theclassofai / dlcovid19 Goto Github PK

In the Create and Compile the Model

AttributeError Traceback (most recent call last)
in ()
19 from keras import optimizers
20 model.compile(loss='binary_crossentropy',
---> 21 optimizer=optimizers.RMSprop(lr=1e-4),
22 metrics=['acc'])

AttributeError: module 'keras.optimizers' has no attribute 'RMSprop'

I tired to fix this with optimizer=keras.optimizers.RMSprop(lr=1e-4), and it did finish running the cell but then when I try Fit the model there happens this error:

Epoch 1/30
16/100 [===>..........................] - ETA: 21s - loss: 1.0884 - acc: 0.5800WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least steps_per_epoch * epochs batches (in this case, 3000 batches). You may need to use the repeat() function when building your dataset.
WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least steps_per_epoch * epochs batches (in this case, 10 batches). You may need to use the repeat() function when building your dataset.
100/100 [==============================] - 5s 46ms/step - loss: 1.0884 - acc: 0.5800 - val_loss: 0.6863 - val_acc: 0.6200

If the values of steps_per_epoch < 25 on the implementation without dropout it works and on the one with dropout it work with values of steps_per_epoch < 16.
I also followed the youtube video example.