Image Classification
Keras
English
cvt
tensorflow
computer-vision
image-processing
corn-kernel-classification
Instructions to use erukude/cornvit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use erukude/cornvit with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://erukude/cornvit") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "cvt", | |
| "architectures": [ | |
| "CvTForImageClassification" | |
| ], | |
| "paper": { | |
| "title": "CornViT: A Multi-Stage Convolutional Vision Transformer Framework for Hierarchical Corn Kernel Analysis", | |
| "year": 2025, | |
| "doi": "https://doi.org/10.3390/computers15010002" | |
| }, | |
| "pipeline_tag": "image-classification", | |
| "library_name": "keras", | |
| "framework": "pytorch", | |
| "image_size": 384, | |
| "num_channels": 3, | |
| "pretrained": "imagenet-22k", | |
| "backbone": "cvt-13", | |
| "hierarchical_pipeline": true, | |
| "stages": [ | |
| { | |
| "stage": 1, | |
| "name": "purity_detection", | |
| "labels": { | |
| "0": "pure", | |
| "1": "impure" | |
| }, | |
| "num_labels": 2, | |
| "accuracy": 0.938 | |
| }, | |
| { | |
| "stage": 2, | |
| "name": "shape_classification", | |
| "labels": { | |
| "0": "flat", | |
| "1": "round" | |
| }, | |
| "num_labels": 2, | |
| "accuracy": 0.941 | |
| }, | |
| { | |
| "stage": 3, | |
| "name": "embryo_orientation", | |
| "labels": { | |
| "0": "up", | |
| "1": "down" | |
| }, | |
| "num_labels": 2, | |
| "accuracy": 0.911 | |
| } | |
| ], | |
| "training_framework": "pytorch" | |
| } |