From 97cdda17b00afe4955479126ffaf878e2e2e8c43 Mon Sep 17 00:00:00 2001 From: root Date: Thu, 8 Aug 2024 02:40:11 +0000 Subject: [PATCH 1/2] Signed-off-by: root add centermask2 pytorch model link #IAINBO add centermask2 pytorch model --- cv/detection/centermask2/pytorch/README.md | 69 ++++++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 cv/detection/centermask2/pytorch/README.md diff --git a/cv/detection/centermask2/pytorch/README.md b/cv/detection/centermask2/pytorch/README.md new file mode 100644 index 000000000..aa8a69c23 --- /dev/null +++ b/cv/detection/centermask2/pytorch/README.md @@ -0,0 +1,69 @@ +# [CenterMask](https://arxiv.org/abs/1911.06667)2 + +[[`CenterMask(original code)`](https://github.com/youngwanLEE/CenterMask)][[`vovnet-detectron2`](https://github.com/youngwanLEE/vovnet-detectron2)][[`arxiv`](https://arxiv.org/abs/1911.06667)] [[`BibTeX`](#CitingCenterMask)] + +**CenterMask2** is an upgraded implementation on top of [detectron2](https://github.com/facebookresearch/detectron2) beyond original [CenterMask](https://github.com/youngwanLEE/CenterMask) based on [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark). + +> **[CenterMask : Real-Time Anchor-Free Instance Segmentation](https://arxiv.org/abs/1911.06667) (CVPR 2020)**
+> [Youngwan Lee](https://github.com/youngwanLEE) and Jongyoul Park
+> Electronics and Telecommunications Research Institute (ETRI)
+> pre-print : https://arxiv.org/abs/1911.06667 + + +
+ +
+ + + +## Installation +All you need to use centermask2 is [detectron2](https://github.com/facebookresearch/detectron2). It's easy! +you just install [detectron2](https://github.com/facebookresearch/detectron2) following [INSTALL.md](https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md). +Prepare for coco dataset following [this instruction](https://github.com/facebookresearch/detectron2/tree/master/datasets). +```bash +git clone https://github.com/facebookresearch/detectron2.git +python3 -m pip install -e detectron2 +git clone https://github.com/youngwanLEE/centermask2.git +cd centermask2 +``` + +## Step 2: Preparing datasets + +Go to visit [COCO official website](https://cocodataset.org/#download), then select the COCO dataset you want to download. + +Take coco2017 dataset as an example, specify `/path/to/coco2017` to your COCO path in later training process, the unzipped dataset path structure sholud look like: + +```bash +coco2017 +├── annotations +│ ├── instances_train2017.json +│ ├── instances_val2017.json +│ └── ... +├── train2017 +│ ├── 000000000009.jpg +│ ├── 000000000025.jpg +│ └── ... +├── val2017 +│ ├── 000000000139.jpg +│ ├── 000000000285.jpg +│ └── ... +├── train2017.txt +├── val2017.txt +└── ... +``` + +```bash +mkdir -p /datasets/ +ln -s /path/to/coco2017 /datasets/ +``` + + + +To train a model, run +For example, to launch CenterMask training with VoVNetV2-39 backbone on 8 GPUs, +one should execute: +```bash +cd centermask2 +python3 train_net.py --config-file "configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml" --num-gpus 8 +``` + -- Gitee From c007e05a4f9dd935f8bc911d07ea3a68bd39a753 Mon Sep 17 00:00:00 2001 From: majorli Date: Tue, 13 Aug 2024 10:12:36 +0800 Subject: [PATCH 2/2] format README of centermask2 model Signed-off-by: majorli --- cv/detection/centermask2/pytorch/README.md | 33 ++++++++-------------- 1 file changed, 12 insertions(+), 21 deletions(-) diff --git a/cv/detection/centermask2/pytorch/README.md b/cv/detection/centermask2/pytorch/README.md index aa8a69c23..8938a8254 100644 --- a/cv/detection/centermask2/pytorch/README.md +++ b/cv/detection/centermask2/pytorch/README.md @@ -1,30 +1,17 @@ -# [CenterMask](https://arxiv.org/abs/1911.06667)2 +# CenterMask2 -[[`CenterMask(original code)`](https://github.com/youngwanLEE/CenterMask)][[`vovnet-detectron2`](https://github.com/youngwanLEE/vovnet-detectron2)][[`arxiv`](https://arxiv.org/abs/1911.06667)] [[`BibTeX`](#CitingCenterMask)] +CenterMask2 is an upgraded implementation on top of detectron2 beyond original CenterMask based on maskrcnn-benchmark. -**CenterMask2** is an upgraded implementation on top of [detectron2](https://github.com/facebookresearch/detectron2) beyond original [CenterMask](https://github.com/youngwanLEE/CenterMask) based on [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark). +## Step 1: Installation -> **[CenterMask : Real-Time Anchor-Free Instance Segmentation](https://arxiv.org/abs/1911.06667) (CVPR 2020)**
-> [Youngwan Lee](https://github.com/youngwanLEE) and Jongyoul Park
-> Electronics and Telecommunications Research Institute (ETRI)
-> pre-print : https://arxiv.org/abs/1911.06667 +All you need to use centermask2 is [detectron2](https://github.com/facebookresearch/detectron2). It's easy! +you just install [detectron2](https://github.com/facebookresearch/detectron2) following [INSTALL.md](https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md). -
- -
- - - -## Installation -All you need to use centermask2 is [detectron2](https://github.com/facebookresearch/detectron2). It's easy! -you just install [detectron2](https://github.com/facebookresearch/detectron2) following [INSTALL.md](https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md). -Prepare for coco dataset following [this instruction](https://github.com/facebookresearch/detectron2/tree/master/datasets). ```bash +# Install detectron2 git clone https://github.com/facebookresearch/detectron2.git python3 -m pip install -e detectron2 -git clone https://github.com/youngwanLEE/centermask2.git -cd centermask2 ``` ## Step 2: Preparing datasets @@ -57,13 +44,17 @@ mkdir -p /datasets/ ln -s /path/to/coco2017 /datasets/ ``` +## Step 3: Training - -To train a model, run For example, to launch CenterMask training with VoVNetV2-39 backbone on 8 GPUs, one should execute: + ```bash +git clone https://github.com/youngwanLEE/centermask2.git cd centermask2 python3 train_net.py --config-file "configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml" --num-gpus 8 ``` +## Reference + +- [CenterMask2](https://github.com/youngwanLEE/centermask2) \ No newline at end of file -- Gitee