Instructions to use l45k/lenet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use l45k/lenet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="l45k/lenet", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForImageClassification model = AutoModelForImageClassification.from_pretrained("l45k/lenet", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- preprocessor_config.json +13 -6
preprocessor_config.json
CHANGED
|
@@ -1,8 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": false,
|
| 5 |
+
"do_resize": false,
|
| 6 |
+
"image_mean": 0.1307,
|
| 7 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 8 |
+
"image_std": 0.3081,
|
| 9 |
+
"resample": null,
|
| 10 |
+
"rescale_factor": 0.00392156862745098,
|
| 11 |
+
"size": {
|
| 12 |
+
"height": 28,
|
| 13 |
+
"width": 28
|
| 14 |
+
}
|
| 15 |
}
|