LSTM training error

[MihirBha]

No description provided.

[srivatsan88]

I see you are using fit method rather fit_generator. One is you can go back to 2.2 TF version and use fit_generator. I will try to change the code against latest version and update

[srivatsan88]

Hi, I was able to make the same code work on TF 2.5 as well. instead of fit_generated which is deprecated fit works as well. I am hardening the code and will upload in upcoming week

This is what I used in TF 2.5

early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss',
patience=2,
mode='min')

model.compile(loss=tf.losses.MeanSquaredError(),
optimizer=tf.optimizers.Adam(),
metrics=[tf.metrics.MeanAbsoluteError()])

history = model.fit(train_generator, epochs=20,
validation_data=val_generator,
shuffle=False,
callbacks=[early_stopping])

[MihirBha]

Hi sir , I am Mihir Bhawsar. I work on LSTM model to forecast next 15 days value . I am using your code but I can't predict next 15 days value. So please help me to my project☺️.

…

On Thu, 10 Jun, 2021, 7:02 pm Srivatsan Srinivasan, < ***@***.***> wrote: Hi, I was able to make the same code work on TF 2.5 as well. instead of fit_generated which is deprecated fit works as well. I am hardening the code and will upload in upcoming week This is what I used in TF 2.5 early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=2, mode='min') model.compile(loss=tf.losses.MeanSquaredError(), optimizer=tf.optimizers.Adam(), metrics=[tf.metrics.MeanAbsoluteError()]) history = model.fit(train_generator, epochs=20, validation_data=val_generator, shuffle=False, callbacks=[early_stopping]) — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AT4ID7D7ULAK3XZKC3EUUYDTSC5GFANCNFSM43ZLVC7A> .