Instructions to use Xrenya/pvt-tiny-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Xrenya/pvt-tiny-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Xrenya/pvt-tiny-224") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("Xrenya/pvt-tiny-224") model = AutoModelForImageClassification.from_pretrained("Xrenya/pvt-tiny-224", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -37,6 +37,7 @@
|
|
| 37 |
],
|
| 38 |
"num_channels": 3,
|
| 39 |
"num_encoder_blocks": 4,
|
|
|
|
| 40 |
"patch_sizes": [
|
| 41 |
4,
|
| 42 |
2,
|
|
@@ -44,7 +45,6 @@
|
|
| 44 |
2
|
| 45 |
],
|
| 46 |
"reshape_last_stage": true,
|
| 47 |
-
"semantic_loss_ignore_index": 255,
|
| 48 |
"sr_ratios": [
|
| 49 |
8,
|
| 50 |
4,
|
|
|
|
| 37 |
],
|
| 38 |
"num_channels": 3,
|
| 39 |
"num_encoder_blocks": 4,
|
| 40 |
+
"num_labels": 1000,
|
| 41 |
"patch_sizes": [
|
| 42 |
4,
|
| 43 |
2,
|
|
|
|
| 45 |
2
|
| 46 |
],
|
| 47 |
"reshape_last_stage": true,
|
|
|
|
| 48 |
"sr_ratios": [
|
| 49 |
8,
|
| 50 |
4,
|