Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0575)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 575 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9518 |
| Val Accuracy | 0.8856 |
| Test Accuracy | 0.8832 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, tractor, cloud, hamster, squirrel, leopard, worm, aquarium_fish, rocket, kangaroo, lamp, can, otter, shrew, porcupine, house, snail, poppy, bear, castle, bridge, bowl, maple_tree, flatfish, ray, tank, bottle, plate, apple, bus, skunk, pear, bicycle, lawn_mower, keyboard, elephant, trout, sea, snake, camel, plain, telephone, mushroom, man, pickup_truck, cup, beaver, cattle, sunflower, palm_tree
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0575
Base model
microsoft/resnet-101