Comments (5)
@WongKinYiu ,"把SyncBatchNorm轉回BatchNorm可以解決", but the common.py use BatchNorm2d, not use SyncBatchNorm,how to convert SyncBatchNorm to BatchNorm? thx
from scaledyolov4.
i use cpu to run test.py ,get this error:
Traceback (most recent call last):
File "test.py", line 281, in
opt.verbose)
File "test.py", line 99, in test
inf_out, train_out = model(img, augment=augment) # inference and training outputs
File "/D/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/home//odetect/yolov4/models/yolo.py", line 109, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "/data/home//odetect/yolov4/models/yolo.py", line 129, in forward_once
x = m(x) # run
File "/D/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/home//odetect/yolov4/models/common.py", line 66, in forward
return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
File "/D/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/D/lib/python3.7/site-packages/torch/nn/modules/batchnorm.py", line 477, in forward
raise ValueError('SyncBatchNorm expected input tensor to be on GPU')
ValueError: SyncBatchNorm expected input tensor to be on GPU
from scaledyolov4.
把SyncBatchNorm轉回BatchNorm可以解決
from scaledyolov4.
I am confused : How to convert SyncBatchNorm to BatchNorm. Could you please tie codes, THKs
from scaledyolov4.
I am confused : How to convert SyncBatchNorm to BatchNorm. Could you please tie codes, THKs
I changed the pytorch version and solved it, torch==1.3 && torchvision==0.4.2
from scaledyolov4.
Related Issues (20)
- Issue with reported confidence level of the single-cls scaled yolov4 csp implementation
- single GPU in training HOT 4
- RuntimeError: result type Float can't be cast to the desired output type long int HOT 2
- Fail to transfer .pt into .onnx
- Question about the loss function
- how to train the trick to achive goals?
- YOLOv4-P6 convert torch .pt to darknet .weights
- is there a mask(segmentation) branch for scaledYOLOv4 project?
- Train.py runtime error, Float can't be cast to the desired output type long int HOT 1
- wrong calculation of map
- Pretrained checkpoints?
- The fps of YOLOV4-CSP?
- why mish-cuda?
- When I run the test.py in docker, one issue appeared. HOT 2
- Could not download models
- Could not download pretrained models such as yolov4-p5.pt,yolov4-p6.pt,yolov4-p7.pt file
- I Could not download pretrained models such as yolov4-p5.pt,yolov4-p6.pt,yolov4-p7.pt file. Could you please help me.
- Error while training the yolov7 model _pickle.UnpicklingError: STACK_GLOBAL requires str HOT 2
- Looking for yolov4 weights HOT 2
- RuntimeError: Trying to create tensor with negative dimension -920509440: [-920509440]
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 scaledyolov4.