search

krematas / soccerontable

Upconverting YouTube soccer videos in 3D for viewing in AR/VR devices.Soccer On Your Tabletop
BSD 2-Clause "Simplified" License
498 stars 95 forks source link

Run Detectron to get bounding boxes error #4

Closed js-john closed 6 years ago

js-john commented 6 years ago

$ python2 tools/infer_subimages.py --cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml --output-dir $DATADIR/detectron --image-ext jpg --wts https://s3-us-west-2.amazonaws.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl $DATADIR/images/

Traceback (most recent call last): File "tools/infer_subimages.py", line 219, in main(args) File "tools/infer_subimages.py", line 103, in main model = infer_engine.initialize_model_from_cfg() TypeError: initialize_model_from_cfg() takes at least 1 argument (0 given)

I checked the "test_engin.py" file in Detectron/detectron/tools and found the function initialize_model_from_cfg needs at least 1 weight_file argument

def initialize_model_from_cfg(weights_file, gpu_id=0): """Initialize a model from the global cfg. Loads test-time weights and creates the networks in the Caffe2 workspace. """ model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id) net_utils.initialize_gpu_from_weights_file( model, weights_file, gpu_id=gpu_id, ) model_builder.add_inference_inputs(model) workspace.CreateNet(model.net) workspace.CreateNet(model.conv_body_net) if cfg.MODEL.MASK_ON: workspace.CreateNet(model.mask_net) if cfg.MODEL.KEYPOINTS_ON: workspace.CreateNet(model.keypoint_net) return model

krematas commented 6 years ago

I updated the script for the newest version of detectron. It works on my side