yolov5_obb
yolov5_obb copied to clipboard
hukaixuan19970627
RuntimeError: result type Float can't be cast to the desired output type __int64
Epoch gpu_mem box obj cls theta labels img_size
0%| | 0/1 [00:07<?, ?it/s]
Traceback (most recent call last):
File "D:/Tian/yolov5_obb-master/train.py", line 633, in
https://github.com/ultralytics/yolov5/issues/8314 这里有类似解决办法，当前版本有点旧了，需要修改loss.py，作者可以更新一下代码 @hukaixuan19970627
ultralytics/yolov5#8314 这里有类似解决办法，当前版本有点旧了，需要修改loss.py，作者可以更新一下代码 @hukaixuan19970627
Logging results to runs\train\exp35 Starting training for 300 epochs...
Epoch gpu_mem box obj cls theta labels img_size
0/299 8.5G 0.1637 0.03505 0 10.14 33 1024: 100%|██████████| 39/39 [00:33<00:00, 1.15it/s]
Class Images Labels P R [email protected] [email protected]:.95: 0%| | 0/20 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 640, in
ultralytics/yolov5#8314 这里有类似解决办法，当前版本有点旧了，需要修改loss.py，作者可以更新一下代码 @hukaixuan19970627
Logging results to runs\train\exp35 Starting training for 300 epochs...
Epoch gpu_mem box obj cls theta labels img_size 0/299 8.5G 0.1637 0.03505 0 10.14 33 1024: 100%|██████████| 39/39 [00:33<00:00, 1.15it/s] Class Images Labels P R [email protected] [email protected]:.95: 0%| | 0/20 [00:00<?, ?it/s]Traceback (most recent call last): File "train.py", line 640, in main(opt) File "train.py", line 537, in main train(opt.hyp, opt, device, callbacks) File "train.py", line 376, in train compute_loss=compute_loss) File "D:\ProgramData\envs\pytorch\lib\site-packages\torch\autograd\grad_mode.py", line 26, in decorate_context return func(*args, *kwargs) File "D:\Tian\yolov5_obb-master\val.py", line 206, in run out = non_max_suppression_obb(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls) # list(n, [xylsθ, conf, cls]) θ ∈ [-pi/2, pi/2) File "D:\Tian\yolov5_obb-master\utils\general.py", line 857, in non_max_suppression_obb _, i = obb_nms(rboxes, scores, iou_thres) File "D:\Tian\yolov5_obb-master\utils\nms_rotated\nms_rotated_wrapper.py", line 41, in obb_nms inds = nms_rotated_ext.nms_rotated(dets_th, scores, iou_thr) RuntimeError: Not compiled with GPU support 我现在可以运行了，但是用GPU的时候，总是在验证的时候中断，之前会训练一些批次，然后中断。现在第一轮就不行了。用CPU的话就没有问题。
把这个步骤生成的.so文件删除，然后再编译一次。
Epoch gpu_mem box obj cls theta labels img_size0%| | 0/1 [00:07<?, ?it/s] Traceback (most recent call last): File "D:/Tian/yolov5_obb-master/train.py", line 633, in main(opt) File "D:/Tian/yolov5_obb-master/train.py", line 530, in main train(opt.hyp, opt, device, callbacks) File "D:/Tian/yolov5_obb-master/train.py", line 326, in train loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size File "D:\Tian\yolov5_obb-master\utils\loss.py", line 136, in call tcls, tbox, indices, anchors, tgaussian_theta = self.build_targets(p, targets) # targets File "D:\Tian\yolov5_obb-master\utils\loss.py", line 267, in build_targets indices.append((b, a, gj.clamp_(0, feature_wh[1] - 1), gi.clamp_(0, feature_wh[0] - 1))) # image, anchor, grid indices RuntimeError: result type Float can't be cast to the desired output type __int64 不太清楚这个问题应该怎么解决。
我遇到一样的问题了。这个问题是怎么解决的呢？
