I am trying to compute the loss between ground truth bounding box and bounding box which is generated from predicted segmentation mask. My function to compute the bounding box loss is as following:
import torch.nn as nn import torchvision.ops as ops def get_bounding_boxes_from_masks(segmentation_masks, device): bbox_tensor_list =  for i in range(segmentation_masks.shape): if torch.sum(segmentation_masks[i]) == 0: bounding_boxes = torch.tensor([[0.0, 0.0, 1.0, 1.0]], dtype=torch.float32).to(device) else: bounding_boxes = ops.masks_to_boxes(segmentation_masks[i]) bbox_tensor_list.append(bounding_boxes) concatenated_bbox = torch.cat(bbox_tensor_list, dim = 0) return concatenated_bbox
Once I have the bounding boxes I compute the loss between ground truth bounding boxes (bboxes) and bounding boxes from segmentation mask (mask_bboxes). My segmentation mask contains single object only.
mse_loss = nn.MSELoss() for step, (image, gt, boxes) in enumerate(tqdm(train_dataloader)): bboxes = Variable(bboxes, requires_grad=False) # mask_predictions are coming from segmentation model mask_predictions = model(image, boxes) mask_predictions = torch.sigmoid(mask_predictions) binary_masks = mask_predictions > 0.5 mask_bboxes = get_bounding_boxes_from_masks(binary_masks, device=device) mask_bboxes = Variable(mask_bboxes, requires_grad=True) loss = mse_loss(mask_bboxes.to(device), bboxes.to(device)) print(loss.item(), loss.grad()) optimizer.zero_grad() loss.backward() optimizer.step() epoch_loss += loss.item()
I am getting loss.grad as “None” and loss is constant after each epoch (not even decimal change). I am not able to understand what’s happening here. Can anyone help?
Let me know if any other information is required.