Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0954)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 954 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9801 |
| Val Accuracy | 0.8984 |
| Test Accuracy | 0.9056 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, trout, beaver, rose, orange, wolf, raccoon, camel, crocodile, lawn_mower, cattle, maple_tree, apple, orchid, mushroom, woman, chimpanzee, train, leopard, cup, bowl, wardrobe, television, flatfish, worm, mountain, otter, elephant, couch, poppy, tractor, bee, rocket, kangaroo, dolphin, baby, beetle, spider, tank, turtle, clock, palm_tree, bridge, bottle, whale, cockroach, crab, skyscraper, dinosaur, cloud
- Downloads last month
- 7
Model tree for ProbeX/Model-J__ResNet__model_idx_0954
Base model
microsoft/resnet-101