大佬，代码运行报错

[lulin1995]

❔Question

完全没有运行起来就开始报这个错，不管是yolov5s.yaml还是yolov5_decoupled.yaml。

Additional context

Traceback (most recent call last): File "D:/objectcode/yolov5_research-master/train.py", line 662, in main(opt) File "D:/objectcode/yolov5_research-master/train.py", line 558, in main train(opt.hyp, opt, device, callbacks) File "D:/objectcode/yolov5_research-master/train.py", line 337, in train loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) if (compute_loss_ota is not None )else compute_loss(pred, targets.to(device)) # loss scaled by batch_siz File "D:\objectcode\yolov5research-master\utils\loss.py", line 224, in call pxy, pwh, , pcls = pi[b, a, gj, gi].tensor.split((2, 4, 5), dim=1) # target-subset of predictions AttributeError: 'Tensor' object has no attribute 'tensor'

[positive666]

❔Question

完全没有运行起来就开始报这个错，不管是yolov5s.yaml还是yolov5_decoupled.yaml。

Additional context

Traceback (most recent call last): File "D:/objectcode/yolov5_research-master/train.py", line 662, in main(opt) File "D:/objectcode/yolov5_research-master/train.py", line 558, in main train(opt.hyp, opt, device, callbacks) File "D:/objectcode/yolov5_research-master/train.py", line 337, in train loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) if (compute_loss_ota is not None )else compute_loss(pred, targets.to(device)) # loss scaled by batch_siz File "D:\objectcode\yolov5research-master\utils\loss.py", line 224, in call pxy, pwh, , pcls = pi[b, a, gj, gi].tensor.split((2, 4, 5), dim=1) # target-subset of predictions AttributeError: 'Tensor' object has no attribute 'tensor'

现在应该没问题了吧

[lulin1995]

❔Question

完全没有运行起来就开始报这个错，不管是yolov5s.yaml还是yolov5_decoupled.yaml。

Additional context

Traceback (most recent call last): File "D:/objectcode/yolov5_research-master/train.py", line 662, in main(opt) File "D:/objectcode/yolov5_research-master/train.py", line 558, in main train(opt.hyp, opt, device, callbacks) File "D:/objectcode/yolov5_research-master/train.py", line 337, in train loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) if (compute_loss_ota is not None )else compute_loss(pred, targets.to(device)) # loss scaled by batch_siz File "D:\objectcode\yolov5research-master\utils\loss.py", line 224, in call pxy, pwh, , pcls = pi[b, a, gj, gi].tensor.split((2, 4, 5), dim=1) # target-subset of predictions AttributeError: 'Tensor' object has no attribute 'tensor'

现在应该没问题了吧 大佬，虽然可以运行起来了，但是训练时的P、R、mAP值都出现不上升的情况，不为0，但是mAP只有0.0175左右这样不上升，在原版的YOLOv5里面mAP是可以上升到0.9左右的，自己的数据集

[lulin1995]

❔Question

完全没有运行起来就开始报这个错，不管是yolov5s.yaml还是yolov5_decoupled.yaml。

Additional context

Traceback (most recent call last): File "D:/objectcode/yolov5_research-master/train.py", line 662, in main(opt) File "D:/objectcode/yolov5_research-master/train.py", line 558, in main train(opt.hyp, opt, device, callbacks) File "D:/objectcode/yolov5_research-master/train.py", line 337, in train loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) if (compute_loss_ota is not None )else compute_loss(pred, targets.to(device)) # loss scaled by batch_siz File "D:\objectcode\yolov5research-master\utils\loss.py", line 224, in call pxy, pwh, , pcls = pi[b, a, gj, gi].tensor.split((2, 4, 5), dim=1) # target-subset of predictions AttributeError: 'Tensor' object has no attribute 'tensor'

现在应该没问题了吧 大佬，虽然可以运行起来了，但是训练时的P、R、mAP值都出现不上升的情况，不为0，但是mAP只有0.0175左右这样不上升，在原版的YOLOv5里面mAP是可以上升到0.9左右的，自己的数据集，box和obj损失值还会为nan

[positive666]

❔Question

完全没有运行起来就开始报这个错，不管是yolov5s.yaml还是yolov5_decoupled.yaml。

Additional context

Traceback (most recent call last): File "D:/objectcode/yolov5_research-master/train.py", line 662, in main(opt) File "D:/objectcode/yolov5_research-master/train.py", line 558, in main train(opt.hyp, opt, device, callbacks) File "D:/objectcode/yolov5_research-master/train.py", line 337, in train loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) if (compute_loss_ota is not None )else compute_loss(pred, targets.to(device)) # loss scaled by batch_siz File "D:\objectcode\yolov5research-master\utils\loss.py", line 224, in call pxy, pwh, , pcls = pi[b, a, gj, gi].tensor.split((2, 4, 5), dim=1) # target-subset of predictions AttributeError: 'Tensor' object has no attribute 'tensor'

现在应该没问题了吧 大佬，虽然可以运行起来了，但是训练时的P、R、mAP值都出现不上升的情况，不为0，但是mAP只有0.0175左右这样不上升，在原版的YOLOv5里面mAP是可以上升到0.9左右的，自己的数据集，box和obj损失值还会为nan

我下午测试一下 最近在做一些low-level的任务 没有管检测这块

[lulin1995]

❔Question

完全没有运行起来就开始报这个错，不管是yolov5s.yaml还是yolov5_decoupled.yaml。

Additional context

Traceback (most recent call last): File "D:/objectcode/yolov5_research-master/train.py", line 662, in main(opt) File "D:/objectcode/yolov5_research-master/train.py", line 558, in main train(opt.hyp, opt, device, callbacks) File "D:/objectcode/yolov5_research-master/train.py", line 337, in train loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) if (compute_loss_ota is not None )else compute_loss(pred, targets.to(device)) # loss scaled by batch_siz File "D:\objectcode\yolov5research-master\utils\loss.py", line 224, in call pxy, pwh, , pcls = pi[b, a, gj, gi].tensor.split((2, 4, 5), dim=1) # target-subset of predictions AttributeError: 'Tensor' object has no attribute 'tensor'

现在应该没问题了吧 大佬，虽然可以运行起来了，但是训练时的P、R、mAP值都出现不上升的情况，不为0，但是mAP只有0.0175左右这样不上升，在原版的YOLOv5里面mAP是可以上升到0.9左右的，自己的数据集，box和obj损失值还会为nan

我下午测试一下 最近在做一些low-level的任务 没有管检测这块

好的，谢谢大佬

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.