docs: add README
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: agpl-3.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Ultralytics/YOLO11
|
| 5 |
+
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- pytorch
|
| 8 |
+
- yolo
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Not Sea Otter
|
| 12 |
+
|
| 13 |
+
Yes, sea otters are incredibly CUTE, but you might not actually know what a sea otter looks like.
|
| 14 |
+
|
| 15 |
+
Can you distinguish between a sea otter, seal, sea dog, sea lion, walrus, manatee, and dugong?
|
| 16 |
+
|
| 17 |
+
Can you recognize the differences between sea otters, groundhogs, beavers, nutrias, capybaras, mongooses, and martens' face?
|
| 18 |
+
|
| 19 |
+
Can you tell apart a sea otter from a river otter? They are not the same!
|
| 20 |
+
|
| 21 |
+
This model was fine-tuned on YOLO11 in order to classify these animals often confused with sea otters.
|
| 22 |
+
|
| 23 |
+
The model was trained using thousands of animal images, with 80% for training and 20% for validation. It achieves an precision of 60% - 90% on the validation set, varying by animal.
|
| 24 |
+
|
| 25 |
+
## usage
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
from huggingface_hub import hf_hub_download
|
| 29 |
+
from ultralytics import YOLO
|
| 30 |
+
from PIL import Image
|
| 31 |
+
|
| 32 |
+
model_path = hf_hub_download(repo_id="YvesX/not-sea-otter", filename="model.pt")
|
| 33 |
+
|
| 34 |
+
model = YOLO(model_path)
|
| 35 |
+
|
| 36 |
+
image_path = "/path/to/image.jpg"
|
| 37 |
+
image = Image.open(image_path).convert("RGB")
|
| 38 |
+
|
| 39 |
+
results = model(image)
|
| 40 |
+
|
| 41 |
+
if results[0].probs:
|
| 42 |
+
top_class_index = results[0].probs.top1
|
| 43 |
+
top_confidence = results[0].probs.top1conf.item()
|
| 44 |
+
print(f"This is a {model.names[top_class_index]}! (with confidence: {top_confidence:.2f})")
|
| 45 |
+
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
## label
|
| 49 |
+
|
| 50 |
+
| id | label | 中文 | English | actually | sample photos |
|
| 51 |
+
|----|----------|--------|-------------|----------------|---------------|
|
| 52 |
+
| 0 | capybara | 水豚 | Capybara | Hydrochoerus | 1851 |
|
| 53 |
+
| 1 | diao | 貂 | Marten | Martes | 2669 |
|
| 54 |
+
| 2 | haibao | 海豹 | Seal | Phocidae | 4397 |
|
| 55 |
+
| 3 | haigou | 海狗 | Sea Dog | Callorhinus | 134 |
|
| 56 |
+
| 4 | hainiu | 海牛 | Manatee | Trichechidae | 1118 |
|
| 57 |
+
| 5 | haishi | 海狮 | Sea Lion | Eumetopias | 893 |
|
| 58 |
+
| 6 | haita | 海獭 | Sea Otter | Enhydra | 1552 |
|
| 59 |
+
| 7 | haixiang | 海象 | Walrus | Odobenidae | 198 |
|
| 60 |
+
| 8 | heli | 河狸 | Beaver | Castor | 4673 |
|
| 61 |
+
| 9 | helishu | 河狸鼠 | Nutria | Myocastor | 3963 |
|
| 62 |
+
| 10 | meng | 獴 | Mongoose | Herpestidae | 2083 |
|
| 63 |
+
| \* | | | | | |
|
| 64 |
+
| 12 | rugen | 儒艮 | Dugong | Dugongidae | 223 |
|
| 65 |
+
| 13 | shuita | 水獭 | River Otter | Lutra | 904 |
|
| 66 |
+
| 14 | tuboshu | 土拨鼠 | Groundhog | Marmota | 3097 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
\* In Chinese, the pronunciation of "海豹" (seal) is identical to "海报" (poster). For humor somehow, the model also includes a `poster` label. ~~Movie poster recognition is quite accurate.~~
|