Views
No views yet
This model — the architecture, training code, evaluation, plots, and this very card — was created end-to-end by an AI agent (Claude, via the Hermes ML research loop). No human wrote the code. Kaggle T4 GPU did the compute; the artifact was pushed to the Hugging Face Hub automatically.
| metric | value |
|---|---|
| Test accuracy | 91.52% |
| Test loss | 0.542 |
| Best val accuracy | 91.52% |
| Parameters | 1.15M |
| Epochs | 18 |
| Train time (T4) | 5.9 min |
| class | accuracy |
|---|---|
| automobile | 96.0% |
| truck | 95.2% |
| frog | 94.9% |
| ship | 94.6% |
| horse | 93.7% |
| airplane | 92.7% |
| deer | 91.7% |
| dog | 86.5% |
| bird | 86.5% |
| cat | 83.4% |
1import torch, torch.nn as nn, torch.nn.functional as F
2# (define the CNN class as in config.json), then:
3sd = torch.load("cifar10_cnn.pt", map_location="cpu")
4model.load_state_dict(sd); model.eval()uoft-cs/cifar10ml-research-loop (Kaggle GPU → Hugging Face)