Ramanathan Arunachalam

Do the models(especially variants of Faster RCNN) support batching during inference currently?

Hi, I went through the paper and had a tough time understanding the jist of it. Is it: 1. Cut-Mix for segmentation images improving the accuracy metrics or 2. The...

Does Solov2 support Mixed Precision Training?

Clarification about CutMix

3

I saw examples where head of a dog is cut and overlayed with head of a cat. How do identify these specific portions of the body - or how do...

Hi, how do you resume the training with the last saved checkpoint after the training was stopped?

Undo after File closing

1

From the ReadMe, I can see that we can undo the changes even after closing the file. Am I right in my interpretation or we can undo the changes only...

Prelu replacement - "Weights for scale layer" doesn't exists

1

Hi, Was the model trained on relu+scale combination or it was trained on prelu and you just replace the prelu with equivalent operations only in the prototxt file. I have...

BIT1-XNOR accuracy

2

How far is the accuracy when BIT1-XNOR is used for training and inference

Hi @AlexeyAB, doesn't the forward call of convolution support Group Convolution? If I add manual support on my local clone of the repo, does it affect the Calibration calculation?

Pretrained weights

2

How to use your trained .caffemodel as a pretrained weights (transfer learning) in the model which we train. Is it possible in caffe ?