sethah / deeptennis Goto Github PK

make data/interim/tracking_videos/federer_cilic_aus_18\
 FPS=1\
 VFRAMES=100\
 MODEL_PATH=https://deeptennis.s3-us-west-1.amazonaws.com/player_kprcnn_res50_fpn.tar.gz

FileNotFoundError: file /home/sethah/ssd/deeptennis/models/tennis_rpn4 not found

2020-03-12 18:34:22,525 - INFO - allennlp.common.from_params - instantiating class
 <class 'allencv.models.object_detection.keypoint_rcnn.KeypointRCNN'> from params 
{
  'num_keypoints': 4, 
  'rpn': {
    'archive_file': '/home/sethah/ssd/deeptennis/models/tennis_rpn4', 
    'requires_grad': True, 
    'type': 'pretrained_rpn'
  }, 
  'roi_keypoint_head': {
    'feature_extractor': {
      'activations': 'relu', 
      'hidden_channels': 512, 
      'input_channels': 256, 
      'num_layers': 5, 
      'type': 'feedforward'
    }
  }, 
  'train_rpn': True, 
  'roi_box_head': {
    'decoder_nms_thresh': 0.2, 
    'feature_extractor': {
      'feedforward': {
        'activations': 'relu', 
        'hidden_dims': [256, 256], 
        'input_dim': 12544, 
        'num_layers': 2
      }, 
      'input_channels': 256, 
      'input_height': 7, 
      'input_width': 7, 
      'type': 'flatten'
    }, 
    'decoder_thresh': 0.01
  }
} and extras {'vocab'}

python3 -m allencv.service.server_simple\
 --archive-path "https://deeptennis.s3-us-west-1.amazonaws.com/player_kprcnn_res50_fpn.tar.gz"\
 --predictor default_image\
 --include-package allencv.data.dataset_readers\
 --include-package allencv.modules.im2vec_encoders\
 --include-package allencv.modules.im2im_encoders\
 --include-package allencv.models\
 --include-package allencv.predictors\
 --title "Player detector"\
 --detection\
 --overrides '{"dataset_reader": {"type": "image_annotation", "augmentation": [{"type": "resize", "height": 720, "width": 1280}, {"type": "normalize"}], "lazy": true}, "model": {"roi_box_head": {"decoder_detections_per_image": 50}, "rpn": {"archive_file": "https://deeptennis.s3-us-west-1.amazonaws.com/player_rpn_res50_fpn.tar.gz"}}}'
Neither build_dir nor field_names passed. Demo won't render on this port.
You must use nodejs + react app to interact with the server.
Model loaded, serving demo on port 8000
127.0.0.1 - - [2020-03-11 17:55:39] "GET / HTTP/1.1" 200 12402 0.001025
[2020-03-11 17:55:39,405] ERROR in app: Exception on /predict [POST]
Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 2446, in wsgi_app
    response = self.full_dispatch_request()
  File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1951, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "/usr/local/lib/python3.6/dist-packages/flask_cors/extension.py", line 161, in wrapped_function
    return cors_after_request(app.make_response(f(*args, **kwargs)))
  File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1820, in handle_user_exception
    reraise(exc_type, exc_value, tb)
  File "/usr/local/lib/python3.6/dist-packages/flask/_compat.py", line 39, in reraise
    raise value
  File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1949, in full_dispatch_request
    rv = self.dispatch_request()
  File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1935, in dispatch_request
    return self.view_functions[rule.endpoint](**req.view_args)
  File "/usr/local/lib/python3.6/dist-packages/allencv/service/server_simple.py", line 141, in predict
    decoded = base64.b64decode(data[23:])
  File "/usr/lib/python3.6/base64.py", line 87, in b64decode
    return binascii.a2b_base64(s)
binascii.Error: Incorrect padding
127.0.0.1 - - [2020-03-11 17:55:39] "POST /predict HTTP/1.1" 500 477 0.009075```