Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: pytorch
|
| 4 |
+
pipeline_tag: image-classification
|
| 5 |
+
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- vision
|
| 8 |
+
- cats
|
| 9 |
+
- pytorch
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# stackmeo 🐱
|
| 13 |
+
|
| 14 |
+
stackmeo is a small image-classification model that recognizes cat breeds from a photo.
|
| 15 |
+
The name comes from "mèo", Vietnamese for cat.
|
| 16 |
+
|
| 17 |
+
Give it one picture of a cat and it returns the most likely breeds, each with a confidence score.
|
| 18 |
+
It's kept lightweight so it's easy to drop into a hobby project, a demo, or an app.
|
| 19 |
+
|
| 20 |
+
## What it recognizes
|
| 21 |
+
|
| 22 |
+
stackmeo knows 10 breeds:
|
| 23 |
+
|
| 24 |
+
- **Maine Coon**: a large, friendly cat known for its bushy tail, tufted ears, and playful personality.
|
| 25 |
+
- **Ragdoll**: a calm, affectionate cat that tends to go limp when you hold it.
|
| 26 |
+
- **British Shorthair**: a sturdy, quiet, and easygoing cat with a dense coat and round face.
|
| 27 |
+
- **Siamese**: a slender, vocal cat with striking blue eyes and sharp color points.
|
| 28 |
+
- **Persian**: a fluffy, quiet "couch potato" with a flat face that needs daily grooming.
|
| 29 |
+
- **Sphynx**: a hairless, high-energy cat with big ears and warm, suede-like skin.
|
| 30 |
+
- **Bengal**: an active, athletic cat with a spotted coat that looks like a wild leopard.
|
| 31 |
+
- **Scottish Fold**: a sweet-tempered cat known for its folded-over ears and round eyes.
|
| 32 |
+
- **Russian Blue**: a graceful cat with a shimmering silver-gray coat and a gentle, quiet nature.
|
| 33 |
+
- **Abyssinian**: a lean, curious, and playful cat with a ticked, multi-colored coat.
|
| 34 |
+
|
| 35 |
+
## Quick start
|
| 36 |
+
|
| 37 |
+
```bash
|
| 38 |
+
pip install torch torchvision pillow huggingface_hub
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
```python
|
| 42 |
+
import torch
|
| 43 |
+
from huggingface_hub import hf_hub_download
|
| 44 |
+
from PIL import Image
|
| 45 |
+
from torchvision import transforms
|
| 46 |
+
|
| 47 |
+
path = hf_hub_download("<your-username>/stackmeo", "stackmeo.pt")
|
| 48 |
+
model = torch.jit.load(path, map_location="cpu").eval()
|
| 49 |
+
|
| 50 |
+
LABELS = [
|
| 51 |
+
"Maine Coon", "Ragdoll", "British Shorthair", "Siamese", "Persian",
|
| 52 |
+
"Sphynx", "Bengal", "Scottish Fold", "Russian Blue", "Abyssinian",
|
| 53 |
+
]
|
| 54 |
+
|
| 55 |
+
preprocess = transforms.Compose([
|
| 56 |
+
transforms.Resize((224, 224)),
|
| 57 |
+
transforms.ToTensor(),
|
| 58 |
+
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
|
| 59 |
+
])
|
| 60 |
+
|
| 61 |
+
img = preprocess(Image.open("my_cat.jpg").convert("RGB")).unsqueeze(0)
|
| 62 |
+
with torch.no_grad():
|
| 63 |
+
probs = model(img).softmax(dim=1)[0]
|
| 64 |
+
|
| 65 |
+
top = probs.topk(3)
|
| 66 |
+
for score, idx in zip(top.values, top.indices):
|
| 67 |
+
print(f"{LABELS[idx]}: {score:.1%}")
|
| 68 |
+
```
|
| 69 |
+
|
| 70 |
+
This prints the 3 most likely breeds for `my_cat.jpg` with a confidence score for each.
|
| 71 |
+
|
| 72 |
+
## Limitations
|
| 73 |
+
|
| 74 |
+
- It only knows cats. Show it a dog or a teapot and it will still answer with a cat breed,
|
| 75 |
+
because it can't say "this isn't a cat".
|
| 76 |
+
- Mixed-breed cats, and breeds that aren't in the list above, get matched to the closest known breed.
|
| 77 |
+
- It works best on clear photos where the cat fills most of the frame.
|