Why are my tensorflow gradients None when using tf.python.ops.gradients?
I am struggling with tensorflow gradients. I am using a custom second order optimizer where I need to compute hessians. The library I have chosen uses tf.python.ops.gradients instead of the standard tape.gradients(…). Running the below script raises a value error (gradients are None):
INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘conv2d_input’ with dtype float and shape
I was trying to build a gradient heatmap model using the following code:
INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘conv2d_input’ with dtype float and shape
I was trying to build a gradient heatmap model using the following code:
Problem with displaying recommendation images in a TensorFlow-based recommendation system
I am developing a recommendation system for H&M dataset, my goal is to recommend articles to users based on the article they have chosen and display images corresponding to the recommended items.