Hi, When I Save Model Using Tf.Keras.Save_Model Or Using Modelcheckpoint Model Is Not Saved As An Artifact. Output Uri Is Set To Google Cloud Bucket. When Reporting With Logger Everything Is Stored Correctly. Do You Maybe Have Any Idea Why This Would Not

Unanswered

I'm sorry for late response. You could probably replicate it by instead of using activation="relu" you used new ReLU layer after Dense. Or if this does not do, extract part of the model in separate Sequential model, for example
Sequential([ Dense(128), BatchNormalization(), ReLU(), ])

  				
Posted 
	2 years ago

					More
				  		
  Report
		
					OutrageousGiraffe8
				
					0
					 × 1

168 Views

0 Answers

2 years ago

one year ago