mask2former/modeling/criterion.py [161:263]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - with torch.no_grad(): # sample point_coords point_coords = get_uncertain_point_coords_with_randomness( src_masks, lambda logits: calculate_uncertainty(logits), self.num_points, self.oversample_ratio, self.importance_sample_ratio, ) # get gt labels point_labels = point_sample( target_masks, point_coords, align_corners=False, ).squeeze(1) point_logits = point_sample( src_masks, point_coords, align_corners=False, ).squeeze(1) losses = { "loss_mask": sigmoid_ce_loss_jit(point_logits, point_labels, num_masks), "loss_dice": dice_loss_jit(point_logits, point_labels, num_masks), } del src_masks del target_masks return losses def _get_src_permutation_idx(self, indices): # permute predictions following indices batch_idx = torch.cat([torch.full_like(src, i) for i, (src, _) in enumerate(indices)]) src_idx = torch.cat([src for (src, _) in indices]) return batch_idx, src_idx def _get_tgt_permutation_idx(self, indices): # permute targets following indices batch_idx = torch.cat([torch.full_like(tgt, i) for i, (_, tgt) in enumerate(indices)]) tgt_idx = torch.cat([tgt for (_, tgt) in indices]) return batch_idx, tgt_idx def get_loss(self, loss, outputs, targets, indices, num_masks): loss_map = { 'labels': self.loss_labels, 'masks': self.loss_masks, } assert loss in loss_map, f"do you really want to compute {loss} loss?" return loss_map[loss](outputs, targets, indices, num_masks) def forward(self, outputs, targets): """This performs the loss computation. Parameters: outputs: dict of tensors, see the output specification of the model for the format targets: list of dicts, such that len(targets) == batch_size. The expected keys in each dict depends on the losses applied, see each loss' doc """ outputs_without_aux = {k: v for k, v in outputs.items() if k != "aux_outputs"} # Retrieve the matching between the outputs of the last layer and the targets indices = self.matcher(outputs_without_aux, targets) # Compute the average number of target boxes accross all nodes, for normalization purposes num_masks = sum(len(t["labels"]) for t in targets) num_masks = torch.as_tensor( [num_masks], dtype=torch.float, device=next(iter(outputs.values())).device ) if is_dist_avail_and_initialized(): torch.distributed.all_reduce(num_masks) num_masks = torch.clamp(num_masks / get_world_size(), min=1).item() # Compute all the requested losses losses = {} for loss in self.losses: losses.update(self.get_loss(loss, outputs, targets, indices, num_masks)) # In case of auxiliary losses, we repeat this process with the output of each intermediate layer. if "aux_outputs" in outputs: for i, aux_outputs in enumerate(outputs["aux_outputs"]): indices = self.matcher(aux_outputs, targets) for loss in self.losses: l_dict = self.get_loss(loss, aux_outputs, targets, indices, num_masks) l_dict = {k + f"_{i}": v for k, v in l_dict.items()} losses.update(l_dict) return losses def __repr__(self): head = "Criterion " + self.__class__.__name__ body = [ "matcher: {}".format(self.matcher.__repr__(_repr_indent=8)), "losses: {}".format(self.losses), "weight_dict: {}".format(self.weight_dict), "num_classes: {}".format(self.num_classes), "eos_coef: {}".format(self.eos_coef), "num_points: {}".format(self.num_points), "oversample_ratio: {}".format(self.oversample_ratio), "importance_sample_ratio: {}".format(self.importance_sample_ratio), ] _repr_indent = 4 lines = [head] + [" " * _repr_indent + line for line in body] return "\n".join(lines) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - mask2former_video/modeling/criterion.py [157:259]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - with torch.no_grad(): # sample point_coords point_coords = get_uncertain_point_coords_with_randomness( src_masks, lambda logits: calculate_uncertainty(logits), self.num_points, self.oversample_ratio, self.importance_sample_ratio, ) # get gt labels point_labels = point_sample( target_masks, point_coords, align_corners=False, ).squeeze(1) point_logits = point_sample( src_masks, point_coords, align_corners=False, ).squeeze(1) losses = { "loss_mask": sigmoid_ce_loss_jit(point_logits, point_labels, num_masks), "loss_dice": dice_loss_jit(point_logits, point_labels, num_masks), } del src_masks del target_masks return losses def _get_src_permutation_idx(self, indices): # permute predictions following indices batch_idx = torch.cat([torch.full_like(src, i) for i, (src, _) in enumerate(indices)]) src_idx = torch.cat([src for (src, _) in indices]) return batch_idx, src_idx def _get_tgt_permutation_idx(self, indices): # permute targets following indices batch_idx = torch.cat([torch.full_like(tgt, i) for i, (_, tgt) in enumerate(indices)]) tgt_idx = torch.cat([tgt for (_, tgt) in indices]) return batch_idx, tgt_idx def get_loss(self, loss, outputs, targets, indices, num_masks): loss_map = { 'labels': self.loss_labels, 'masks': self.loss_masks, } assert loss in loss_map, f"do you really want to compute {loss} loss?" return loss_map[loss](outputs, targets, indices, num_masks) def forward(self, outputs, targets): """This performs the loss computation. Parameters: outputs: dict of tensors, see the output specification of the model for the format targets: list of dicts, such that len(targets) == batch_size. The expected keys in each dict depends on the losses applied, see each loss' doc """ outputs_without_aux = {k: v for k, v in outputs.items() if k != "aux_outputs"} # Retrieve the matching between the outputs of the last layer and the targets indices = self.matcher(outputs_without_aux, targets) # Compute the average number of target boxes accross all nodes, for normalization purposes num_masks = sum(len(t["labels"]) for t in targets) num_masks = torch.as_tensor( [num_masks], dtype=torch.float, device=next(iter(outputs.values())).device ) if is_dist_avail_and_initialized(): torch.distributed.all_reduce(num_masks) num_masks = torch.clamp(num_masks / get_world_size(), min=1).item() # Compute all the requested losses losses = {} for loss in self.losses: losses.update(self.get_loss(loss, outputs, targets, indices, num_masks)) # In case of auxiliary losses, we repeat this process with the output of each intermediate layer. if "aux_outputs" in outputs: for i, aux_outputs in enumerate(outputs["aux_outputs"]): indices = self.matcher(aux_outputs, targets) for loss in self.losses: l_dict = self.get_loss(loss, aux_outputs, targets, indices, num_masks) l_dict = {k + f"_{i}": v for k, v in l_dict.items()} losses.update(l_dict) return losses def __repr__(self): head = "Criterion " + self.__class__.__name__ body = [ "matcher: {}".format(self.matcher.__repr__(_repr_indent=8)), "losses: {}".format(self.losses), "weight_dict: {}".format(self.weight_dict), "num_classes: {}".format(self.num_classes), "eos_coef: {}".format(self.eos_coef), "num_points: {}".format(self.num_points), "oversample_ratio: {}".format(self.oversample_ratio), "importance_sample_ratio: {}".format(self.importance_sample_ratio), ] _repr_indent = 4 lines = [head] + [" " * _repr_indent + line for line in body] return "\n".join(lines) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -