search

healthonrails / annolid

An annotation and instance segmentation-based multiple animal tracking and behavior analysis package.
Other
39 stars 9 forks source link

Error in running track animals command #16

Closed Hatem-Jr closed 2 years ago

Hatem-Jr commented 3 years ago

I tried running this command: (labelme) D:\custom code\annolid\annolid\segmentation\yolact>python eval.py --trained_model=model_final.pth --score_threshold=0.2 --top_k=4 --video_multiframe=1 --video=Novel_Object_Test_1.mp4:my_result_video.mp4 --mot --config=data.yaml

but I got this error in the cmd: TypeError: type torch.cuda.FloatTensor not available. Torch not compiled with CUDA enabled.

note: I installed tensorflow with cuda 10.1 support on my gpu in python 3.6 version

another test file has this code in it: import tensorflow as tf print(tf.test.is_gpu_available(cuda_only=False,min_cuda_compute_capability=None))

and this is the output: Created TensorFlow device (/device:GPU:0 with 2917 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce GTX 1650, pci bus id: 0000:01:00.0, compute capability: 7.5)
True

and my guess is that there is a gpu with cuda and tensorflow

healthonrails commented 3 years ago

You need to install PyTorch for YOLACT instance segmentation. Please check the installation info here https://github.com/dbolya/yolact.