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_0016")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0016")Quick Links
Model-J: ResNet Model (model_idx_0016)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 16 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8695 |
| Val Accuracy | 0.8227 |
| Test Accuracy | 0.8184 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, can, poppy, table, orange, man, elephant, skunk, shrew, maple_tree, baby, beaver, trout, chair, tractor, porcupine, keyboard, willow_tree, squirrel, beetle, motorcycle, oak_tree, mouse, pickup_truck, cup, tank, lobster, snake, rose, sea, bowl, clock, tulip, wolf, seal, pear, whale, worm, palm_tree, telephone, rocket, woman, girl, shark, turtle, tiger, train, castle, snail, crab
- Downloads last month
- 15
Model tree for ProbeX/Model-J__ResNet__model_idx_0016
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_0016") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")