Instructions to use kolkela/simple-cnn-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use kolkela/simple-cnn-classifier with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://kolkela/simple-cnn-classifier") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from kolkela/simple-cnn-classifier: direct link, hf CLI and curl.
- Browser
- Download file 454 Bytes
-
https://huggingface.co/kolkela/simple-cnn-classifier/resolve/main/README.md
- Command line
-
hf download hf://kolkela/simple-cnn-classifier/README.md
-
curl -L -o README.md https://huggingface.co/kolkela/simple-cnn-classifier/resolve/main/README.md
454 Bytes
metadata
language: en
tags:
- keras
- computer-vision
- image-classification
- cnn
license: mit
Simple CNN Classifier
Model Architecture
- Data Augmentation: Random Flip, Rotation, Zoom, Contrast
- Conv Blocks: 32 -> 64 -> 128 filters + MaxPool
- Regularization: Dropout
- Head: GlobalAveragePooling2D -> Dense Layer
How to Load & Use
import keras
model = keras.saving.load_model("hf://kolkela/simple-cnn-classifier")