small-object-detection's People
small-object-detection's Issues
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces).
F:\softwares\Anaconda3\envs\py36\lib\site-packages\torch\nn_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead.
warnings.warn(warning.format(ret))
Traceback (most recent call last):
File "train.py", line 58, in
main(config)
File "train.py", line 39, in main
trainer.train()
File "D:\GitHub\my new code\base\base_trainer.py", line 65, in train
result = self.train_epoch(epoch)
File "D:\GitHub\my new code\trainer\trainer.py", line 54, in train_epoch
output_boxes, output_scores = self.model(data)
File "F:\softwares\Anaconda3\envs\py36\lib\site-packages\torch\nn\modules\module.py", line 532, in __ call
result = self.forward(*input, **kwargs)
File "D:\GitHub\my new code\model\model.py", line 450, in forward
spatial_corr4 = self.spatialcooc4(conv4_out)
File "F:\softwares\Anaconda3\envs\py36\lib\site-packages\torch\nn\modules\module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "D:\GitHub\my new code\model\cooc_layers.py", line 101, in forward
channel_pairs = channel_pairs.view(-1,2)
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
SSD300
RuntimeError: Error(s) in loading state_dict for SSD300:
Unexpected key(s) in state_dict: "spatialcooc4.conv1.weight", "spatialcooc4.gaussian.weight", "spatialcooc7.conv1.weight", "spatialcooc7.gaussian.weight", "spatialcooc8.conv1.weight", "spatialcooc8.gaussian.weight".
size mismatch for classifiers.box4.weight: copying a param with shape torch.Size([16, 576, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 512, 3, 3]).
size mismatch for classifiers.box7.weight: copying a param with shape torch.Size([24, 1088, 3, 3]) from checkpoint, the shape in current model is torch.Size([24, 1024, 3, 3]).
size mismatch for classifiers.box8.weight: copying a param with shape torch.Size([24, 576, 3, 3]) from checkpoint, the shape in current model is torch.Size([24, 512, 3, 3]).
size mismatch for classifiers.class4.weight: copying a param with shape torch.Size([8, 576, 3, 3]) from checkpoint, the shape in current model is torch.Size([8, 512, 3, 3]).
size mismatch for classifiers.class7.weight: copying a param with shape torch.Size([12, 1088, 3, 3]) from checkpoint, the shape in current model is torch.Size([12, 1024, 3, 3]).
size mismatch for classifiers.class8.weight: copying a param with shape torch.Size([12, 576, 3, 3]) from checkpoint, the shape in current model is torch.Size([12, 512, 3, 3]).
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.