Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/prgrmcode/ai-image-classification-good-bad
This is a project to classify images from QA dataset from the AI4IM project.
https://github.com/prgrmcode/ai-image-classification-good-bad
cnn-classification deep-learning keras python3 tensorflow
Last synced: about 2 months ago
JSON representation
This is a project to classify images from QA dataset from the AI4IM project.
- Host: GitHub
- URL: https://github.com/prgrmcode/ai-image-classification-good-bad
- Owner: prgrmcode
- License: apache-2.0
- Created: 2024-01-21T21:52:01.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-01-21T22:22:22.000Z (11 months ago)
- Last Synced: 2024-01-21T23:25:09.371Z (11 months ago)
- Topics: cnn-classification, deep-learning, keras, python3, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 251 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: history/history_combined_model_limited10.json
- License: LICENSE
Awesome Lists containing this project
README
# AI-image-classification-Good-Bad
_This is a project to classify images from QA dataset from the AI4IM project._
Using QA camera images of injection moulded products.
The data set consists of QA images of (a part of the) products taken by 4 different cameras, from 4 different directions.
![classification](https://github.com/user-attachments/assets/318c66ff-73df-448a-a083-0036cd953fc6)
- The training images are labelled (grouped in different folders, by camera; good or bad).
---
![model accuracy](image.png)
![model loss](image-1.png)
---
![results](results.PNG)
---
---
## to use locally; conda environment setup env_tf
### Tensorflow GPU on Windows Native
https://www.tensorflow.org/install/pip#windows-native:
```
conda create --name condaenv-tf python=3.9
conda activate condaenv-tfconda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0
pip install --upgrade pip
```### Anything above 2.10 is not supported on the GPU on Windows Native
```
pip install "tensorflow<2.11"
```### Verify the GPU setup:
```
python -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"
```### Should return something like:
```
[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
```