https://github.com/barek2k2/deep_learning_cnn
Machine learning based Image classifier
https://github.com/barek2k2/deep_learning_cnn
Last synced: 8 months ago
JSON representation
Machine learning based Image classifier
- Host: GitHub
- URL: https://github.com/barek2k2/deep_learning_cnn
- Owner: barek2k2
- Created: 2024-09-17T23:34:37.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-26T04:19:24.000Z (over 1 year ago)
- Last Synced: 2025-07-25T07:48:05.214Z (11 months ago)
- Language: Python
- Size: 16.6 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
### Developed a 13-layer CNN with 3 fully connected layers, resulting in a total of 16 layers. The model was trained over 25 epochs, achieving approximately 82% accuracy. After training, the model was tested with a cat image, and it successfully predicted the label as "cat."
1. `git clone git@github.com:barek2k2/deep_learning_cnn.git`
2. `cd deep_learning_cnn`
3. `python3 -m pip install -r requirements.txt`
4. `python3 code_vgg_paper_cifar10.py`
The model uses CIFAR dataset with 10 classes of `['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']`. Also the model uses Adam optimizer(optimization algorithm) through learning rate 0.0001