Add SAM2 + Remove YOLOv5

.github/workflows/release.yml

@@ -74,7 +74,7 @@ jobs:
     - uses: conda-incubator/setup-miniconda@v2
       with:
         auto-update-conda: true
-        python-version: '3.7'
+        python-version: '3.10'
 
     - name: Set preferred device to CPU
       shell: bash -l {0}
@@ -169,7 +169,7 @@ jobs:
     - uses: conda-incubator/setup-miniconda@v2
       with:
         auto-update-conda: true
-        python-version: '3.7'
+        python-version: '3.10'
 
     - name: Set preferred device to GPU
       shell: bash -l {0}

README.md

@@ -33,7 +33,7 @@
 **Features:**
 
 - [x] Image annotation for polygon, rectangle, circle, line and point.
-- [x] Auto-labeling with YOLOv5 and Segment Anything.
+- [x] Auto-labeling YOLOv8, Segment Anything (SAM, SAM2).
 - [x] Text detection, recognition and KIE (Key Information Extraction) labeling.
 - [x] Multiple languages availables: English, Vietnamese, Chinese.
 
@@ -49,7 +49,7 @@
 
 ### 2. Install from Pypi
 
-- Requirements: Python >= 3.8, <= 3.12. Recommended: Python 3.12.
+- Requirements: Python 3.10+. Recommended: Python 3.12.
 - Recommended: [Miniconda/Anaconda](https://docs.conda.io/en/latest/miniconda.html).
 
 - Create environment:
@@ -126,4 +126,4 @@ If you want to contribute to **AnyLabeling**, please read [Contribution Guidelin
 
 - Labeling UI built with ideas and components from [LabelImg](https://github.com/heartexlabs/labelImg), [LabelMe](https://github.com/wkentaro/labelme).
 - Auto-labeling with [Segment Anything Models](https://segment-anything.com/), [MobileSAM](https://github.com/ChaoningZhang/MobileSAM).
-- Auto-labeling with [YOLOv5](https://github.com/ultralytics/yolov5), [YOLOv8](https://github.com/ultralytics/ultralytics).
+- Auto-labeling with [YOLOv8](https://github.com/ultralytics/ultralytics).

anylabeling/app_info.py

@@ -1,4 +1,4 @@
 __appname__ = "AnyLabeling"
 __appdescription__ = "Effortless data labeling with AI support"
-__version__ = "0.3.3"
+__version__ = "0.4.0"
 __preferred_device__ = "CPU"  # GPU or CPU

anylabeling/configs/auto_labeling/models.yaml

@@ -1,3 +1,15 @@
+- name: "sam2_hiera_tiny_20240803"
+  display_name: Segment Anything 2 (Hiera-Tiny)
+  download_url: https://huggingface.co/vietanhdev/segment-anything-2-onnx-models/resolve/main/sam2_hiera_tiny.zip
+- name: "sam2_hiera_small_20240803"
+  display_name: Segment Anything 2 (Hiera-Small)
+  download_url: https://huggingface.co/vietanhdev/segment-anything-2-onnx-models/resolve/main/sam2_hiera_small.zip
+- name: "sam2_hiera_base_plus_20240803"
+  display_name: Segment Anything 2 (Hiera-Base+)
+  download_url: https://huggingface.co/vietanhdev/segment-anything-2-onnx-models/resolve/main/sam2_hiera_base_plus.zip
+- name: "sam2_hiera_large_20240803"
+  display_name: Segment Anything 2 (Hiera-Large)
+  download_url: https://huggingface.co/vietanhdev/segment-anything-2-onnx-models/resolve/main/sam2_hiera_large.zip
 - name: "mobile_sam_20230629"
   display_name: Segment Anything (MobileSAM)
   download_url: https://huggingface.co/vietanhdev/segment-anything-onnx-models/resolve/main/mobile_sam_20230629.zip
@@ -19,22 +31,6 @@
 - name: "sam_vit_h_4b8939_quant"
   display_name: Segment Anything (ViT-H Quant)
   download_url: https://huggingface.co/vietanhdev/segment-anything-onnx-models/resolve/main/sam_vit_h_4b8939_quant.zip
-- name: "yolov5n-r20230415"
-  display_name: YOLOv5n
-  download_url: https://github.com/vietanhdev/anylabeling-assets/releases/download/v0.4.0/yolov5n-r20230415.zip
-- name: "yolov5s-r20230415"
-  display_name: YOLOv5s
-  download_url: https://github.com/vietanhdev/anylabeling-assets/releases/download/v0.4.0/yolov5s-r20230415.zip
-- name: "yolov5m-r20230415"
-  display_name: YOLOv5m
-  download_url: https://github.com/vietanhdev/anylabeling-assets/releases/download/v0.4.0/yolov5m-r20230415.zip
-- name: "yolov5l-r20230415"
-  display_name: YOLOv5l
-  download_url: https://github.com/vietanhdev/anylabeling-assets/releases/download/v0.4.0/yolov5l-r20230415.zip
-- name: "yolov5x-r20230415"
-  display_name: YOLOv5x
-  download_url: https://github.com/vietanhdev/anylabeling-assets/releases/download/v0.4.0/yolov5x-r20230415.zip
-- name: "yolov8n-r20230415"
   display_name: YOLOv8n
   download_url: https://github.com/vietanhdev/anylabeling-assets/releases/download/v0.4.0/yolov8n-r20230415.zip
 - name: "yolov8s-r20230415"