chauncey-eng
commented
6 months ago +1我也有这问题，改成torch.max，torch.min之后， File "E:\PycharmProjects\yolov8-pytorch-master\nets\yolo_training.py", line 38, in select_candidates_in_gts return bboxdeltas.amin(3).gt(eps) AttributeError: 'Tensor' object has no attribute 'amin' 又出现了这个问题
Traceback (most recent call last): File "train.py", line 547, in
fit_one_epoch(model_train, model, ema, yolo_loss, loss_history, eval_callback, optimizer, epoch, epoch_step, epoch_step_val, gen, gen_val, UnFreeze_Epoch, Cuda, fp16, scaler, save_period, save_dir, local_rank)
File "/data/caixj/yolov8-pytorch-master/utils/utils_fit.py", line 35, in fit_one_epoch
loss_value = yolo_loss(outputs, bboxes)
File "/data/caixj/yolov8-pytorch-master/nets/yolo_training.py", line 463, in call
anchor_points stride_tensor, gt_labels, gt_bboxes, mask_gt
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(input, *kwargs)
File "/opt/conda/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 15, in decorate_context
return func(args, *kwargs)
File "/data/caixj/yolov8-pytorch-master/nets/yolo_training.py", line 123, in forward
mask_pos, align_metric, overlaps = self.get_pos_mask(pd_scores, pd_bboxes, gt_labels, gt_bboxes, anc_points, mask_gt)
File "/data/caixj/yolov8-pytorch-master/nets/yolo_training.py", line 160, in get_pos_mask
align_metric, overlaps = self.get_box_metrics(pd_scores, pd_bboxes, gt_labels, gt_bboxes)
File "/data/caixj/yolov8-pytorch-master/nets/yolo_training.py", line 208, in get_box_metrics
overlaps = bbox_iou(gt_bboxes.unsqueeze(2), pd_bboxes.unsqueeze(1), xywh=False, CIoU=True).squeeze(3).clamp(0)
File "/data/caixj/yolov8-pytorch-master/nets/yolo_training.py", line 282, in bbox_iou
inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp(0) \
AttributeError: 'Tensor' object has no attribute 'minimum'
这是什么问题，训练的时候遇到的。
按理来说训练之前应该是numpy，b导训练时有遇到这个问题吗？