训练yolo时报错RuntimeError: result type Float can‘t be cast to the desired output type _

运行YOLOv5 6.1和yolor的时候，训练都没能正常运行，均出现了如下错误：

AutoAnchor: 5.00 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset
Image sizes 640 train, 640 val
Using 0 dataloader workers
Logging results to runs\train\exp14
Starting training for 300 epochs...Epoch   gpu_mem       box       obj       cls    labels  img_size
0%| | 0/8 [00:03<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 634, in
main(opt)
File "train.py", line 525, in main
train(opt.hyp, opt, device, callbacks)
File "train.py", line 320, in train
loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size
File "E:Deeplearn\yolov5\utils\loss.py", line 120, in call
tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets
File "E:Deeplearn\yolov5\utils\loss.py", line 217, in build_targets
indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices
RuntimeError: result type Float can't be cast to the desired output type __int64

在网络上搜索错误，没有找到解决方案，只能尝试自己分析错误原因。

由于学校的电脑可以正常运行，家中电脑就出现了这个问题，两台电脑的环境差别只有pytorch版本不同，故合理怀疑是Pytorch 1.12版本的问题，将pytorch降级为1.11版本，再次运行后问题解决

PS:pytorch降级办法：

用anaconda管理环境的话，直接输入官方上提供的安装1.11的指令，就可以，由于1.12支持11.6版本的cuda，所以很多人因为cuda版本是11.6所以安装的pytorch1.12（比如我），所以降级的时候一定要注意自己的cuda版本与1.11要求的匹配

# CUDA 10.2
conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=10.2 -c pytorch# CUDA 11.3
conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3 -c pytorch# CPU Only
conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cpuonly -c pytorch

训练yolo时报错RuntimeError: result type Float can‘t be cast to the desired output type __int64个人解决方案相关推荐

YOLOV5报错：RuntimeError: result type Float can‘t be cast to the desired output type long int
YOLOV5训练时报错: Traceback (most recent call last): File "train.py", line 626, in <module ...
YOLOv5训练报错：result type Float can‘t be cast to the desired output type __int64
记录一个报错: 因为把Pytorch版本从1.8.0更新到1.13.1,YOLOv5-6.1版本的训练代码报错: RuntimeError: result type Float can't be ca ...
解决Yolov5的RuntimeError: result type Float can‘t be cast to the desired output type long int 问题
在yolov5中,直接下载github上的代码可能出现无法运行的情况,会报错 RuntimeError: result type Float can't be cast to the desired ...
RuntimeError: result type Float can‘t be cast to the desired output type __int64
yolo问题:RuntimeError: result type Float can't be cast to the desired output type __int64 解决办法: loss.p ...
解决错误：RuntimeError: result type Float can‘t be cast to the desired output type __int64
在运行yolov5 train.py时出现了这个错误解决方式: 将loss.py中gain = torch.ones(7, device=targets.device)改为gain = torch. ...
【Error Logs】YoloV5出现RuntimeError: result type Float can‘t be cast to the desired output
问题描述在训练 yolov5做简单的识别的时候出现,错误:RuntimeError: result type Float can't be cast to the desired output ty ...
Faster rcnn 训练coco2017数据报错 RuntimeError: CUDA error: device-side assert triggered
Faster rcnn 训练coco2017数据报错 RuntimeError: CUDA error: device-side assert triggered 使用faster rcnn训练自己的 ...
项目中引用NG-ZORRO，在使用nz-form时报错Can't bind to 'formGroup' since it isn't a known property of 'form'的解决方案
项目中引用NG-ZORRO,在使用nz-form时报错 Can't bind to 'formGroup' since it isn't a known property of 'form' comp ...
(已解决)多卡训练时报错RuntimeError: grad can be implicitly created only for scalar outputs
背景博主第一次使用多卡训练,在程序中添加了如下代码 # 包装为并行风格模型 os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID& ...

训练yolo时报错RuntimeError: result type Float can‘t be cast to the desired output type __int64个人解决方案

训练yolo时报错RuntimeError: result type Float can‘t be cast to the desired output type __int64个人解决方案相关推荐

最新文章

热门文章