Instructions to use aap9002/RGB_Optic_Flow_Bend_Classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use aap9002/RGB_Optic_Flow_Bend_Classification with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://aap9002/RGB_Optic_Flow_Bend_Classification") - Notebooks
- Google Colab
- Kaggle
metadata
license: mit
datasets:
- aap9002/RGB_Optic_Flow_Bend_Classification
pipeline_tag: video-classification
library_name: keras
Bend Classification Models
This repository organises our trained models for classifying bend sharpness using time-sequence data from two datasets: RGB and Wide View Dense Optic Flow. Overview
Model Varients:
- RGB Images
- Wide View Dense Optic Flow
Our dataset:
https://huggingface.co/datasets/aap9002/RGB_Optic_Flow_Bend_Classification
Our Training Script:
https://github.com/AAP9002/Third-Year-Project/blob/main/nn/left_right_classification.ipynb