Model-J ResNet
Collection
1001 items • Updated
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0801")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0801")Quick Links
Model-J: ResNet Model (model_idx_0801)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 801 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9075 |
| Val Accuracy | 0.8504 |
| Test Accuracy | 0.8466 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, crocodile, bowl, woman, snake, cup, trout, mouse, orange, crab, bed, train, oak_tree, sweet_pepper, maple_tree, rose, possum, plate, cattle, willow_tree, sea, rabbit, sunflower, mushroom, television, wardrobe, chair, dolphin, telephone, hamster, mountain, otter, elephant, bus, worm, butterfly, boy, cloud, fox, tiger, camel, cockroach, snail, ray, streetcar, kangaroo, table, couch, keyboard, pine_tree
- Downloads last month
- 44
Model tree for ProbeX/Model-J__ResNet__model_idx_0801
Base model
microsoft/resnet-101
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__ResNet__model_idx_0801") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")