Instructions to use microsoft/beit-large-patch16-384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/beit-large-patch16-384 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="microsoft/beit-large-patch16-384") 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("microsoft/beit-large-patch16-384") model = AutoModelForImageClassification.from_pretrained("microsoft/beit-large-patch16-384") - Notebooks
- Google Colab
- Kaggle
Commit ·
c1f9c8a
1
Parent(s): 0cb6a04
add config
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.0,
|
| 6 |
"drop_path_rate": 0.1,
|
|
@@ -2021,7 +2021,7 @@
|
|
| 2021 |
"num_hidden_layers": 24,
|
| 2022 |
"patch_size": 16,
|
| 2023 |
"torch_dtype": "float32",
|
| 2024 |
-
"transformers_version": "4.
|
| 2025 |
"use_absolute_position_embeddings": false,
|
| 2026 |
"use_mask_token": false,
|
| 2027 |
"use_mean_pooling": true,
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"BeitForImageClassification"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.0,
|
| 6 |
"drop_path_rate": 0.1,
|
|
|
|
| 2021 |
"num_hidden_layers": 24,
|
| 2022 |
"patch_size": 16,
|
| 2023 |
"torch_dtype": "float32",
|
| 2024 |
+
"transformers_version": "4.11.0.dev0",
|
| 2025 |
"use_absolute_position_embeddings": false,
|
| 2026 |
"use_mask_token": false,
|
| 2027 |
"use_mean_pooling": true,
|