fix mask shape bug
This commit is contained in:
@@ -14,7 +14,7 @@ Grounded SAM 2 does not introduce significant methodological changes compared to
|
|||||||
|
|
||||||
## Contents
|
## Contents
|
||||||
- [Installation](#installation)
|
- [Installation](#installation)
|
||||||
- [Grounded SAM 2 Demo](#grounded-sam-2-demo)
|
- [Grounded SAM 2 Demo](#grounded-sam-2-demos)
|
||||||
- [Grounded SAM 2 Image Demo](#grounded-sam-2-image-demo-with-grounding-dino)
|
- [Grounded SAM 2 Image Demo](#grounded-sam-2-image-demo-with-grounding-dino)
|
||||||
- [Grounded SAM 2 Image Demo (with Grounding DINO 1.5 & 1.6)](#grounded-sam-2-image-demo-with-grounding-dino-15--16)
|
- [Grounded SAM 2 Image Demo (with Grounding DINO 1.5 & 1.6)](#grounded-sam-2-image-demo-with-grounding-dino-15--16)
|
||||||
- [Grounded SAM 2 Video Object Tracking Demo](#grounded-sam-2-video-object-tracking-demo)
|
- [Grounded SAM 2 Video Object Tracking Demo](#grounded-sam-2-video-object-tracking-demo)
|
||||||
@@ -65,7 +65,7 @@ wget https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alp
|
|||||||
wget https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha2/groundingdino_swinb_cogcoor.pth
|
wget https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha2/groundingdino_swinb_cogcoor.pth
|
||||||
```
|
```
|
||||||
|
|
||||||
## Grounded SAM 2 Demo
|
## Grounded SAM 2 Demos
|
||||||
### Grounded SAM 2 Image Demo (with Grounding DINO)
|
### Grounded SAM 2 Image Demo (with Grounding DINO)
|
||||||
Note that `Grounding DINO` has already been supported in [Huggingface](https://huggingface.co/IDEA-Research/grounding-dino-tiny), so we provide two choices for running `Grounded SAM 2` model:
|
Note that `Grounding DINO` has already been supported in [Huggingface](https://huggingface.co/IDEA-Research/grounding-dino-tiny), so we provide two choices for running `Grounded SAM 2` model:
|
||||||
- Use huggingface API to inference Grounding DINO (which is simple and clear)
|
- Use huggingface API to inference Grounding DINO (which is simple and clear)
|
||||||
|
@@ -89,11 +89,7 @@ masks, scores, logits = sam2_predictor.predict(
|
|||||||
Post-process the output of the model to get the masks, scores, and logits for visualization
|
Post-process the output of the model to get the masks, scores, and logits for visualization
|
||||||
"""
|
"""
|
||||||
# convert the shape to (n, H, W)
|
# convert the shape to (n, H, W)
|
||||||
if masks.ndim == 3:
|
if masks.ndim == 4:
|
||||||
masks = masks[None]
|
|
||||||
scores = scores[None]
|
|
||||||
logits = logits[None]
|
|
||||||
elif masks.ndim == 4:
|
|
||||||
masks = masks.squeeze(1)
|
masks = masks.squeeze(1)
|
||||||
|
|
||||||
|
|
||||||
|
@@ -81,11 +81,7 @@ masks, scores, logits = sam2_predictor.predict(
|
|||||||
Post-process the output of the model to get the masks, scores, and logits for visualization
|
Post-process the output of the model to get the masks, scores, and logits for visualization
|
||||||
"""
|
"""
|
||||||
# convert the shape to (n, H, W)
|
# convert the shape to (n, H, W)
|
||||||
if masks.ndim == 3:
|
if masks.ndim == 4:
|
||||||
masks = masks[None]
|
|
||||||
scores = scores[None]
|
|
||||||
logits = logits[None]
|
|
||||||
elif masks.ndim == 4:
|
|
||||||
masks = masks.squeeze(1)
|
masks = masks.squeeze(1)
|
||||||
|
|
||||||
|
|
||||||
|
@@ -68,11 +68,7 @@ masks, scores, logits = sam2_predictor.predict(
|
|||||||
Post-process the output of the model to get the masks, scores, and logits for visualization
|
Post-process the output of the model to get the masks, scores, and logits for visualization
|
||||||
"""
|
"""
|
||||||
# convert the shape to (n, H, W)
|
# convert the shape to (n, H, W)
|
||||||
if masks.ndim == 3:
|
if masks.ndim == 4:
|
||||||
masks = masks[None]
|
|
||||||
scores = scores[None]
|
|
||||||
logits = logits[None]
|
|
||||||
elif masks.ndim == 4:
|
|
||||||
masks = masks.squeeze(1)
|
masks = masks.squeeze(1)
|
||||||
|
|
||||||
|
|
||||||
|
Reference in New Issue
Block a user