When I was training, I encountered the following problem（ubuntu16.04+pytorch0.4.1）

[Ailce8862]

[epoch 1: 0/499] train loss: 4.879579 lr: 0.00100 [epoch 1: 20/499] train loss: 1.237031 lr: 0.00100 [epoch 1: 40/499] train loss: 0.955243 lr: 0.00100 [epoch 1: 60/499] train loss: 0.735887 lr: 0.00100 [epoch 1: 80/499] train loss: 0.685161 lr: 0.00100 [epoch 1: 100/499] train loss: 0.482436 lr: 0.00100 [epoch 1: 120/499] train loss: 0.854511 lr: 0.00100 [epoch 1: 140/499] train loss: 0.695081 lr: 0.00100 [epoch 1: 160/499] train loss: 0.860770 lr: 0.00100 [epoch 1: 180/499] train loss: 0.354899 lr: 0.00100 [epoch 1: 200/499] train loss: 0.505713 lr: 0.00100 [epoch 1: 220/499] train loss: 0.378871 lr: 0.00100 [epoch 1: 240/499] train loss: 0.411512 lr: 0.00100 [epoch 1: 260/499] train loss: 0.565703 lr: 0.00100 [epoch 1: 280/499] train loss: 0.386525 lr: 0.00100 [epoch 1: 300/499] train loss: 0.400440 lr: 0.00100 [epoch 1: 320/499] train loss: 0.352148 lr: 0.00100 [epoch 1: 340/499] train loss: 0.571778 lr: 0.00100 train_partseg.py:155: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead. points, target = Variable(points, volatile=True), Variable(target, volatile=True) Traceback (most recent call last): File "train_partseg.py", line 214, in main() File "train_partseg.py", line 95, in main train(train_dataloader, test_dataloader, model, criterion, optimizer, lr_scheduler, bnm_scheduler, args, num_batch) File "train_partseg.py", line 138, in train validate(test_dataloader, model, criterion, args, batch_count) File "train_partseg.py", line 172, in validate cat = seg_label_to_cat[target[b, 0]] KeyError: tensor(5)

[Anniessq]

Hello,I'v met the same error,could you tell me how you fixed it?

I tried to change the linecat = seg_label_to_cat[target[b, 0]] in the following ways. 1.Firstly, I change it to cat = seg_label_to_cat[target[b, 0].numpy()] or cat = seg_label_to_cat[target[b, 0].numpy()[0]], I met :TypeError:unhashable type:'numpy.ndarray'. 2.And also, I change it to cat = seg_label_to_cat[target[b,0].item()] or cat = seg_label_to_cat[target.numpy()[b][0]]. In both situation， the code can run ,but the IOU of several category remains zero. I very want to know your solution,waiting for your suggetion and answer.Thank you!

[Ailce8862]

I used pytorch 0.3

	梁攀

邮箱：liangxiaopan8862@126.com |

签名由 网易邮箱大师 定制

On 12/30/2019 09:57, Anniessq wrote:

Hello,I'v met the same error,could you tell me how you fixed it?

I tried to change the line cat = seg_label_to_cat[target[b, 0]] in the following ways. 1.Firstly, I change it to cat = seg_label_to_cat[target[b, 0].numpy()] or cat = seg_label_to_cat[target[b, 0].numpy()[0]] , I met :TypeError:unhashable type:'numpy.ndarray'. 2.And also, I change it to cat = seg_label_to_cat[target[b,0].item()] or cat = seg_label_to_cat[target.numpy()[b][0]]. In both situation， the code can run ,but the IOU of several category remains zero. I very want to know your solution,waiting for your suggetion and answer.Thank you!

— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub, or unsubscribe.

[Anniessq]

Thank you, but cuda 10 can't support pytorch 0.3 and Ubuntu 18.0 can only support cuda10

[Ailce8862]

You can try anaconda.I also use cuda10

	梁攀

邮箱：liangxiaopan8862@126.com |

签名由 网易邮箱大师 定制

On 12/30/2019 16:43, Anniessq wrote:

Thank you, but cuda 10 can't support pytorch 0.3 and Ubuntu 18.0 can only support cuda10

— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub, or unsubscribe.

[pixar0407]

It's been long time, but i figure it out.

i changed (at 167)

cat = seg_label_to_cat[target[b, 0]] to cat = seg_label_to_cat[target[b, 0].item()]

And i changed (at 174)

cat = seg_label_to_cat[segl[0]] to cat = seg_label_to_cat[segl[0].item()]

this works for me.