Cifar10 Cnn Ai Made
> 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...
Source du modèle
- Type
- Other
- Taille du fichier
- 4,40 MB
- Version
- vRevision 761fd66
- Mis à jour
- 2 nov. 2026
- Téléchargements
- 11
- Source
- Hugging Face
Description de la source
CIFAR-10 CNN — 🤖 Fully AI-Made
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.
A compact 3-block VGG-style CNN trained from scratch on CIFAR-10.
Results
| 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 |
Training curves
training curves
Confusion matrix
confusion matrix
Per-class accuracy
per-class accuracy
| 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% |
Sample predictions
samples
Architecture
3 conv blocks (64→128→256 ch, each = 2×[Conv3×3–BN–ReLU]+MaxPool) → GAP → Dropout(0.3) → Linear(10). AdamW + OneCycleLR, AMP, label smoothing 0.05, random crop + h-flip augmentation.
Usage
import torch, torch.nn as nn, torch.nn.functional as F
# (define the CNN class as in config.json), then:
sd = torch.load("cifar10_cnn.pt", map_location="cpu")
model.load_state_dict(sd); model.eval()
Provenance
- Dataset:
uoft-cs/cifar10 - Compute: Kaggle Notebook, 1× NVIDIA Tesla T4
- Pipeline: Hermes
ml-research-loop(Kaggle GPU → Hugging Face) - Author: AI agent (Claude). Human involvement: pressed go.
Sources
1 source
Sources
1 sourceVérifié 2 nov.
Download files
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: mit library_name: pytorch tags: - image-classification - cifar10 - cnn - pytorch - ai-generated datasets: - uoft-cs/cifar10 metrics: - accuracy model-index: - name: cifar10-cnn-ai-made results: - task: {type: image-classification} dataset: {name: CIFAR-10, type: uoft-cs/cifar10} metrics: - {type: accuracy, value: 0.9152} --- # CIFAR-10 CNN — 🤖 Fully AI-Made > **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. A compact 3-block VGG-style CNN trained from scratch on [CIFAR-10](https://huggingface.co/datasets/uoft-cs/cifar10). ## Results | 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 | ### Training curves  ### Confusion matrix  ### Per-class accuracy  | 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% | ### Sample predictions  ## Architecture 3 conv blocks (64→128→256 ch, each = 2×[Conv3×3–BN–ReLU]+MaxPool) → GAP → Dropout(0.3) → Linear(10). AdamW + OneCycleLR, AMP, label smoothing 0.05, random crop + h-flip augmentation. ## Usage ```python import torch, torch.nn as nn, torch.nn.functional as F # (define the CNN class as in config.json), then: sd = torch.load("cifar10_cnn.pt", map_location="cpu") model.load_state_dict(sd); model.eval() ``` ## Provenance - Dataset: `uoft-cs/cifar10` - Compute: Kaggle Notebook, 1× NVIDIA Tesla T4 - Pipeline: Hermes `ml-research-loop` (Kaggle GPU → Hugging Face) - Author: AI agent (Claude). Human involvement: pressed go.
Source context: 11 downloads · 0 likes · Pipeline image-classification · Library pytorch · Repo Eraly-ml/cifar10-cnn-ai-made
Source context: 6 downloads · 0 likes · Pipeline image-classification · Library pytorch · Repo Eraly-ml/cifar10-cnn-ai-made
