您好，我这边在用tusimple数据集跑Bezierlannet的训练时，命令是 python main_landet.py --train --config=configs/lane_detection/bezierlanenet/resnet18_tusimple_aug1b.py，出现了报错，请问您是否能提供解决方案或者建议呢？谢谢您！ #180
Comments
@Diamond88 你这边有修改代码吗，还是直接跑的？ |
|
没有修改呢，就是下载的原代码和原数据直接跑的
…---原始邮件---
发件人: "Zhengyang ***@***.***>
发送时间: 2024年12月19日(周四) 晚上6:14
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [voldemortX/pytorch-auto-drive] 您好，我这边在用tusimple数据集跑Bezierlannet的训练时，命令是 python main_landet.py --train --config=configs/lane_detection/bezierlanenet/resnet18_tusimple_aug1b.py，出现了报错，请问您是否能提供解决方案或者建议呢？谢谢您！ (Issue #180)
Traceback (most recent call last):
File "main_landet.py", line 76, in
runner.run()
File "/home/ubuntu/code/pytorch-auto-drive/utils/runners/lane_det_trainer.py", line 55, in run
self.model)
File "/home/ubuntu/anaconda3/envs/pad/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/ubuntu/code/pytorch-auto-drive/utils/losses/hungarian_bezier_loss.py", line 150, in forward
loss_seg = self.binary_seg_loss(inputs=outputs['segmentations'], targets=target_segmentations)
File "/home/ubuntu/code/pytorch-auto-drive/utils/losses/hungarian_bezier_loss.py", line 204, in binary_seg_loss
reduction='none') / self.pos_weight_seg
File "/home/ubuntu/anaconda3/envs/pad/lib/python3.6/site-packages/torch/nn/functional.py", line 2538, in binary_cross_entropy_with_logits
raise ValueError("Target size ({}) must be the same as input size ({})".format(target.size(), input.size()))
ValueError: Target size (torch.Size([20, 360, 640, 3])) must be the same as input size (torch.Size([20, 640, 3]))
@Diamond88 你这边有修改代码吗，还是直接跑的？
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
|
@Diamond88 奇怪，你可以尝试看一下模型输入时刻图片是否正常么，有h和w |
|
好的好的，我看看输入是否有问题，谢谢您～
…---原始邮件---
发件人: "Zhengyang ***@***.***>
发送时间: 2024年12月19日(周四) 晚上7:27
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [voldemortX/pytorch-auto-drive] 您好，我这边在用tusimple数据集跑Bezierlannet的训练时，命令是 python main_landet.py --train --config=configs/lane_detection/bezierlanenet/resnet18_tusimple_aug1b.py，出现了报错，请问您是否能提供解决方案或者建议呢？谢谢您！ (Issue #180)
@Diamond88 奇怪，你可以尝试看一下模型输入时刻图片是否正常么，有h和w
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
|
@Diamond88 如果发现代码有bug欢迎pr修复 |
Traceback (most recent call last):
File "main_landet.py", line 76, in
runner.run()
File "/home/ubuntu/code/pytorch-auto-drive/utils/runners/lane_det_trainer.py", line 55, in run
self.model)
File "/home/ubuntu/anaconda3/envs/pad/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/ubuntu/code/pytorch-auto-drive/utils/losses/hungarian_bezier_loss.py", line 150, in forward
loss_seg = self.binary_seg_loss(inputs=outputs['segmentations'], targets=target_segmentations)
File "/home/ubuntu/code/pytorch-auto-drive/utils/losses/hungarian_bezier_loss.py", line 204, in binary_seg_loss
reduction='none') / self.pos_weight_seg
File "/home/ubuntu/anaconda3/envs/pad/lib/python3.6/site-packages/torch/nn/functional.py", line 2538, in binary_cross_entropy_with_logits
raise ValueError("Target size ({}) must be the same as input size ({})".format(target.size(), input.size()))
ValueError: Target size (torch.Size([20, 360, 640, 3])) must be the same as input size (torch.Size([20, 640, 3]))
The text was updated successfully, but these errors were encountered: