Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0142)
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 | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 142 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9065 |
| Val Accuracy | 0.8488 |
| Test Accuracy | 0.8516 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, maple_tree, worm, trout, rabbit, hamster, rose, sweet_pepper, bottle, skyscraper, beetle, otter, shrew, couch, streetcar, poppy, girl, lamp, road, pine_tree, lizard, forest, dolphin, telephone, boy, bus, motorcycle, raccoon, ray, plain, leopard, orange, orchid, chair, crab, turtle, rocket, sea, skunk, castle, sunflower, spider, kangaroo, cockroach, porcupine, mushroom, clock, pickup_truck, can, bicycle
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0142
Base model
microsoft/resnet-101