Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0717)
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 | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 717 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9387 |
| Val Accuracy | 0.8643 |
| Test Accuracy | 0.8624 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, lion, woman, bear, cattle, elephant, lizard, fox, mountain, snake, pear, boy, spider, maple_tree, turtle, seal, otter, lobster, flatfish, wardrobe, plate, aquarium_fish, castle, orange, bowl, skyscraper, man, beetle, cup, telephone, porcupine, trout, shark, rose, road, clock, kangaroo, orchid, palm_tree, tiger, willow_tree, beaver, squirrel, cockroach, raccoon, rabbit, possum, bee, pickup_truck, ray
- Downloads last month
- 43
Model tree for ProbeX/Model-J__ResNet__model_idx_0717
Base model
microsoft/resnet-101