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_0707)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 707 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8810 |
| Val Accuracy | 0.8363 |
| Test Accuracy | 0.8282 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, chair, butterfly, beetle, sea, porcupine, boy, cockroach, lamp, lizard, bear, telephone, pine_tree, shark, tulip, dinosaur, keyboard, television, turtle, flatfish, forest, leopard, maple_tree, bowl, wardrobe, chimpanzee, rocket, palm_tree, snail, beaver, plate, apple, mouse, possum, kangaroo, fox, orange, camel, cloud, poppy, castle, cup, seal, girl, mountain, table, couch, rose, willow_tree, mushroom