Instructions to use dima806/mammals_45_types_image_classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dima806/mammals_45_types_image_classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dima806/mammals_45_types_image_classification") 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/mammals_45_types_image_classification") model = AutoModelForImageClassification.from_pretrained("dima806/mammals_45_types_image_classification") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,62 @@ metrics:
|
|
| 4 |
- accuracy
|
| 5 |
- f1
|
| 6 |
---
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- accuracy
|
| 5 |
- f1
|
| 6 |
---
|
| 7 |
+
Returns a common mammal type given an image.
|
| 8 |
+
|
| 9 |
+
See https://www.kaggle.com/code/dima806/mammals-45-types-image-classification-vit for more details.
|
| 10 |
+
|
| 11 |
+
```
|
| 12 |
+
Classification report:
|
| 13 |
+
|
| 14 |
+
precision recall f1-score support
|
| 15 |
+
|
| 16 |
+
african_elephant 1.0000 1.0000 1.0000 71
|
| 17 |
+
alpaca 0.9200 0.9718 0.9452 71
|
| 18 |
+
american_bison 1.0000 1.0000 1.0000 71
|
| 19 |
+
anteater 0.9853 0.9437 0.9640 71
|
| 20 |
+
arctic_fox 0.9286 0.9155 0.9220 71
|
| 21 |
+
armadillo 0.9726 1.0000 0.9861 71
|
| 22 |
+
baboon 0.9718 0.9718 0.9718 71
|
| 23 |
+
badger 1.0000 0.9718 0.9857 71
|
| 24 |
+
blue_whale 0.9710 0.9437 0.9571 71
|
| 25 |
+
brown_bear 0.9722 0.9859 0.9790 71
|
| 26 |
+
camel 0.9861 1.0000 0.9930 71
|
| 27 |
+
dolphin 0.8974 0.9859 0.9396 71
|
| 28 |
+
giraffe 0.9857 0.9718 0.9787 71
|
| 29 |
+
groundhog 0.9714 0.9577 0.9645 71
|
| 30 |
+
highland_cattle 0.9859 0.9859 0.9859 71
|
| 31 |
+
horse 1.0000 0.9859 0.9929 71
|
| 32 |
+
jackal 0.9577 0.9444 0.9510 72
|
| 33 |
+
kangaroo 0.8415 0.9583 0.8961 72
|
| 34 |
+
koala 0.9589 0.9859 0.9722 71
|
| 35 |
+
manatee 0.9861 0.9861 0.9861 72
|
| 36 |
+
mongoose 0.9483 0.7746 0.8527 71
|
| 37 |
+
mountain_goat 0.9855 0.9577 0.9714 71
|
| 38 |
+
opossum 1.0000 0.9577 0.9784 71
|
| 39 |
+
orangutan 1.0000 1.0000 1.0000 71
|
| 40 |
+
otter 1.0000 0.9577 0.9784 71
|
| 41 |
+
polar_bear 0.9706 0.9296 0.9496 71
|
| 42 |
+
porcupine 1.0000 0.9722 0.9859 72
|
| 43 |
+
red_panda 0.9718 0.9718 0.9718 71
|
| 44 |
+
rhinoceros 0.9859 0.9859 0.9859 71
|
| 45 |
+
sea_lion 0.7600 0.8028 0.7808 71
|
| 46 |
+
seal 0.8308 0.7500 0.7883 72
|
| 47 |
+
snow_leopard 1.0000 1.0000 1.0000 71
|
| 48 |
+
squirrel 0.9444 0.9577 0.9510 71
|
| 49 |
+
sugar_glider 0.8554 1.0000 0.9221 71
|
| 50 |
+
tapir 1.0000 1.0000 1.0000 71
|
| 51 |
+
vampire_bat 1.0000 0.9861 0.9930 72
|
| 52 |
+
vicuna 1.0000 0.8873 0.9403 71
|
| 53 |
+
walrus 0.9342 0.9861 0.9595 72
|
| 54 |
+
warthog 0.9571 0.9437 0.9504 71
|
| 55 |
+
water_buffalo 0.9333 0.9859 0.9589 71
|
| 56 |
+
weasel 0.9583 0.9583 0.9583 72
|
| 57 |
+
wildebeest 0.9577 0.9444 0.9510 72
|
| 58 |
+
wombat 0.8947 0.9577 0.9252 71
|
| 59 |
+
yak 1.0000 0.9437 0.9710 71
|
| 60 |
+
zebra 0.9595 1.0000 0.9793 71
|
| 61 |
+
|
| 62 |
+
accuracy 0.9572 3204
|
| 63 |
+
macro avg 0.9587 0.9573 0.9572 3204
|
| 64 |
+
weighted avg 0.9586 0.9572 0.9572 3204
|
| 65 |
+
```
|