Eileen000
commented
3 years ago 这个报错呢？
Traceback (most recent call last):
File "/drive/MyDrive/DANet-0.5.0/danet/train.py", line 204, in
Open Eileen000 opened 3 years ago
Eileen000
commented
3 years ago 这个报错呢？
Traceback (most recent call last):
File "/drive/MyDrive/DANet-0.5.0/danet/train.py", line 204, in
JIA-HONG-CHU
commented
3 years ago 在danet.py 更改input 可以使用 transpose 和 view套件
wlj567
commented
3 years ago 在 danet.py 更改输入可以使用转置和视图套件 您好，能具体点吗，谢谢了
JIA-HONG-CHU
commented
3 years ago https://zhuanlan.zhihu.com/p/342675997 。這篇有講蠻淺顯易懂的
wlj567
commented
3 years ago https://zhuanlan.zhihu.com/p/342675997 。這篇有講蠻淺顯易懂的
麻烦了，谢谢
wlj567
commented
3 years ago @Eileen000 您好，请问你能运行完整代码吗，方便加个联系方式吗，谢谢了
Eileen000
commented
3 years ago 能运行 需要改一些地方 还要指定pytorch版本 以及你的显卡配置不能太低 我有在本地电脑和colab上运行过 需要代码可以 但有偿 ------ 原始邮件 ------ @.>; 发送时间:2021年9月29日(星期三) 上午9:16 @.>; @.**@.>; 主题:Re: [junfu1115/DANet] 训练时网络参数报错怎么解决？ (#133)
@Eileen000 您好，请问你能运行完整代码吗，方便加个联系方式吗，谢谢了
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
JIA-HONG-CHU
commented
3 years ago 我有用 encnet danet dranet 用在 mmsegmentation 套件上並且套用swin transformer backbone而不是resnet101，你可以參考 https://github.com/JIA-HONG-CHU/Swin-Transformer-add-EncNet-DaNet-DraNet-for-semantic-segmentation-on-Statelite-Dataset
wlj567
commented
3 years ago 十分感谢你们的回复，作为新人，代码上的问题颇多，我再好好琢磨琢磨吧。打扰了
wlj567
commented
3 years ago 十分感谢你们的回复，作为新人，代码上的问题颇多，我再好好琢磨琢磨吧。打扰了
wlj567
commented
2 years ago 您们好，我想问问训练DANet，怎么用cityscapes数据集进行训练？希望能有空回复一下，先谢谢了。
报错如下： Traceback (most recent call last): File "/drive/MyDrive/DANet-0.5.0/danet/train.py", line 199, in
trainer = Trainer(args)
File "/drive/MyDrive/DANet-0.5.0/danet/train.py", line 67, in init
multi_dilation=args.multi_dilation)
File "/drive/MyDrive/DANet-0.5.0/encoding/models/init.py", line 17, in get_segmentation_model
return modelsname.lower()
File "/drive/MyDrive/DANet-0.5.0/encoding/models/danet.py", line 119, in get_danet
model = DANet(datasets[dataset.lower()].NUM_CLASS, backbone=backbone, root=root, kwargs)
File "/drive/MyDrive/DANet-0.5.0/encoding/models/danet.py", line 40, in init
super(DANet, self).init(nclass, backbone, aux, se_loss, norm_layer=norm_layer, kwargs)
File "/drive/MyDrive/DANet-0.5.0/encoding/models/base.py", line 46, in init
multi_grid=multi_grid,multi_dilation=multi_dilation)
File "/drive/MyDrive/DANet-0.5.0/encoding/dilated/resnet.py", line 283, in resnet101
get_model_file('resnet101', root=root)), strict=False)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 830, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for ResNet:
size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]).
size mismatch for layer1.0.downsample.0.weight: copying a param with shape torch.Size([256, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]).
请问如何解决？