The 365 Data Science team is proud to invite you to our own community forum. A very well built system to support your queries, questions and give the chance to show your knowledge and help others in their path of becoming Data Science specialists.
Ask
Anybody can ask a question
Answer
Anybody can answer
Vote
The best answers are voted up and moderated by our team

value error in Deep learning wirh tensorflow

value error in Deep learning wirh tensorflow

0
Votes
1
Answer

This line is code giving me value error _,batch_loss=sess.run([optimize.mean_loss],feed_dict={inputs: input_batch, targets: target_batch})

1 Answer

365 Team
0
Votes

Hi Amit,
Please try using this code instead: 
STEPS = num_validation_samples/BATCH_SIZE
model.fit(train_data, epochs=NUM_EPOCHS, validation_data=(validation_inputs, validation_targets), validation_steps=STEPS, verbose =2)
There has been an update to TF which caused this issue. Sorry for the inconvenience!
Best regards,
Iliya

THANK YOU sir, but after writing these lines i am getting a name error as: num_validation_samples is not defined. This line of code i mentioned above is from MNSIT lecture of deep learning.

6 months

Please sir can you help.

6 months

Hi Amit, are you sure you have executed all cells before that? Could you try selecting ‘Kernel -> Restart and Run All’ ?

6 months