Surya Prakash Mishra

icon indicating a website link https://old-school-kid.github.io/my-portfolio/ icon indicating an email [email protected]

icon company IIT (ISM) Dhanbad @RoboISM icon location Mumbai, India icon location IIT ISM Dhanbad Undergrad || Robotics ||Computer Vision || Learning everyday what to learn

Results 16 comments of Surya Prakash Mishra

minval can be greater than maxval in tf.keras.initializers.RandomUniform

@gadagashwini @cheyennee Logically, yes it should throw an error. But i tried it multiple times and it initializes values in range `[minval, maxval]` or `[maxval, minval]` whichever holds. I would...

Raise ValueError if reducing axis dimension is 0

@fchollet Sorry for the extreme delay, had some academic commitments. Added two checks each for GlobalAveragePooling and GlobalMaxPooling for 1D and 3D (with keepdims=True). Please let me know if I...

Raise ValueError if reducing axis dimension is 0

Also keras-team/tf-keras#471 has a similar issue when 1 dimension is empty in case of Conv Transpose layers. I guess a similar solution could work for that too?!

Raise ValueError if reducing axis dimension is 0

@gbaned Would you please remove the `awaiting response from contributor` label.? TIA

Raise ValueError if reducing axis dimension is 0

Hi @fchollet Could you please give it a look? TIA

Raise ValueError if reducing axis dimension is 0

Sorry to bug again @fchollet ! But would you please take a look at the PR? TIA