Instructions to use microsoft/swinv2-base-patch4-window8-256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/swinv2-base-patch4-window8-256 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="microsoft/swinv2-base-patch4-window8-256") 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/swinv2-base-patch4-window8-256") model = AutoModelForImageClassification.from_pretrained("microsoft/swinv2-base-patch4-window8-256") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
f5f9e81
1
Parent(s): 52dda77
Update weights
Browse files- config.json +7 -1
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -2033,9 +2033,15 @@
|
|
| 2033 |
"num_layers": 4,
|
| 2034 |
"patch_size": 4,
|
| 2035 |
"path_norm": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2036 |
"qkv_bias": true,
|
| 2037 |
"torch_dtype": "float32",
|
| 2038 |
-
"transformers_version": "4.
|
| 2039 |
"use_absolute_embeddings": false,
|
| 2040 |
"window_size": 8
|
| 2041 |
}
|
|
|
|
| 2033 |
"num_layers": 4,
|
| 2034 |
"patch_size": 4,
|
| 2035 |
"path_norm": true,
|
| 2036 |
+
"pretrained_window_sizes": [
|
| 2037 |
+
0,
|
| 2038 |
+
0,
|
| 2039 |
+
0,
|
| 2040 |
+
0
|
| 2041 |
+
],
|
| 2042 |
"qkv_bias": true,
|
| 2043 |
"torch_dtype": "float32",
|
| 2044 |
+
"transformers_version": "4.21.0.dev0",
|
| 2045 |
"use_absolute_embeddings": false,
|
| 2046 |
"window_size": 8
|
| 2047 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7aeded1e50fc6e9dca604336e537c429d5d3832947d630a2edef7b39922de9e
|
| 3 |
+
size 351833871
|