Instructions to use Harsha901/swinv2-tiny-human-pose-classification-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Harsha901/swinv2-tiny-human-pose-classification-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Harsha901/swinv2-tiny-human-pose-classification-model") 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("Harsha901/swinv2-tiny-human-pose-classification-model") model = AutoModelForImageClassification.from_pretrained("Harsha901/swinv2-tiny-human-pose-classification-model") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- preprocessor_config.json +30 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": null,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.485,
|
| 13 |
+
0.456,
|
| 14 |
+
0.406
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "ViTImageProcessorFast",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.229,
|
| 19 |
+
0.224,
|
| 20 |
+
0.225
|
| 21 |
+
],
|
| 22 |
+
"input_data_format": null,
|
| 23 |
+
"resample": 3,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"return_tensors": null,
|
| 26 |
+
"size": {
|
| 27 |
+
"height": 256,
|
| 28 |
+
"width": 256
|
| 29 |
+
}
|
| 30 |
+
}
|