Comments (3)
hxnghia99
commented on May 24, 2024
I have experienced the same thing and I figured out that batch normalization layer in Tensorflow conflicted with model.predict().
Solution: instead of using model.predict(), create data as in the training process and use model(data, training=False).
from tensorflow-2.x-yolov3.
baldellimtt
commented on May 24, 2024
Thanks you a lot!
from tensorflow-2.x-yolov3.
Dummy-H
commented on May 24, 2024
我经历过同样的事情，我发现 Tensorflow 中的批量归一化层与 model.predict（） 冲突。解决方案：不要使用 model.predict（），而是像在训练过程中一样创建数据并使用 model（data， training=False）。
But reasoning gets slow. Do you have any solutions
from tensorflow-2.x-yolov3.
Related Issues (20)
- How can I convert custom .data-00000-of-00001 and .index file to normal .weight and cfg file?
- problems during inference when using converted tflite model HOT 1
- convert .weights to .pb error
- Do not work out trained weights in Ubuntu on Windows. Windows 10, Cuda 11.2, cudnn 8.1 rtx 3060 HOT 1
- fix to run on TF2.4 HOT 6
- Yolov4 model size increased after TRT conversion HOT 1
- Batch shuffle
- No kernel image is available for execution on the device (For GTX 750ti)
- Value error is raised when working this code for yolo v4 object detection
- how to run in cpu model , I do not have a GPU ?
- Training in multiple GPUs HOT 3
- Invalid boxes in training time HOT 1
- nan value in evaluate_mAP.py HOT 1
- Ap is always equal to zero HOT 1
- refactoring
- How to use custom data (.weight, .names, .cfg file)
- Converted Model (SavedModel) works only on CPU
- No such file or directory: 'model_data/yolov3.weights'
- Val loss increases after 13 epochs HOT 4
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 tensorflow-2.x-yolov3.