errors in maxpooling

[dgai91]

Testing started at 14:37 ... C:\ProgramData\Anaconda3\python.exe "C:\Program Files\JetBrains\PyCharm 2017.3.4\helpers\pycharm_jb_pytest_runner.py" --path C:/Users/LawLi/PycharmProjects/Micro-Expression-with-Deep-Learning-master/test_spatial_only.py Launching py.test with arguments C:/Users/LawLi/PycharmProjects/Micro-Expression-with-Deep-Learning-master/test_spatial_only.py in C:\Users\LawLi\PycharmProjects\Micro-Expression-with-Deep-Learning-master

============================= test session starts ============================= platform win32 -- Python 3.6.4, pytest-3.3.2, py-1.5.2, pluggy-0.6.0 rootdir: C:\Users\LawLi\PycharmProjects\Micro-Expression-with-Deep-Learning-master, inifile:Datasets/CASME2_TIM/CASME2_TIM/ [ 9. 13. 7. 5. 19. 5. 9. 3. 15. 14. 10. 12. 8. 4. 3. 4. 36. 3.

16. 11. 2. 2. 12. 11. 7. 17.] [ 8. 8. 9. 16. 16. 18. 23. 23. 23. 23. 25.] Loaded Images into the tray... Loaded Labels into the tray... C:\ProgramData\Anaconda3\lib\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 Using TensorFlow backend.

test_spatial_only.py:None (test_spatial_only.py) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1567: in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) E tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

During handling of the above exception, another exception occurred: test_spatial_only.py:112: in vgg_model = VGG_16_tim(spatial_size, classes=5, channels=3) models.py:199: in VGG_16_tim model.add(MaxPooling2D((2, 2), strides=(2, 2))) C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py:492: in add output_tensor = layer(self.outputs[0]) C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py:619: in call output = self.call(inputs, **kwargs) C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\pooling.py:158: in call data_format=self.data_format) C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\pooling.py:221: in _pooling_function pool_mode='max') C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:3657: in pool2d data_format=tf_data_format) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_ops.py:2142: in max_pool name=name) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py:5045: in max_pool data_format=data_format, name=name) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:787: in _apply_op_helper op_def=op_def) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:3392: in create_op op_def=op_def) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1734: in init control_input_ops) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1570: in _create_c_op raise ValueError(str(e)) E ValueError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128]. collected 0 items / 1 errors =================================== ERRORS ==================================== ____ ERROR collecting test_spatial_only.py ____ C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1567: in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) E tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

During handling of the above exception, another exception occurred: test_spatial_only.py:112: in vgg_model = VGG_16_tim(spatial_size, classes=5, channels=3) models.py:199: in VGG_16_tim model.add(MaxPooling2D((2, 2), strides=(2, 2))) C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py:492: in add output_tensor = layer(self.outputs[0]) C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py:619: in call output = self.call(inputs, **kwargs) C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\pooling.py:158: in call data_format=self.data_format) C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\pooling.py:221: in _pooling_function pool_mode='max') C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:3657: in pool2d data_format=tf_data_format) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_ops.py:2142: in max_pool name=name) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py:5045: in max_pool data_format=data_format, name=name) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:787: in _apply_op_helper op_def=op_def) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:3392: in create_op op_def=op_def) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1734: in init control_input_ops) C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1570: in _create_c_op raise ValueError(str(e)) E ValueError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128]. ------------------------------- Captured stdout ------------------------------- Datasets/CASME2_TIM/CASME2_TIM/ [ 9. 13. 7. 5. 19. 5. 9. 3. 15. 14. 10. 12. 8. 4. 3. 4. 36. 3.

16. 11. 2. 2. 12. 11. 7. 17.] [ 8. 8. 9. 16. 16. 18. 23. 23. 23. 23. 25.] Loaded Images into the tray... Loaded Labels into the tray... ------------------------------- Captured stderr ------------------------------- C:\ProgramData\Anaconda3\lib\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 Using TensorFlow backend. !!!!!!!!!!!!!!!!!!! Interrupted: 1 errors during collection !!!!!!!!!!!!!!!!!!! ========================== 1 error in 14.94 seconds =========================== Process finished with exit code 0

[dgai91]

Hi, I've been testing the code of test_spatial_only.py there are some errors in model

[IcedDoggie]

Hi, for the max pooling error, can you try to run using theano backend and see if it works? for the test_spatial_only.py, i apologize that the code is a quick script i wrote pretty in a pretty hardcoded manner. its usage is to test how well the vgg itself in classifying emotion, without the use of lstm. or can you specify the error on the test_spatial_only so that i can help?

[IcedDoggie]

for replicating our work in single db, you can run this

python main.py --dB 'CASME2_Optical' --batch_size=1 --spatial_epochs=100 --temporal_epochs=100 --train_id='default_test' --spatial_size=224 --flag='st'

or you can refer to the documentation below.

[dgai91]

I'd found the cause of these error. Because of the channel whether first

[IcedDoggie]

Oh. great. Any further issues please do not hesitate to msg me. :)

[dgai91]

so kind of you :)

[dgai91]

sorry for bother you this time. when I run main.py there is 2 strange error. the error is ValueError: cannot reshape array of size 373309440 into shape (2232,224,224,3) This error is raised because of the timestep_tim=9. if I change timestep_tim=10 there is a new error: ValueError: Input arrays should have the same number of samples as target arrays. Found 2480 input samples and 2370 target samples.

[IcedDoggie]

to clarify, timestep_tim = 9 is because optical_flow_image and optical_strain_image is taking displacement/derivative of the 10 original frames. Are you training on optical_image or the grayscale image? What is the db name you are using?

[IcedDoggie]

btw, just asking, are you from MEGC?

[dgai91]

emmm.... no.I am a NLP researcher in a CN U. my db is CASME2_Optical

[dgai91]

btw, do you know Detriot: Become human :)

[IcedDoggie]

Nope. Do you have this line in your code? listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(db_path, list_db)

[dgai91]

  elif db_name == 'CASME2_Optical':
        print("arrived")
        table = loading_casme_table(db_home + 'CASME2_label_Ver_2.xls')
        listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(db_path, list_db)

        r = w = spatial_size
        subjects = 26
        samples = 246
        n_exp = 5
        VidPerSubject = get_subfolders_num(db_images, IgnoredSamples_index)

        timesteps_TIM = 10
        data_dim = r * w
        channel = 3

        if os.path.isdir(db_home + "Classification/" + db_name + "_label.txt") == True:
            os.remove(db_home + "Classification/" + db_name + "_label.txt")

[IcedDoggie]

is your folders named in this format for subject and video directory? eg: subject 9 and video 13_02 'sub09/EP13_02/'

[dgai91]

yeah, the dataset has been downloaded from the url you offered, and I did not modify any thing

[IcedDoggie]

The error exists because the algorithm should omit some files (due to small class problem) and 11 videos should be omitted. I am confuse as well....

[IcedDoggie]

May I know how to do you call python main.py?

[dgai91]

thank you all the same :) if you fix this problem, plz update this repo

[IcedDoggie]

Because it works on my pc. does the following works? python main.py --dB 'CASME2_Optical' --batch_size=30 --spatial_epochs=100 --temporal_epochs=100 --train_id='default_test' --spatial_size=224 --flag='st'

[dgai91]

I can not run this code using these param but I deleted the data which should be ignored. and that worked :)