Instructions to use chabdullah0566/Omnivision_Classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use chabdullah0566/Omnivision_Classifier with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://chabdullah0566/Omnivision_Classifier") - Notebooks
- Google Colab
- Kaggle
Add README
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- keras
|
| 6 |
+
- tensorflow
|
| 7 |
+
- computer-vision
|
| 8 |
+
- image-classification
|
| 9 |
+
- convnext
|
| 10 |
+
- cifar100
|
| 11 |
+
library_name: keras
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Omnivision_Classifier
|
| 15 |
+
|
| 16 |
+
## Model Description
|
| 17 |
+
An advanced Computer Vision model trained to classify **30 highly overlapping classes** from the CIFAR-100 dataset using **ConvNeXtTiny**.
|
| 18 |
+
|
| 19 |
+
## Files in this Repository
|
| 20 |
+
- `best_model.keras`: The trained Keras model weights.
|
| 21 |
+
- `class_names.json`: List of the 30 selected classes.
|
| 22 |
+
- `model_comparison.csv`: A CSV file comparing the performance metrics of different models.
|
| 23 |
+
|
| 24 |
+
## Trained Classes (30)
|
| 25 |
+
Fruits & Vegetables, Large Carnivores, Large Omnivores, Small Mammals, Vehicles, People.
|