训练自己数据集时，train.py报错？向大佬求助

[Seanhom]

Loading weights into state dict... Finished! Traceback (most recent call last): File "/data/iiot-data/caixh/ssd-pytorch/train.py", line 108, in out = net(images) File "/home/amax/anaconda3/envs/iiot/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/home/amax/anaconda3/envs/iiot/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 153, in forward return self.gather(outputs, self.output_device) File "/home/amax/anaconda3/envs/iiot/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 165, in gather return gather(outputs, output_device, dim=self.dim) File "/home/amax/anaconda3/envs/iiot/lib/python3.7/site-packages/torch/nn/parallel/scatter_gather.py", line 68, in gather res = gather_map(outputs) File "/home/amax/anaconda3/envs/iiot/lib/python3.7/site-packages/torch/nn/parallel/scatter_gather.py", line 63, in gather_map return type(out)(map(gather_map, zip(*outputs))) File "/home/amax/anaconda3/envs/iiot/lib/python3.7/site-packages/torch/nn/parallel/scatter_gather.py", line 55, in gather_map return Gather.apply(target_device, dim, *outputs) File "/home/amax/anaconda3/envs/iiot/lib/python3.7/site-packages/torch/nn/parallel/_functions.py", line 54, in forward assert all(map(lambda i: i.is_cuda, inputs)) AssertionError 不知道bug如何解决？

[bubbliiiing]

版本？驱动？

[Seanhom]

我重新指定GPU设备解决啦，具体原因还未深究。

[Momaek-w]

我重新指定GPU设备解决啦，具体原因还未深究。

我也遇到相同的情况请问如何解决的呢

[bubbliiiing]

unknown，我是贫穷仔，没有多卡

[animation123]

我重新指定GPU设备解决啦，具体原因还未深究。

执行楼主的train.py代码时，也碰到了这个问题，在faster r-cnn、yolov3上面运行都没有问题，只有ssd不可以，请问层主是怎么解决的？ Loading weights into state dict... Finished! Epoch 1/50: 0%| | 0/59 [00:00<?, ?it/s<class 'dict'>]Start Train Epoch 1/50: 0%| | 0/59 [00:05<?, ?it/s<class 'dict'>] Traceback (most recent call last): File "/home/wzz/Desktop/Qi/ssd-pytorch-master/train.py", line 205, in fit_one_epoch(net,criterion,epoch,epoch_size,epoch_size_val,gen,gen_val,Freeze_Epoch,Cuda) File "/home/wzz/Desktop/Qi/ssd-pytorch-master/train.py", line 56, in fit_one_epoch out = net(images) File "/home/wzz/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in call result = self.forward(*input, **kwargs) File "/home/wzz/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 153, in forward return self.gather(outputs, self.output_device) File "/home/wzz/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 165, in gather return gather(outputs, output_device, dim=self.dim) File "/home/wzz/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/scatter_gather.py", line 68, in gather res = gather_map(outputs) File "/home/wzz/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/scatter_gather.py", line 63, in gather_map return type(out)(map(gather_map, zip(*outputs))) File "/home/wzz/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/scatter_gather.py", line 55, in gather_map return Gather.apply(target_device, dim, *outputs) File "/home/wzz/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/_functions.py", line 54, in forward assert all(map(lambda i: i.is_cuda, inputs)) AssertionError

[bubbliiiing]

指定GPU设备兄弟