defined at /home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py:197) ]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 261, in tf.app.run() File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 258, in main run_training() File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 206, in run_training saver.restore(sess, model_filename) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 1312, in restore err, "a mismatch between the current graph and the graph") tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Assign requires shapes of both tensors to match. lhs shape= [4096,16] rhs shape= [4096,101] [[node save/Assign_21 (defined at /home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py:197) ]]

Caused by op 'save/Assign_21', defined at: File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 261, in tf.app.run() File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 258, in main run_training() File "/home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py", line 197, in run_training saver = tf.train.Saver(list(weights.values()) + list(biases.values())) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 832, in init self.build() File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 844, in build self._build(self._filename, build_save=True, build_restore=True) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 881, in _build build_save=build_save, build_restore=build_restore) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 513, in _build_internal restore_sequentially, reshape) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 354, in _AddRestoreOps assign_ops.append(saveable.restore(saveable_tensors, shapes)) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/training/saving/saveable_object_util.py", line 73, in restore self.op.get_shape().is_fully_defined()) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/ops/state_ops.py", line 223, in assign validate_shape=validate_shape) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/ops/gen_state_ops.py", line 64, in assign use_locking=use_locking, name=name) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op op_def=op_def) File "/root/PycharmProjects/c3d/venv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1801, in init self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Assign requires shapes of both tensors to match. lhs shape= [4096,16] rhs shape= [4096,101] [[node save/Assign_21 (defined at /home/ltroot/Downloads/C3D-tensorflow-master/train_c3d_ucf101.py:197) ]] Please help

On Fri, Mar 22, 2019 at 12:42 PM highway007 notifications@github.com wrote:

@abhisheksurya578 https://github.com/abhisheksurya578 There must be some error when you run .sh :(

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/hx173149/C3D-tensorflow/issues/98#issuecomment-475607093, or mute the thread https://github.com/notifications/unsubscribe-auth/As_iWkH3EYXAVrSUFqOMad8JCxHJLNEfks5vZM_NgaJpZM4boaTy .

AndyHon commented 5 years ago

Cannot feed value of shape (11, 16, 160, 160, 3) for Tensor 'Placeholder:0', which has shape '(12, 16, 160, 160, 3)' What should I do about it?help me,thanks