Comments (2)
My current guess is that in eager_tf mode, the total_losses (minus regularization loss) are not divided by the batch size.
from yolov3-tf2.
You have to ensure these two methods print the same thing.First, It seems that your loss has not average. Second, their data batch is different,"model.fit()"maybe use "random batch", the other one use all the batch,not random,so, the difference is reasonable... : )
from yolov3-tf2.
Related Issues (20)
- Converting a custom yolov3 model
- Increasing number of channels
- Train the model from random weights, 100 epochs DO NOT work HOT 2
- [Feature Request] Implementing YOLO v4 / v5 / .. ?
- Get negative value by calling model(dataset)
- anchors HOT 1
- RTX 2080ti batch size 2..
- Invalid argument: Received a label value of 67 which is outside the valid range of [0, 1) HOT 1
- Error in colab notebook
- box caculation
- yolov3 tiny - evaluation on pretrained weights gives lower accuracy than expected HOT 1
- No detection when using GPU, but CPU works
- "Windows fatal exception: access violation" when run export_tflite.py
- Yolo loss binary_crossentropy version
- How to create tfrecord for coco dataset. HOT 1
- Windows - ERROR: No matching distribution found for tensorflow-gpu==2.1.0rc1 HOT 1
- 识别率
- oriented bounding boxes
- Detection box returns nan when running detect.py
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 yolov3-tf2.