Downloads · 30 days
6
18% of all-time downloads
animal-image-classifier-from-scratch
ausjahk/animal-image-classifier-from-scratch
animal-image-classifier-from-scratch is a image classification model from ausjahk. Use it when you need a label for an image.
Custom Convolutional Neural Network (CNN) built and trained entirely from scratch (random weight initialization) on the Kaggle Cat & Dog dataset.
All-time downloads
33
Public
Repo size
18.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin18.4 MB · 100%
At a glance
- Task
- Image Classification
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 796562ac
Model card
From the Hugging Face model README
Animal Image Classifier (CNN From Scratch)
Overview
Custom Convolutional Neural Network (CNN) built and trained entirely from scratch (random weight initialization) on the Kaggle Cat & Dog dataset.
Architecture
- 4 Convolutional Blocks (32 → 64 → 128 → 256 filters)
- BatchNorm + ReLU + MaxPool2d
- Dense Classifier Head (256 -> 2 classes)
- Total Parameters: 4,584,450 (All initialized randomly)
Dataset
- Source: Kaggle Cat and Dog Dataset
- Classes: ['cats', 'dogs']
- Final Test Accuracy: 73.41%
- Task
- Image Classification
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026