Modify the softmax values without causing errors

1

I am trying to do something similar to Instance Mapping projection, where I project the instance segmentation results (output from sigmoid function) to a softmax probability map. However, I get error saying that the gradient computation has been modified by an inplace operation. How do I solve this ? any suggestions.

Here is the code

feature_probs = F.softmax(feature_probs,1) [ 1xCxHxW]
masks = masks_logits.sigmoid() [Nx1x28x28]
boxes = [Nx4]
classes = [Nx1] 
for  mask, box, pred_class in zip(masks, boxes, classes):
     w = box[3] - box[1]
     h = box[2] - box[0]
     resize_mask = interpolate(mask, [w,h])
     feature_prob[0][pred_class+1: box[1]:box[3],box[0]:box[2] ] = resize_mask

feature_prob_normalize = F.normalize(feature_prob, p=1 ,dim=0)
loss = calculate_loss(feature_prob_normalize, target)

Error : RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 7, 256, 256]], which is output 0 of SoftmaxBackward. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later.

2

One easy thing you could try is to use feature_probs = F.softmax(feature_probs, 1).clone() instead. Then only the clone of the output tensor is modified, not the output tensor itself.

Best regards

Thomas

3

Thanks !! It works :slight_smile: