Skip to content

Commit

Permalink
[Feature] Support GroundingSAM2 model
Browse files Browse the repository at this point in the history
  • Loading branch information
CVHub520 committed Aug 6, 2024
1 parent 7f207fe commit b242f15
Show file tree
Hide file tree
Showing 12 changed files with 729 additions and 3 deletions.
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,8 @@
- Aug. 2024:
- 🤗 Pre-release the latest version [2.4.0](https://github.com/CVHub520/X-AnyLabeling/releases/tag/v2.4.0) 🤗
- ✨✨✨ Support [Segment-Anything-2](https://github.com/facebookresearch/segment-anything-2) model! (Recommended)
- 👏👏👏 Support lightweight model for Japanese recognition.
- 👏👏👏 Support [Grounding-SAM2](./docs/en/model_zoo.md) model.
- Support lightweight model for Japanese recognition.
- Jul. 2024:
- Add PPOCR-Recognition and KIE import/export functionality for training PP-OCR task.
- Add ODVG import/export functionality for training grounding task.
Expand Down
3 changes: 2 additions & 1 deletion README_zh-CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,8 @@
- 2024年8月:
- 🤗 预发布[X-AnyLabeling v2.4.0](https://github.com/CVHub520/X-AnyLabeling/releases/tag/v2.4.0)最新版本 🤗
- ✨✨✨ 支持[Segment-Anything-2](https://github.com/facebookresearch/segment-anything-2)模型。
- 👏👏👏 支持[日文字符识别](./anylabeling/configs/auto_labeling/japan_ppocr.yaml)模型。
- 👏👏👏 支持[Grounding-SAM2](./docs/zh_cn/model_zoo.md)模型。
- 支持[日文字符识别](./anylabeling/configs/auto_labeling/japan_ppocr.yaml)模型。
- 2024年7月:
- 新增 PPOCR 识别和关键信息提取标签导入/导出功能。
- 新增 ODVG 标签导入/导出功能,以支持 Grounding 模型训练。
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
type: grounding_sam2
name: groundingdino_swint_sam2_large-r20240806
display_name: GroundingSAM2
# Grounding-DINO (swint)
model_type: groundingdino_swint_ogc
model_path: https://github.com/CVHub520/X-AnyLabeling/releases/download/v1.0.0/groundingdino_swint_ogc_quant.onnx
input_width: 1200
input_height: 800
box_threshold: 0.3
text_threshold: 0.25
# Segment-Anything-2 (large)
encoder_model_path: https://github.com/CVHub520/X-AnyLabeling/releases/download/v2.4.0/sam2_hiera_large.encoder.onnx
decoder_model_path: https://github.com/CVHub520/X-AnyLabeling/releases/download/v2.4.0/sam2_hiera_large.decoder.onnx
2 changes: 2 additions & 0 deletions anylabeling/configs/auto_labeling/models.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,8 @@
config_file: ":/groundingdino_swinb_attn_fuse_sam_hq_vit_l_quant.yaml"
- model_name: "groundingdino_swint_ogc_quant-r20231024"
config_file: ":/groundingdino_swint_ogc_quant.yaml"
- model_name: "groundingdino_swint_sam2_large-r20240806"
config_file: ":/groundingdino_swint_sam2_large.yaml"
- model_name: "internimage_l_22kto1k_384-r20230520"
config_file: ":/internimage_l_22kto1k_384.yaml"
- model_name: "lvm_sam_ssk_buid_vit_b-r20230810"
Expand Down
1 change: 1 addition & 0 deletions anylabeling/services/auto_labeling/grounding_sam.py
Original file line number Diff line number Diff line change
Expand Up @@ -224,6 +224,7 @@ class Meta:
]
widgets = [
"edit_text",
"button_send",
"output_label",
"output_select_combobox",
"button_add_point",
Expand Down
Loading

0 comments on commit b242f15

Please sign in to comment.