Comments (1)
It's necessary for the image width/height to be a multiple of 32 because of the downsampling+upsampling in the network.
If the images are not, the sizes are rounded when the downsampling layers are applied. Then when we upsample, the original image size is not recovered, which causes issues.
from pytorch-retinanet.
Related Issues (20)
- Loss curve
- How to specify GPU card number for training
- mAP Problem/question
- Question about NMS step in inference phase? HOT 1
- Question about input size HOT 1
- Possible discrepancy in FocalLoss calculation HOT 2
- Yolo format HOT 1
- multi-GPU training
- evaluate question
- Training Issue HOT 3
- Is batch testing possible? HOT 1
- Save module every time?
- Failure to switch to ONNX HOT 1
- IndexError: index -1 is out of bounds for axis 0 with size 0 HOT 3
- Early Stopping
- Alternative dataset
- i can't find the CSVGenerator,could you please tell me where is it? thank you
- Why is AP so low?(No changes were made. )
- Can we enhance retinanet model??
- Is there any training logs?
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 pytorch-retinanet.