mac-net's Issues
Error in loading model "ckpt_15"
Hi,
Your code is extremely impressive and clear. However, I have some difficulties running the code. When loading the model "ckpt_15", it seems to miss some layers in the model. Can you give me some suggestions or solutions?
I run the code by
python test
The error message is attached.
Error(s) in loading state_dict for MACNet:
Missing key(s) in state_dict: "net.encoder.5.bn.weight", "net.encoder.5.bn.bias", "net.encoder.5.bn.running_mean", "net.encoder.5.bn.running_var", "net.encoder.5.conv.weight", "net.decoder.5.bn.weight", "net.decoder.5.bn.bias", "net.decoder.5.bn.running_mean", "net.decoder.5.bn.running_var", "net.decoder.5.upsample_conv.conv3d.weight".
size mismatch for net.decoder.0.bn.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.0.bn.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.0.bn.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.0.bn.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.0.deconv.weight: copying a param with shape torch.Size([64, 64, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3, 3]).
size mismatch for net.decoder.1.bn.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.1.bn.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.1.bn.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.1.bn.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for net.decoder.1.upsample_conv.conv3d.weight: copying a param with shape torch.Size([32, 64, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 128, 3, 3, 3]).
size mismatch for net.decoder.2.bn.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.2.bn.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.2.bn.running_mean: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.2.bn.running_var: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.2.deconv.weight: copying a param with shape torch.Size([32, 32, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3, 3]).
size mismatch for net.decoder.3.bn.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.3.bn.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.3.bn.running_mean: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.3.bn.running_var: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for net.decoder.3.upsample_conv.conv3d.weight: copying a param with shape torch.Size([16, 32, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 64, 3, 3, 3]).
size mismatch for net.decoder.4.bn.weight: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for net.decoder.4.bn.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for net.decoder.4.bn.running_mean: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for net.decoder.4.bn.running_var: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for net.decoder.4.deconv.weight: copying a param with shape torch.Size([16, 16, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3, 3]).
ckpt loading failed @trained_model/ckpt_15, exit ...
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.