HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.2.83 fix SAM2 CLI usage (#15871)

Browse source 
Signed-off-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher 2024-08-28 23:11:53 +02:00 • committed by GitHub
parent f8c5bf7eec
commit a222b94897
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 44 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

56
docs/en/models/sam-2.md
View file

@ -168,47 +168,45 @@ SAM 2 can be utilized across a broad spectrum of tasks, including real-time vide
- This example demonstrates how SAM 2 can be used to segment the entire content of an image or video if no prompts (bboxes/points/masks) are provided. - This example demonstrates how SAM 2 can be used to segment the entire content of an image or video if no prompts (bboxes/points/masks) are provided.
## SAM comparison vs YOLOv8 ## SAM 2 comparison vs YOLOv8
Here we compare Meta's smallest SAM model, SAM-b, with Ultralytics smallest segmentation model, [YOLOv8n-seg](../tasks/segment.md): Here we compare Meta's smallest SAM 2 model, SAM2-t, with Ultralytics smallest segmentation model, [YOLOv8n-seg](../tasks/segment.md):
| Model | Size | Parameters | Speed (CPU) | | Model | Size<br><sup>(MB)</sup> | Parameters<br><sup>(M)</sup> | Speed (CPU)<br><sup>(ms/im)</sup> |
| ---------------------------------------------- | -------------------------- | ---------------------- | -------------------------- | | ---------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- |
| Meta's SAM-b | 358 MB | 94.7 M | 51096 ms/im | | [Meta SAM-b](sam.md) | 375 | 93.7 | 161440 |
| [MobileSAM](mobile-sam.md) | 40.7 MB | 10.1 M | 46122 ms/im | | Meta SAM2-b | 162 | 80.8 | 121923 |
| [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 MB | 11.8 M | 115 ms/im | | Meta SAM2-t | 78.1 | 38.9 | 85155 |
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7 MB** (53.4x smaller) | **3.4 M** (27.9x less) | **59 ms/im** (866x faster) | | [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 98543 |
| [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 | 11.8 | 140 |
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7** (11.7x smaller) | **3.4** (11.4x less) | **79.5** (1071x faster) |
This comparison shows the order-of-magnitude differences in the model sizes and speeds between models. Whereas SAM presents unique capabilities for automatic segmenting, it is not a direct competitor to YOLOv8 segment models, which are smaller, faster and more efficient. This comparison shows the order-of-magnitude differences in the model sizes and speeds between models. Whereas SAM presents unique capabilities for automatic segmenting, it is not a direct competitor to YOLOv8 segment models, which are smaller, faster and more efficient.
Tests run on a 2023 Apple M2 Macbook with 16GB of RAM. To reproduce this test: Tests run on a 2023 Apple M2 Macbook with 16GB of RAM using `torch==2.3.1` and `ultralytics==8.3.82`. To reproduce this test:
!!! Example !!! Example
=== "Python" === "Python"
```python ```python
from ultralytics import SAM, YOLO, FastSAM from ultralytics import ASSETS, SAM, YOLO, FastSAM
# Profile SAM-b # Profile SAM2-t, SAM2-b, SAM-b, MobileSAM
model = SAM("sam_b.pt") for file in ["sam_b.pt", "sam2_b.pt", "sam2_t.pt", "mobile_sam.pt"]:
model.info() model = SAM(file)
model("ultralytics/assets") model.info()
model(ASSETS)
# Profile MobileSAM
model = SAM("mobile_sam.pt")
model.info()
model("ultralytics/assets")
# Profile FastSAM-s # Profile FastSAM-s
model = FastSAM("FastSAM-s.pt") model = FastSAM("FastSAM-s.pt")
model.info() model.info()
model("ultralytics/assets") model(ASSETS)
# Profile YOLOv8n-seg # Profile YOLOv8n-seg
model = YOLO("yolov8n-seg.pt") model = YOLO("yolov8n-seg.pt")
model.info() model.info()
model("ultralytics/assets") model(ASSETS)
``` ```
## Auto-Annotation: Efficient Dataset Creation ## Auto-Annotation: Efficient Dataset Creation
@ -331,11 +329,13 @@ This mechanism ensures continuity even when objects are temporarily obscured or
SAM 2 and Ultralytics YOLOv8 serve different purposes and excel in different areas. While SAM 2 is designed for comprehensive object segmentation with advanced features like zero-shot generalization and real-time performance, YOLOv8 is optimized for speed and efficiency in object detection and segmentation tasks. Here's a comparison: SAM 2 and Ultralytics YOLOv8 serve different purposes and excel in different areas. While SAM 2 is designed for comprehensive object segmentation with advanced features like zero-shot generalization and real-time performance, YOLOv8 is optimized for speed and efficiency in object detection and segmentation tasks. Here's a comparison:
| Model | Size | Parameters | Speed (CPU) | | Model | Size<br><sup>(MB)</sup> | Parameters<br><sup>(M)</sup> | Speed (CPU)<br><sup>(ms/im)</sup> |
| ---------------------------------------------- | -------------------------- | ---------------------- | -------------------------- | | ---------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- |
| Meta's SAM-b | 358 MB | 94.7 M | 51096 ms/im | | [Meta SAM-b](sam.md) | 375 | 93.7 | 161440 |
| [MobileSAM](mobile-sam.md) | 40.7 MB | 10.1 M | 46122 ms/im | | Meta SAM2-b | 162 | 80.8 | 121923 |
| [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 MB | 11.8 M | 115 ms/im | | Meta SAM2-t | 78.1 | 38.9 | 85155 |
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7 MB** (53.4x smaller) | **3.4 M** (27.9x less) | **59 ms/im** (866x faster) | | [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 98543 |
| [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 | 11.8 | 140 |
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7** (11.7x smaller) | **3.4** (11.4x less) | **79.5** (1071x faster) |
For more details, see the [SAM comparison vs YOLOv8](#sam-comparison-vs-yolov8) section. For more details, see the [SAM 2 comparison vs YOLOv8](#sam-2-comparison-vs-yolov8) section.

