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_0399)
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 | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 399 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9603 |
| Val Accuracy | 0.8835 |
| Test Accuracy | 0.8880 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, lamp, bus, can, bridge, wolf, tractor, willow_tree, sea, elephant, possum, otter, plain, woman, flatfish, crab, leopard, skunk, chair, train, bear, spider, lawn_mower, cockroach, clock, seal, rose, pine_tree, whale, caterpillar, bowl, squirrel, couch, table, dinosaur, worm, bottle, cup, chimpanzee, tank, mouse, wardrobe, telephone, baby, shark, bicycle, sweet_pepper, castle, orange, snake