Open hapyty opened 7 months ago
You've chosen to report an unexpected problem or bug. Unless you already know the root cause of it, please include details about it by filling the issue template. The following information is missing: "Instructions To Reproduce the Issue and Full Logs"; "Your Environment";
Looks like you have a problem loading pre-trained models firstly load the correct yaml file depending upon which pretrained model to use you cannot have mask_rcnn_R_50_FPN_3x.yaml and use different models weight both should be same you can either define like this or give direct path to pretrained weights using cfg.MODEL.WEIGHTS = ("pretrained_model_path")
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")) cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
Looks like you have a problem loading pre-trained models firstly load the correct yaml file depending upon which pretrained model to use you cannot have mask_rcnn_R_50_FPN_3x.yaml and use different models weight both should be same you can either define like this or give direct path to pretrained weights using cfg.MODEL.WEIGHTS = ("pretrained_model_path")
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")) cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
thank you for reply
can you also checkout this? https://github.com/facebookresearch/detectron2/issues/5170
Hello! The pre-trained model I load was trained by "epoch", so detectron2 can't recognize it. Then I met following error:
ValueError: Unsupported type found in checkpoint! epoch: <class 'int'>
Anyone met this error? Enviroment info:
sys.platform linux Python 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] numpy 1.21.5 detectron2 0.5 @/data/wrz/transfiner/detectron2 Compiler GCC 7.3 CUDA compiler CUDA 10.2 detectron2 arch flags 7.0 DETECTRON2_ENV_MODULE
PyTorch 1.7.1 @/home/asc005/anaconda3/envs/transfiner/lib/python3.7/site-packages/torch
PyTorch debug build False
GPU available Yes
GPU 0,1 Tesla V100-PCIE-32GB (arch=7.0)
Driver version 440.64.00
CUDA_HOME /usr/local/cuda-10.2
Pillow 9.0.1
torchvision 0.8.2 @/home/asc005/anaconda3/envs/transfiner/lib/python3.7/site-packages/torchvision
torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5
fvcore 0.1.5.post20221221
iopath 0.1.9
cv2 4.4.0
PyTorch built with: