train model

[Leila-sd]

Hi, I successfully run it on the samples images using your pretrained model. Now i'm trying to retrain the models using your code but get this error:
Using Theano backend.
/home/kntu/anaconda3/lib/python3.6/site-packages/keras/backend/theano_backend.py:1282: UserWarning: DEPRECATION: the 'ds' parameter is not going to exist anymore as it is going to be replaced by the parameter 'ws'.
mode='max')
/home/kntu/anaconda3/lib/python3.6/site-packages/keras/backend/theano_backend.py:1282: UserWarning: DEPRECATION: the 'st' parameter is not going to exist anymore as it is going to be replaced by the parameter 'stride'.
mode='max')
/home/kntu/anaconda3/lib/python3.6/site-packages/keras/backend/theano_backend.py:1282: UserWarning: DEPRECATION: the 'padding' parameter is not going to exist anymore as it is going to be replaced by the parameter 'pad'.
mode='max')
/home/kntu/anaconda3/lib/python3.6/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
Compiling SAM-ResNet
Training SAM-ResNet
Epoch 1/10
Exception in thread Thread-1:
Traceback (most recent call last):
File "/home/kntu/anaconda3/lib/python3.6/threading.py", line 916, in _bootstrap_inner
self.run()
File "/home/kntu/anaconda3/lib/python3.6/threading.py", line 864, in run
self._target(*self._args, **self._kwargs)
File "/home/kntu/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 425, in data_generator_task
generator_output = next(generator)
File "main.py", line 46, in generator
Y_fix = preprocess_fixmaps(fixs[counter:counter + b_s], shape_r_out, shape_c_out)
File "/home/kntu/LS/new_sam/sam-master/sam-master/utilities.py", line 106, in preprocess_fixmaps
fix_map = scipy.io.loadmat(path)["I"]
KeyError: 'I'

Traceback (most recent call last):
File "main.py", line 97, in
ModelCheckpoint('weights.sam-resnet.{epoch:02d}-{val_loss:.4f}.pkl', save_best_only=True)])
File "/home/kntu/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1417, in fit_generator
'or (x, y). Found: ' + str(generator_output))
Exception: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None
thanks.

[marcellacornia]

Hi @Leila-sd,
sorry for the late reply.

Our training code is compatible with images coming from the SALICON dataset, where both saliency density map and fixation map are provided for each image. The error you reported seems to be related to the lack of fixation maps.

[Leila-sd]

Thanks for your consideration.

[Leila-sd]

Hi Based on the paper, I want to get the output from the first and second time steps. But when I changed the time step variable in the source code, I did not get the desired output. Conversely my expectation, the output does not change. Do you have any idea about this problem? Kind regards,

…

On Tue, Jul 9, 2019 at 4:30 PM Marcella Cornia ***@***.***> wrote: Hi @Leila-sd <https://github.com/Leila-sd>, sorry for the late reply. Our training code is compatible with images coming from the SALICON dataset, where both saliency density map and fixation map are provided for each image. The error you reported seems to be related to the lack of fixation maps. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#32?email_source=notifications&email_token=AL5IQZ45PXEXWXMUMWUXR6DP6R4VVA5CNFSM4H4M2PB2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZQBMMA#issuecomment-509613616>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AL5IQZ2F7ZCTEGZHMH4TJNTP6R4VVANCNFSM4H4M2PBQ> .