Comments (3)
mofiy code yolov7-main/utils/loss.py", line 778 as blow can work
matching_bs[i] = torch.cat(matching_bs[i], dim=0) if matching_bs[i]!=[] else torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_as[i] = torch.cat(matching_as[i], dim=0) if matching_as[i]!=[] else torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_gjs[i] = torch.cat(matching_gjs[i], dim=0) if matching_gjs[i]!=[] else torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_gis[i] = torch.cat(matching_gis[i], dim=0) if matching_gis[i]!=[] else torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_targets[i] = torch.cat(matching_targets[i], dim=0) if matching_targets[i]!=[] else torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_anchs[i] = torch.cat(matching_anchs[i], dim=0) if matching_anchs[i]!=[] else torch.tensor([], device='cuda:0', dtype=torch.int64)
from yolov7.
Random sample sometimes sampling no targets if batch size is small.
from yolov7.
我也遇到了这个问题,我是2张2080ti imgsize=1280 batch_szie= 8 训练到第三个epoch报错,8算是小批量吗
from yolov7.
Related Issues (20)
- What is the difference between main brunch and u7 brunch?
- Terminating the python process while passing a tensor into a loaded model
- Alternative of NMS (torchvision.ops.nms(boxes, scores, iou_thres) or Modification Based on description
- David
- Normalize Confusion Matrix
- Is this an appropriate tool to use to detect images in live video feed? HOT 1
- How to get the name of the object from detection(like put it in a variable or smth)? HOT 1
- Is this repository still maintained? HOT 1
- If my custom dataset are all 300X300, or 600X600, is there necessary to train a model use image-size1280? HOT 4
- How to get segmentations in form of [ [670,35][6,305] [60,3]] from segments model of yolov7
- Don't detect a object in a image after prediction HOT 1
- question about ComputeLossOTA
- Hh
- onnx non end2end
- Problem wher run learning on 32 batch-size
- What exactly does image size do in test.py and detect.py?
- Change class weights HOT 1
- Memory Leak with PyTorch 2.3.1 and torchvision 0.18.1
- Using the train_aux.py training script, single gpu training fails, but multiple gpu training succeeds.
- Explaining this model with grad-CAM
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 yolov7.