Convolutional-Autoencoder icon indicating copy to clipboard operation
Convolutional-Autoencoder copied to clipboard

NameError: name 'CHECKPOINTS_PATH' is not defined

Open DIPTIMISHRA opened this issue 7 years ago • 3 comments

checkpoints path is defined in the code,still it is showing this error

File "train_autoencoder.py", line 89, in main checkpoint_path=CHECKPOINTS_PATH) NameError: name 'CHECKPOINTS_PATH' is not defined

DIPTIMISHRA avatar Jul 05 '18 11:07 DIPTIMISHRA

No it is not. It is CHECKPOINT_PATH

its5Q avatar Oct 06 '18 06:10 its5Q

Yes, I fixed the spellings but now the problem is: checkpoint_path=CHECKPOINT_PATH) TypeError: fit() got an unexpected keyword argument 'checkpoint_path'

hinash88 avatar Apr 10 '19 10:04 hinash88

Problem fixed! For anyone who is interested, replace the code in "train_autoencoder.py" with model = tflearn.DNN(conv_autencoder, tensorboard_verbose=3,checkpoint_path=CHECKPOINT_PATH) model.fit(X, X, n_epoch=20, shuffle=True, show_metric=True, batch_size=BATCH_SIZE, validation_set=0.1, snapshot_epoch=True, run_id='selfie_conv_autoencoder' )

hinash88 avatar Apr 10 '19 10:04 hinash88