New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Optimizer problem #244
Comments
Did you fix this problem? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
When i run the training file, i got the error below in the last cell of the code file:
Training details:
INFO:ISR.utils.train_helper:
Training details:
training_parameters:
INFO:ISR.utils.train_helper: training_parameters:
lr_train_dir: div2k/DIV2K_train_LR_bicubic/X2/
INFO:ISR.utils.train_helper: lr_train_dir: div2k/DIV2K_train_LR_bicubic/X2/
hr_train_dir: div2k/DIV2K_train_HR/
INFO:ISR.utils.train_helper: hr_train_dir: div2k/DIV2K_train_HR/
lr_valid_dir: div2k/DIV2K_train_LR_bicubic/X2/
INFO:ISR.utils.train_helper: lr_valid_dir: div2k/DIV2K_train_LR_bicubic/X2/
hr_valid_dir: div2k/DIV2K_train_HR/
INFO:ISR.utils.train_helper: hr_valid_dir: div2k/DIV2K_train_HR/
loss_weights: {'generator': 0.0, 'feature_extractor': 0.0833, 'discriminator': 0.01}
INFO:ISR.utils.train_helper: loss_weights: {'generator': 0.0, 'feature_extractor': 0.0833, 'discriminator': 0.01}
log_dirs: {'logs': './logs', 'weights': './weights'}
INFO:ISR.utils.train_helper: log_dirs: {'logs': './logs', 'weights': './weights'}
fallback_save_every_n_epochs: 2
INFO:ISR.utils.train_helper: fallback_save_every_n_epochs: 2
dataname: div2k
INFO:ISR.utils.train_helper: dataname: div2k
n_validation: 40
INFO:ISR.utils.train_helper: n_validation: 40
flatness: {'min': 0.0, 'max': 0.15, 'increase': 0.01, 'increase_frequency': 5}
INFO:ISR.utils.train_helper: flatness: {'min': 0.0, 'max': 0.15, 'increase': 0.01, 'increase_frequency': 5}
learning_rate: {'initial_value': 0.0004, 'decay_factor': 0.5, 'decay_frequency': 30}
INFO:ISR.utils.train_helper: learning_rate: {'initial_value': 0.0004, 'decay_factor': 0.5, 'decay_frequency': 30}
adam_optimizer: {'beta1': 0.9, 'beta2': 0.999, 'epsilon': None}
INFO:ISR.utils.train_helper: adam_optimizer: {'beta1': 0.9, 'beta2': 0.999, 'epsilon': None}
losses: {'generator': 'mae', 'discriminator': 'binary_crossentropy', 'feature_extractor': 'mse'}
INFO:ISR.utils.train_helper: losses: {'generator': 'mae', 'discriminator': 'binary_crossentropy', 'feature_extractor': 'mse'}
metrics: {'generator': <function PSNR_Y at 0x7f43af969c60>}
INFO:ISR.utils.train_helper: metrics: {'generator': <function PSNR_Y at 0x7f43af969c60>}
lr_patch_size: 40
INFO:ISR.utils.train_helper: lr_patch_size: 40
steps_per_epoch: 20
INFO:ISR.utils.train_helper: steps_per_epoch: 20
batch_size: 4
INFO:ISR.utils.train_helper: batch_size: 4
starting_epoch: 0
INFO:ISR.utils.train_helper: starting_epoch: 0
generator:
INFO:ISR.utils.train_helper: generator:
name: rrdn
INFO:ISR.utils.train_helper: name: rrdn
parameters: {'C': 4, 'D': 3, 'G': 64, 'G0': 64, 'T': 10, 'x': 2}
INFO:ISR.utils.train_helper: parameters: {'C': 4, 'D': 3, 'G': 64, 'G0': 64, 'T': 10, 'x': 2}
weights_generator: None
INFO:ISR.utils.train_helper: weights_generator: None
discriminator:
INFO:ISR.utils.train_helper: discriminator:
name: srgan-large
INFO:ISR.utils.train_helper: name: srgan-large
weights_discriminator: None
INFO:ISR.utils.train_helper: weights_discriminator: None
feature_extractor:
INFO:ISR.utils.train_helper: feature_extractor:
name: vgg19
INFO:ISR.utils.train_helper: name: vgg19
layers: [5, 9]
INFO:ISR.utils.train_helper: layers: [5, 9]
WARNING:tensorflow:Model failed to serialize as JSON. Ignoring... maximum recursion depth exceeded
5/5 [==============================] - 7s 1s/step
Epoch 0/1
INFO:ISR.train.trainer:Epoch 0/1
Current learning rate: 0.00039999998989515007
INFO:ISR.train.trainer:Current learning rate: 0.00039999998989515007
0%| | 0/20 [00:00<?, ?it/s]1/1 [==============================] - 4s 4s/step
1/1 [==============================] - 0s 186ms/step
0%| | 0/20 [00:07<?, ?it/s]
TypeError Traceback (most recent call last)
in <cell line: 1>()
----> 1 trainer.train(
2 epochs=1,
3 steps_per_epoch=20,
4 batch_size=4,
5 monitored_metrics={'val_generator_PSNR_Y': 'max'}
3 frames
/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py in _call(self, *args, **kwds)
924 # In this case we have created variables on the first call, so we run the
925 # defunned version which is guaranteed to never create variables.
--> 926 return self._no_variable_creation_fn(*args, **kwds) # pylint: disable=not-callable
927 elif self._variable_creation_fn is not None:
928 # Release the lock early so that multiple threads can perform the call
TypeError: 'NoneType' object is not callable
The text was updated successfully, but these errors were encountered: