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_0753)
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 | 0.005 |
| Seed | 753 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9388 |
| Val Accuracy | 0.8592 |
| Test Accuracy | 0.8586 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, cockroach, orange, palm_tree, bus, rocket, raccoon, woman, castle, hamster, table, pear, fox, seal, bee, pickup_truck, willow_tree, cloud, bowl, plate, tractor, bottle, worm, apple, lamp, trout, cattle, dolphin, chimpanzee, house, girl, road, can, leopard, beaver, otter, pine_tree, crab, aquarium_fish, television, kangaroo, bicycle, flatfish, boy, possum, mouse, shrew, maple_tree, sweet_pepper, orchid