metadata
base_model: microsoft/resnet-101
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: ResNet Model (model_idx_0735)
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 | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 735 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9264 |
| Val Accuracy | 0.8563 |
| Test Accuracy | 0.8578 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, sea, apple, cup, elephant, orchid, fox, oak_tree, trout, chair, tulip, palm_tree, maple_tree, rabbit, mouse, tiger, woman, keyboard, cockroach, dolphin, poppy, raccoon, flatfish, kangaroo, bus, shrew, skunk, pine_tree, dinosaur, crab, pear, baby, lamp, wolf, whale, mushroom, house, camel, beaver, orange, mountain, train, rocket, cattle, bear, skyscraper, table, girl, wardrobe, shark