32
docs/en/models/sam.md
View file

@ -138,12 +138,12 @@ The Segment Anything Model can be employed for a multitude of downstream tasks t
Here we compare Meta's smallest SAM model, SAM-b, with Ultralytics smallest segmentation model, [YOLOv8n-seg](../tasks/segment.md): Here we compare Meta's smallest SAM model, SAM-b, with Ultralytics smallest segmentation model, [YOLOv8n-seg](../tasks/segment.md):
| Model | Size | Parameters | Speed (CPU) | | Model | Size<br><sup>(MB)</sup> | Parameters<br><sup>(M)</sup> | Speed (CPU)<br><sup>(ms/im)</sup> |
| ---------------------------------------------- | -------------------------- | ---------------------- | -------------------------- | | ---------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- |
| Meta's SAM-b | 358 MB | 94.7 M | 51096 ms/im | | Meta SAM-b | 358 | 94.7 | 51096 |
| [MobileSAM](mobile-sam.md) | 40.7 MB | 10.1 M | 46122 ms/im | | [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 46122 |
| [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 MB | 11.8 M | 115 ms/im | | [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 | 11.8 | 115 |
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7 MB** (53.4x smaller) | **3.4 M** (27.9x less) | **59 ms/im** (866x faster) | | Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7** (53.4x smaller) | **3.4** (27.9x less) | **59** (866x faster) |
This comparison shows the order-of-magnitude differences in the model sizes and speeds between models. Whereas SAM presents unique capabilities for automatic segmenting, it is not a direct competitor to YOLOv8 segment models, which are smaller, faster and more efficient. This comparison shows the order-of-magnitude differences in the model sizes and speeds between models. Whereas SAM presents unique capabilities for automatic segmenting, it is not a direct competitor to YOLOv8 segment models, which are smaller, faster and more efficient.
@ -154,27 +154,23 @@ Tests run on a 2023 Apple M2 Macbook with 16GB of RAM. To reproduce this test:
=== "Python" === "Python"
```python ```python
from ultralytics import SAM, YOLO, FastSAM from ultralytics import ASSETS, SAM, YOLO, FastSAM
# Profile SAM-b # Profile SAM-b, MobileSAM
model = SAM("sam_b.pt") for file in ["sam_b.pt", "mobile_sam.pt"]:
model.info() model = SAM(file)
model("ultralytics/assets") model.info()
model(ASSETS)
# Profile MobileSAM
model = SAM("mobile_sam.pt")
model.info()
model("ultralytics/assets")
# Profile FastSAM-s # Profile FastSAM-s
model = FastSAM("FastSAM-s.pt") model = FastSAM("FastSAM-s.pt")
model.info() model.info()
model("ultralytics/assets") model(ASSETS)
# Profile YOLOv8n-seg # Profile YOLOv8n-seg
model = YOLO("yolov8n-seg.pt") model = YOLO("yolov8n-seg.pt")
model.info() model.info()
model("ultralytics/assets") model(ASSETS)
``` ```
## Auto-Annotation: A Quick Path to Segmentation Datasets ## Auto-Annotation: A Quick Path to Segmentation Datasets

2
ultralytics/__init__.py
View file

@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license # Ultralytics YOLO 🚀, AGPL-3.0 license
__version__ = "8.2.82" __version__ = "8.2.83"
import os import os

6
ultralytics/cfg/__init__.py
View file

@ -793,11 +793,7 @@ def entrypoint(debug=""):
from ultralytics import FastSAM from ultralytics import FastSAM
model = FastSAM(model) model = FastSAM(model)
elif "sam2" in stem: elif "sam_" in stem or "sam2_" in stem:
from ultralytics import SAM2
model = SAM2(model)
elif "sam" in stem:
from ultralytics import SAM from ultralytics import SAM
model = SAM(model) model = SAM(model)