Instructions to use facebook/mask2former-swin-small-coco-instance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mask2former-swin-small-coco-instance with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="facebook/mask2former-swin-small-coco-instance")# Load model directly from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-small-coco-instance") model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-small-coco-instance") - Inference
- Notebooks
- Google Colab
- Kaggle
Upload Mask2FormerForUniversalSegmentation
Browse files- config.json +2 -1
config.json
CHANGED
|
@@ -2113,9 +2113,10 @@
|
|
| 2113 |
"decoder_layers": 10,
|
| 2114 |
"dice_weight": 5.0,
|
| 2115 |
"dim_feedforward": 2048,
|
| 2116 |
-
"dropout": 0.
|
| 2117 |
"encoder_feedforward_dim": 1024,
|
| 2118 |
"encoder_layers": 6,
|
|
|
|
| 2119 |
"enforce_input_projection": false,
|
| 2120 |
"feature_size": 256,
|
| 2121 |
"feature_strides": [
|
|
|
|
| 2113 |
"decoder_layers": 10,
|
| 2114 |
"dice_weight": 5.0,
|
| 2115 |
"dim_feedforward": 2048,
|
| 2116 |
+
"dropout": 0.0,
|
| 2117 |
"encoder_feedforward_dim": 1024,
|
| 2118 |
"encoder_layers": 6,
|
| 2119 |
+
"enforce_input_proj": false,
|
| 2120 |
"enforce_input_projection": false,
|
| 2121 |
"feature_size": 256,
|
| 2122 |
"feature_strides": [
|