Gunnvant Singh

Hello, Sebastian, can you please also include, FCN with Vgg16 and Resnet backbones sometime in near future. Currently I could only find pytorch implementations with Vgg16 backbones but not Resnet....

In the fcn32, the output has been cropped. Why are we ignoring the first 19 pixels? Is there any reason for this cropping scheme?

You have used BCE loss in your train file but I don't see you using sigmoid activation. Will that not affect anything as we use sigmoid activation when using BCE...

Thanks for sharing your solution. I was going through your solution and would like to know why you exclude the data before 2010-04-01?

Question Answering has advanced quite a bit, I feel there is need to relook at some ideas and remove/modify them.

Local deployment failing when trying to deploy a model registered in workspace.

1

- **Package Name: azure.ai.ml**: - **Package Version: 1.12.1**: - **Operating System: mac os**: - **Python Version:3.10**: **Describe the bug** Trying to do a local deployemnt based on docs present here...

Feature importance is zero!!!

14

I am using a dataset to compute feature importance using permutation. Have checked results with R implementation, I am getting non zero var importance. What could be the reason? Here...

I checked the mean values of all the keypoints it is not 100, so where are the numbers 100 and 50 coming from?