search

gaomingqi / Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
MIT License
6.52k stars 482 forks source link

在我的macstudio上运行出错，我的是Apple M1 Max芯片，32GB内存，macOS是13.0 (22A380) #53

Open sepplu opened 1 year ago

sepplu commented 1 year ago

运行情况：(supple) sepplu@seppdeMac-Studio Track-Anything % python3 app.py --device cpu Defaulting to user installation because normal site-packages is not writeable Looking in links: https://download.openmmlab.com/mmcv/dist/cpu/torch2.0.0/index.html Requirement already satisfied: mmcv in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (2.0.0) Requirement already satisfied: addict in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmcv) (2.4.0) Requirement already satisfied: mmengine>=0.2.0 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmcv) (0.7.3) Requirement already satisfied: numpy in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmcv) (1.24.3) Requirement already satisfied: packaging in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmcv) (23.1) Requirement already satisfied: Pillow in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmcv) (9.5.0) Requirement already satisfied: pyyaml in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmcv) (6.0) Requirement already satisfied: yapf in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmcv) (0.33.0) Requirement already satisfied: matplotlib in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmengine>=0.2.0->mmcv) (3.7.1) Requirement already satisfied: rich in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmengine>=0.2.0->mmcv) (13.3.5) Requirement already satisfied: termcolor in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmengine>=0.2.0->mmcv) (2.3.0) Requirement already satisfied: opencv-python>=3 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from mmengine>=0.2.0->mmcv) (4.7.0.72) Requirement already satisfied: tomli>=2.0.1 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from yapf->mmcv) (2.0.1) Requirement already satisfied: contourpy>=1.0.1 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from matplotlib->mmengine>=0.2.0->mmcv) (1.0.7) Requirement already satisfied: cycler>=0.10 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from matplotlib->mmengine>=0.2.0->mmcv) (0.11.0) Requirement already satisfied: fonttools>=4.22.0 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from matplotlib->mmengine>=0.2.0->mmcv) (4.39.3) Requirement already satisfied: kiwisolver>=1.0.1 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from matplotlib->mmengine>=0.2.0->mmcv) (1.4.4) Requirement already satisfied: pyparsing>=2.3.1 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from matplotlib->mmengine>=0.2.0->mmcv) (3.0.9) Requirement already satisfied: python-dateutil>=2.7 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from matplotlib->mmengine>=0.2.0->mmcv) (2.8.2) Requirement already satisfied: importlib-resources>=3.2.0 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from matplotlib->mmengine>=0.2.0->mmcv) (5.12.0) Requirement already satisfied: markdown-it-py<3.0.0,>=2.2.0 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from rich->mmengine>=0.2.0->mmcv) (2.2.0) Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from rich->mmengine>=0.2.0->mmcv) (2.15.1) Requirement already satisfied: zipp>=3.1.0 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from importlib-resources>=3.2.0->matplotlib->mmengine>=0.2.0->mmcv) (3.15.0) Requirement already satisfied: mdurl~=0.1 in /Users/sepplu/Library/Python/3.9/lib/python/site-packages (from markdown-it-py<3.0.0,>=2.2.0->rich->mmengine>=0.2.0->mmcv) (0.1.2) Requirement already satisfied: six>=1.5 in /Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/site-packages (from python-dateutil>=2.7->matplotlib->mmengine>=0.2.0->mmcv) (1.15.0) Initializing BaseSegmenter to cpu Traceback (most recent call last): File "/Users/sepplu/Track-Anything/app.py", line 383, in model = TrackingAnything(SAM_checkpoint, xmem_checkpoint, e2fgvi_checkpoint,args) File "/Users/sepplu/Track-Anything/track_anything.py", line 19, in init self.xmem = BaseTracker(self.xmem_checkpoint, device=args.device) File "/Users/sepplu/Track-Anything/tracker/base_tracker.py", line 32, in init network = XMem(config, xmem_checkpoint).to(device).eval() File "/Users/sepplu/Track-Anything/tracker/model/network.py", line 24, in init model_weights = self.init_hyperparameters(config, model_path, map_location) File "/Users/sepplu/Track-Anything/tracker/model/network.py", line 145, in init_hyperparameters model_weights = torch.load(model_path, map_location=map_location) File "/Users/sepplu/miniconda3/envs/supple/lib/python3.10/site-packages/torch/serialization.py", line 809, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "/Users/sepplu/miniconda3/envs/supple/lib/python3.10/site-packages/torch/serialization.py", line 1172, in _load result = unpickler.load() File "/Users/sepplu/miniconda3/envs/supple/lib/python3.10/site-packages/torch/serialization.py", line 1142, in persistent_load typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) File "/Users/sepplu/miniconda3/envs/supple/lib/python3.10/site-packages/torch/serialization.py", line 1116, in load_tensor wrap_storage=restore_location(storage, location), File "/Users/sepplu/miniconda3/envs/supple/lib/python3.10/site-packages/torch/serialization.py", line 217, in default_restore_location result = fn(storage, location) File "/Users/sepplu/miniconda3/envs/supple/lib/python3.10/site-packages/torch/serialization.py", line 182, in _cuda_deserialize device = validate_cuda_device(location) File "/Users/sepplu/miniconda3/envs/supple/lib/python3.10/site-packages/torch/serialization.py", line 166, in validate_cuda_device raise RuntimeError('Attempting to deserialize object on a CUDA ' RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

sepplu commented 1 year ago

不懂编程，是影视行业从业者，对这个模型实现的功能很感兴趣，希望工作中能用上这个模型，请高手指导

memoryunreal commented 1 year ago

Thanks for your interest. We haven't tested it on Mac. We recommend you use an NVIDIA device for testing this model. Please check our latest commit, we move the checkpoint stored in the CPU.

Osub commented 1 year ago

me too

BingQiangChen commented 1 year ago

You can set --device mps and revise app.py file change args.device = "mps" not "cuda:3"

moralibiao commented 1 year ago

You can set --device mps and revise app.py file change args.device = "mps" not "cuda:3"

I did as you suggested, but it did not work. Could you please share more info? Thanks a lot

alon1samuel commented 7 months ago

I've tried, but encountered a problem with mmcv, and after following their installation guide in which they recommend to download torch==1.13 I've tried to run app.py in here but there was a torch problem. So I've reverted to run it on a linux based machine...

alon1samuel commented 7 months ago

I've managed to make it work for Mac!

Stuff I've added:

(on the same terminal window before running python.py)

export PYTORCH_ENABLE_MPS_FALLBACK=1

In tracker/config/config.yaml I've changed:

...
num_prototypes: 16
top_k: 16
...

In app.py:

...
args.device = "mps"
...