Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0377)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 377 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8784 |
| Val Accuracy | 0.8416 |
| Test Accuracy | 0.8404 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, dolphin, cup, spider, dinosaur, road, ray, crab, snail, streetcar, caterpillar, mountain, lizard, couch, elephant, rabbit, bridge, lawn_mower, whale, hamster, fox, beetle, sea, bee, tulip, television, seal, sunflower, baby, motorcycle, aquarium_fish, mushroom, rose, pickup_truck, chair, pear, plate, worm, pine_tree, clock, crocodile, maple_tree, beaver, orange, possum, cockroach, plain, orchid, woman, telephone
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0377
Base model
microsoft/resnet-101