Comments (10)
in_ch= 15#输入通道数 out_ch = 13#输出通道数 作者您好,我在运行train.py的时候出现了这个问题,然后我发现是在config.py中的通道数是不匹配的,不知道这个是怎么解决的,直接修改通道数吗还是有别的方式
嗯,是这样的,可以灵活改变config.py中的参数以应对您的情况。在印象中论文原文中输入通道应该是15。
from dsen2_cr_pytorch.
是的,输入通道是15没错,当我改变输出通道为15时还是报一样的错误
cloud_img.shape torch.Size([1, 15, 256, 256])
ground_truth.shape torch.Size([1, 15, 256, 256])
csm_img.shape torch.Size([1, 1, 256, 256])
开始训练...
Traceback (most recent call last):
File "train.py", line 134, in
train(myconfig)
File "train.py", line 102, in train
img_fake = net(img_cld)
File "/root/miniconda3/envs/dsen/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/dsen2_cr/models/DSen2_CR.py", line 46, in forward
return x[:,2:,:,:]+self.net(x)
RuntimeError: The size of tensor a (13) must match the size of tensor b (15) at non-singleton dimension 1
from dsen2_cr_pytorch.
是的,输入通道是15没错,当我改变输出通道为15时还是报一样的错误 cloud_img.shape torch.Size([1, 15, 256, 256]) ground_truth.shape torch.Size([1, 15, 256, 256]) csm_img.shape torch.Size([1, 1, 256, 256]) 开始训练... Traceback (most recent call last): File "train.py", line 134, in train(myconfig) File "train.py", line 102, in train img_fake = net(img_cld) File "/root/miniconda3/envs/dsen/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/autodl-tmp/dsen2_cr/models/DSen2_CR.py", line 46, in forward return x[:,2:,:,:]+self.net(x) RuntimeError: The size of tensor a (13) must match the size of tensor b (15) at non-singleton dimension 1
如果输入通道是15,那么
- x.shape = [batch_size, 15, height, width]
- x[:,2:,:,:].shape = [batch_size, 13, height, width]
请你检查一下self.net(x)
的输出是否是13通道?从报错信息上来看,net输出的是15通道。所以不能进行element-wise的加法。
from dsen2_cr_pytorch.
x.shape torch.Size([1, 15, 256, 256])
self.net(x) torch.Size([1, 15, 256, 256])
x[:,2:,:,:] torch.Size([1, 13, 256, 256])
是的我输出来self.net(x)的输出是13通道,这个要怎么改
from dsen2_cr_pytorch.
x.shape torch.Size([1, 15, 256, 256]) self.net(x) torch.Size([1, 15, 256, 256]) x[:,2:,:,:] torch.Size([1, 13, 256, 256]) 是的我输出来self.net(x)的输出是13通道,这个要怎么改
在config.py
的第34行,out_ch = 13#输出通道数
,这个out_ch应该是13的,你看看是不是误修改成15了。
from dsen2_cr_pytorch.
是的 我只修改这一个地方,改成13也是报一样的错误
from dsen2_cr_pytorch.
这就又回到了最初的问题
Traceback (most recent call last):
File "train.py", line 131, in
train(myconfig)
File "train.py", line 100, in train
loss= CARL_Loss(img_truth,img_csm,img_fake,img_cld)
File "/root/autodl-tmp/dsen2_cr/utils/img_operations.py", line 65, in carl_error
cscmae = t.mean(clearmask * t.abs(predicted - input_cloudy) + csm * t.abs(
RuntimeError: The size of tensor a (13) must match the size of tensor b (15) at non-singleton dimension 1
from dsen2_cr_pytorch.
这就又回到了最初的问题 Traceback (most recent call last): File "train.py", line 131, in train(myconfig) File "train.py", line 100, in train loss= CARL_Loss(img_truth,img_csm,img_fake,img_cld) File "/root/autodl-tmp/dsen2_cr/utils/img_operations.py", line 65, in carl_error cscmae = t.mean(clearmask * t.abs(predicted - input_cloudy) + csm * t.abs( RuntimeError: The size of tensor a (13) must match the size of tensor b (15) at non-singleton dimension 1
这个问题有人已经提出来了,很奇怪,在我之前用的时候并没有出问题,有可能是我上传了之前的版本到github
详情请看这里
from dsen2_cr_pytorch.
loss= CARL_Loss(img_truth,img_csm,img_fake,img_cld)我在这个函数之前将img_cld拆分了一下,是对的吗
from dsen2_cr_pytorch.
loss= CARL_Loss(img_truth,img_csm,img_fake,img_cld)我在这个函数之前将img_cld拆分了一下,是对的吗
嗯,是对的。这几天比较忙回复不及时,不好意思哈。我目前没有条件运行代码,有任何问题欢迎在下面留言
from dsen2_cr_pytorch.
Related Issues (6)
- 询问数据集 HOT 2
- 数据集 HOT 8
- Batch size HOT 4
- predict.py报错 HOT 2
- 损失函数 HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dsen2_cr_pytorch.