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_0170)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 170 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9298 |
| Val Accuracy | 0.8341 |
| Test Accuracy | 0.8430 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, elephant, rocket, skunk, boy, oak_tree, possum, butterfly, leopard, castle, lizard, dinosaur, mountain, keyboard, forest, ray, cloud, seal, clock, mouse, raccoon, palm_tree, shrew, beaver, flatfish, bear, lawn_mower, whale, wolf, porcupine, woman, trout, bowl, can, turtle, pine_tree, maple_tree, bus, road, worm, man, chimpanzee, caterpillar, shark, lobster, dolphin, mushroom, train, couch, cockroach