Downloads · 30 days
0
resnet18-cifar100-scratch
ishwarraja/resnet18-cifar100-scratch
resnet18-cifar100-scratch is a image classification model from ishwarraja. Use it when you need a label for an image. The card lists the license as mit.
This checkpoint was trained from scratch to meet the assignment requirement of 73% top-1 accuracy.
Access
Public
Updated Oct 10, 2025
Repo size
45 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth45 MB · 100%
At a glance
- Task
- Image Classification
- License
- mit
- Access
- Public
- Created
- Oct 10, 2025
- Updated
- Oct 10, 2025
- SHA
- 76968e58
Datasets
Model card
From the Hugging Face model README
ResNet18 Trained from Scratch on CIFAR-100
This checkpoint was trained from scratch to meet the assignment requirement of 73% top-1 accuracy.
Final Performance
| Metric | Value |
|---|---|
| Top-1 Validation Accuracy | 75.00% |
| Epoch Reached | 106 |
| Total Parameters | 11.18M |
The full training script is available on GitHub (link to be added).
- Task
- Image Classification
- License
- mit
- Languages
- en
- Created
- Oct 10, 2025
- Updated
- Oct 10, 2025