quoccuongle/Grounded-SAM-2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update links after renaming the repo from segment-anything-2 to sam2 (#341)

Browse Source 
This PR update repo links after we renamed the repo from `segment-anything-2` to `sam2`. It also changes `NAME` in setup.py to `SAM-2` (which is already the named used in pip setup since python packages don't allow whitespace)
This commit is contained in:
Ronghang Hu
2024-09-30 20:27:44 -07:00
committed by GitHub
parent 05d9e57fb3
commit 98fcb164bf
9 changed files with 28 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
notebooks/video_predictor_example.ipynb
View File

@@ -37,7 +37,7 @@
"id": "a887b90f-6576-4ef8-964e-76d3a156ccb6",
"metadata": {},
"source": [
"<a target=\"_blank\" href=\"https://colab.research.google.com/github/facebookresearch/segment-anything-2/blob/main/notebooks/video_predictor_example.ipynb\">\n",
"<a target=\"_blank\" href=\"https://colab.research.google.com/github/facebookresearch/sam2/blob/main/notebooks/video_predictor_example.ipynb\">\n",
" <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
"</a>"
]
@@ -55,7 +55,7 @@
"id": "8491a127-4c01-48f5-9dc5-f148a9417fdf",
"metadata": {},
"source": [
"If running locally using jupyter, first install `sam2` in your environment using the [installation instructions](https://github.com/facebookresearch/segment-anything-2#installation) in the repository.\n",
"If running locally using jupyter, first install `sam2` in your environment using the [installation instructions](https://github.com/facebookresearch/sam2#installation) in the repository.\n",
"\n",
"If running from Google Colab, set `using_colab=True` below and run the cell. In Colab, be sure to select 'GPU' under 'Edit'->'Notebook Settings'->'Hardware accelerator'. Note that it's recommended to use **A100 or L4 GPUs when running in Colab** (T4 GPUs might also work, but could be slow and might run out of memory in some cases)."
]
@@ -85,7 +85,7 @@
" print(\"CUDA is available:\", torch.cuda.is_available())\n",
" import sys\n",
" !{sys.executable} -m pip install opencv-python matplotlib\n",
" !{sys.executable} -m pip install 'git+https://github.com/facebookresearch/segment-anything-2.git'\n",
" !{sys.executable} -m pip install 'git+https://github.com/facebookresearch/sam2.git'\n",
"\n",
" !mkdir -p videos\n",
" !wget -P videos https://dl.fbaipublicfiles.com/segment_anything_2/assets/bedroom.zip\n",
@@ -1047,7 +1047,7 @@
"id": "e023f91f-0cc5-4980-ae8e-a13c5749112b",
"metadata": {},
"source": [
"Note that in addition to clicks or boxes, SAM 2 also supports directly using a **mask prompt** as input via the `add_new_mask` method in the `SAM2VideoPredictor` class. This can be helpful in e.g. semi-supervised VOS evaluations (see [tools/vos_inference.py](https://github.com/facebookresearch/segment-anything-2/blob/main/tools/vos_inference.py) for an example)."
"Note that in addition to clicks or boxes, SAM 2 also supports directly using a **mask prompt** as input via the `add_new_mask` method in the `SAM2VideoPredictor` class. This can be helpful in e.g. semi-supervised VOS evaluations (see [tools/vos_inference.py](https://github.com/facebookresearch/sam2/blob/main/tools/vos_inference.py) for an example)."
]
},
{