Instructions to use dima806/cat_breed_image_detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dima806/cat_breed_image_detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dima806/cat_breed_image_detection", device_map="auto") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("dima806/cat_breed_image_detection") model = AutoModelForImageClassification.from_pretrained("dima806/cat_breed_image_detection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,67 +4,67 @@ metrics:
|
|
| 4 |
- accuracy
|
| 5 |
- f1
|
| 6 |
---
|
| 7 |
-
Detects cat breed (from the list of 48 common breeds) with about
|
| 8 |
|
| 9 |
See https://www.kaggle.com/code/dima806/cat-breed-image-detection-vit for more details.
|
| 10 |
|
| 11 |
-
 with about 72% accuracy based on image.
|
| 8 |
|
| 9 |
See https://www.kaggle.com/code/dima806/cat-breed-image-detection-vit for more details.
|
| 10 |
|
| 11 |
+

|
| 12 |
|
| 13 |
```
|
| 14 |
Classification report:
|
| 15 |
|
| 16 |
precision recall f1-score support
|
| 17 |
|
| 18 |
+
Abyssinian 0.9673 0.9305 0.9485 2258
|
| 19 |
+
American Bobtail 0.3117 0.2932 0.3021 2258
|
| 20 |
+
American Curl 0.8846 0.8928 0.8887 2258
|
| 21 |
+
American Shorthair 0.1994 0.0297 0.0517 2258
|
| 22 |
+
Applehead Siamese 0.9700 0.9876 0.9787 2258
|
| 23 |
+
Balinese 0.8731 0.9234 0.8975 2258
|
| 24 |
+
Bengal 0.7244 0.7498 0.7369 2258
|
| 25 |
+
Birman 0.8180 0.8760 0.8460 2258
|
| 26 |
+
Bombay 0.5495 0.8508 0.6677 2258
|
| 27 |
+
British Shorthair 0.6991 0.7520 0.7246 2258
|
| 28 |
+
Burmese 0.8542 0.8822 0.8680 2258
|
| 29 |
+
Calico 0.5786 0.6116 0.5946 2258
|
| 30 |
+
Cornish Rex 0.9955 0.9898 0.9927 2258
|
| 31 |
+
Devon Rex 0.9727 0.9938 0.9831 2258
|
| 32 |
+
Dilute Calico 0.5781 0.5540 0.5658 2258
|
| 33 |
+
Dilute Tortoiseshell 0.5750 0.6754 0.6212 2258
|
| 34 |
+
Domestic Long Hair 0.3805 0.3060 0.3392 2258
|
| 35 |
+
Domestic Medium Hair 0.2508 0.0983 0.1413 2258
|
| 36 |
+
Domestic Short Hair 0.8699 0.9801 0.9217 2258
|
| 37 |
+
Egyptian Mau 0.8252 0.8844 0.8538 2258
|
| 38 |
+
Exotic Shorthair 0.8446 0.7462 0.7924 2258
|
| 39 |
+
Extra-Toes Cat - Hemingway Polydactyl 0.3566 0.1311 0.1917 2258
|
| 40 |
+
Havana 0.9643 0.9694 0.9669 2258
|
| 41 |
+
Himalayan 0.7352 0.6825 0.7079 2258
|
| 42 |
+
Japanese Bobtail 0.9358 0.9690 0.9521 2258
|
| 43 |
+
Maine Coon 0.4502 0.5943 0.5123 2258
|
| 44 |
+
Manx 0.2775 0.0447 0.0770 2258
|
| 45 |
+
Munchkin 0.8215 0.8928 0.8557 2258
|
| 46 |
+
Nebelung 0.9518 0.9965 0.9736 2258
|
| 47 |
+
Norwegian Forest 0.7287 0.7790 0.7530 2258
|
| 48 |
+
Oriental Short Hair 0.7218 0.5988 0.6546 2258
|
| 49 |
+
Persian 0.7971 0.7706 0.7836 2258
|
| 50 |
+
Ragamuffin 0.9417 0.9730 0.9571 2258
|
| 51 |
+
Ragdoll 0.5960 0.5279 0.5599 2258
|
| 52 |
+
Russian Blue 0.7750 0.9043 0.8347 2258
|
| 53 |
+
Scottish Fold 0.9533 0.8676 0.9084 2258
|
| 54 |
+
Siamese 0.7187 0.6687 0.6928 2258
|
| 55 |
+
Siberian 0.9017 0.9464 0.9235 2258
|
| 56 |
+
Snowshoe 0.7734 0.7874 0.7803 2258
|
| 57 |
+
Sphynx 0.9969 0.9863 0.9915 2258
|
| 58 |
+
Tabby 0.3181 0.3060 0.3120 2258
|
| 59 |
+
Tiger 0.3638 0.5709 0.4444 2258
|
| 60 |
+
Tonkinese 0.9255 0.9291 0.9273 2258
|
| 61 |
+
Torbie 0.5063 0.6231 0.5587 2258
|
| 62 |
+
Tortoiseshell 0.6405 0.7803 0.7035 2258
|
| 63 |
+
Turkish Angora 0.6801 0.7524 0.7145 2258
|
| 64 |
+
Turkish Van 0.6508 0.8534 0.7385 2258
|
| 65 |
+
Tuxedo 0.5899 0.8344 0.6911 2258
|
| 66 |
|
| 67 |
+
accuracy 0.7239 108384
|
| 68 |
+
macro avg 0.7040 0.7239 0.7059 108384
|
| 69 |
+
weighted avg 0.7040 0.7239 0.7059 108384
|
| 70 |
```
|