Update README.md
Browse files
README.md
CHANGED
|
@@ -13,11 +13,11 @@ datasets:
|
|
| 13 |
base_model:
|
| 14 |
- facebook/sam2-hiera-tiny
|
| 15 |
---
|
| 16 |
-
Model Card for culico-net-segm-v1-nano
|
| 17 |
|
| 18 |
-
culico-net-segm-v1-nano - instance segmentation model focused on segmenting mosquito specimens in images and videos. This model is a result of the CulicidaeLab project and was developed by fine-tuning the SAM2 (Segment Anything Model 2) architecture.
|
| 19 |
|
| 20 |
-
The culico-net-segm-v1-nano is based on SAM2's efficient Hiera-Tiny backbone and was specifically adapted for mosquito specimen segmentation using a dedicated dataset. This model can handle both image segmentation and video segmentation tasks with prompt-based interaction.
|
| 21 |
|
| 22 |
**Model Details:**
|
| 23 |
- **Model Type:** Instance segmentation / Mask generation
|
|
@@ -30,7 +30,7 @@ The culico-net-segm-v1-nano is based on SAM2's efficient Hiera-Tiny backbone and
|
|
| 30 |
- SAM 2: Segment Anything in Images and Videos: https://arxiv.org/abs/2408.00714
|
| 31 |
- Original GitHub Repository: https://github.com/facebookresearch/sam2
|
| 32 |
|
| 33 |
-
**Dataset:** The model was trained on the iloncka/mosquito-species-segmentation-dataset
|
| 34 |
|
| 35 |
**Pretrain Dataset:** ImageNet-1k, SA-1B (Segment Anything 1B dataset)
|
| 36 |
|
|
@@ -72,11 +72,11 @@ Refer to the [official SAM2 demo notebooks](https://github.com/facebookresearch/
|
|
| 72 |
|
| 73 |
**The CulicidaeLab Project:**
|
| 74 |
|
| 75 |
-
The culico-net-segm-v1-nano model is a component of the larger CulicidaeLab project. This project aims to provide a comprehensive suite of tools for mosquito monitoring and research. Other parts of the project include:
|
| 76 |
|
| 77 |
- **Related Models:**
|
| 78 |
- [iloncka/culico-net-cls-v1](https://huggingface.co/iloncka/culico-net-cls-v1) - Classification model
|
| 79 |
-
- [iloncka/culico-net-det-v1](https://huggingface.co/iloncka/culico-net-det-v1)
|
| 80 |
|
| 81 |
- **Datasets:**
|
| 82 |
- [iloncka/mosquito-species-detection-dataset](https://huggingface.co/datasets/iloncka/mosquito-species-detection-dataset)
|
|
@@ -93,7 +93,7 @@ The culico-net-segm-v1-nano model is a component of the larger CulicidaeLab proj
|
|
| 93 |
|
| 94 |
**Practical Applications:**
|
| 95 |
|
| 96 |
-
The culico-net-segm-v1-nano model and the broader CulicidaeLab project have several practical applications:
|
| 97 |
|
| 98 |
- **Precise Morphological Analysis:** Enables detailed examination of mosquito anatomical features for species identification and research.
|
| 99 |
- **Automated Specimen Measurement:** Can be used to automatically measure wing dimensions, body size, and other morphological characteristics.
|
|
@@ -103,7 +103,8 @@ The culico-net-segm-v1-nano model and the broader CulicidaeLab project have seve
|
|
| 103 |
|
| 104 |
**Acknowledgments:**
|
| 105 |
|
| 106 |
-
The development of CulicidaeLab is supported by a grant from the Foundation for Assistance to Small Innovative Enterprises (FASIE).
|
|
|
|
| 107 |
|
| 108 |
**Citation:**
|
| 109 |
|
|
|
|
| 13 |
base_model:
|
| 14 |
- facebook/sam2-hiera-tiny
|
| 15 |
---
|
| 16 |
+
Model Card for `culico-net-segm-v1-nano`
|
| 17 |
|
| 18 |
+
`culico-net-segm-v1-nano` - instance segmentation model focused on segmenting mosquito specimens in images and videos. This model is a result of the CulicidaeLab project and was developed by fine-tuning the SAM2 (Segment Anything Model 2) architecture.
|
| 19 |
|
| 20 |
+
The `culico-net-segm-v1-nano` is based on SAM2's efficient Hiera-Tiny backbone and was specifically adapted for mosquito specimen segmentation using a dedicated dataset. This model can handle both image segmentation and video segmentation tasks with prompt-based interaction.
|
| 21 |
|
| 22 |
**Model Details:**
|
| 23 |
- **Model Type:** Instance segmentation / Mask generation
|
|
|
|
| 30 |
- SAM 2: Segment Anything in Images and Videos: https://arxiv.org/abs/2408.00714
|
| 31 |
- Original GitHub Repository: https://github.com/facebookresearch/sam2
|
| 32 |
|
| 33 |
+
**Dataset:** The model was trained on the `iloncka/mosquito-species-segmentation-dataset`. This is one of a suite of datasets which also includes iloncka/mosquito-species-detection-dataset and iloncka/mosquito-species-classification-dataset. These datasets contain images of various mosquito species with detailed segmentation annotations, crucial for training accurate segmentation models.
|
| 34 |
|
| 35 |
**Pretrain Dataset:** ImageNet-1k, SA-1B (Segment Anything 1B dataset)
|
| 36 |
|
|
|
|
| 72 |
|
| 73 |
**The CulicidaeLab Project:**
|
| 74 |
|
| 75 |
+
The `culico-net-segm-v1-nano model` is a component of the larger `CulicidaeLab` project. This project aims to provide a comprehensive suite of tools for mosquito monitoring and research. Other parts of the project include:
|
| 76 |
|
| 77 |
- **Related Models:**
|
| 78 |
- [iloncka/culico-net-cls-v1](https://huggingface.co/iloncka/culico-net-cls-v1) - Classification model
|
| 79 |
+
- [iloncka/culico-net-det-v1](https://huggingface.co/iloncka/culico-net-det-v1) - Detection model
|
| 80 |
|
| 81 |
- **Datasets:**
|
| 82 |
- [iloncka/mosquito-species-detection-dataset](https://huggingface.co/datasets/iloncka/mosquito-species-detection-dataset)
|
|
|
|
| 93 |
|
| 94 |
**Practical Applications:**
|
| 95 |
|
| 96 |
+
The `culico-net-segm-v1-nano` model and the broader `CulicidaeLab` project have several practical applications:
|
| 97 |
|
| 98 |
- **Precise Morphological Analysis:** Enables detailed examination of mosquito anatomical features for species identification and research.
|
| 99 |
- **Automated Specimen Measurement:** Can be used to automatically measure wing dimensions, body size, and other morphological characteristics.
|
|
|
|
| 103 |
|
| 104 |
**Acknowledgments:**
|
| 105 |
|
| 106 |
+
The development of `CulicidaeLab` is supported by a grant from the [Foundation for Assistance to Small Innovative Enterprises (FASIE)]((https://fasie.ru/)).
|
| 107 |
+
|
| 108 |
|
| 109 |
**Citation:**
|
| 110 |
|