Detectron2 DefaultPredictor

[neerajvashistha]

For finetuned models built using detectron2 we generally write predictor() for example

from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file(“COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml”))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5 # set threshold for this model
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url(“COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml”)
predictor = DefaultPredictor(cfg)
im = cv2.imread("./input.jpg")
outputs = predictor(im)
mask = outputs[‘instances’].pred_masks.to(‘cpu’).numpy()

I wanted to use Service Streamer and make my model more reliable. But I am running into errors. The most logical and basic thing I tried was

streamer = ThreadedStreamer(predictor, batch_size=1, max_latency=0.1)
outputs = streamer.predict(im)

and it resulted into below

Traceback (most recent call last):
  File "/usr/lib/python3.6/threading.py", line 916, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.6/threading.py", line 864, in run
    self._target(*self._args, **self._kwargs)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 154, in run_forever
    handled = self._run_once()
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 184, in _run_once
    model_outputs = self.model_predict(model_inputs)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 163, in model_predict
    batch_result = self._predict(batch_input)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/detectron2/engine/defaults.py", line 218, in __call__
    height, width = original_image.shape[:2]
AttributeError: 'list' object has no attribute 'shape'

[2021-02-25 01:08:08,197] ERROR in app: Exception on /predict [POST]
Traceback (most recent call last):
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/flask/app.py", line 2447, in wsgi_app
    response = self.full_dispatch_request()
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/flask/app.py", line 1952, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/flask/app.py", line 1821, in handle_user_exception
    reraise(exc_type, exc_value, tb)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/flask/_compat.py", line 39, in reraise
    raise value
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/flask/app.py", line 1950, in full_dispatch_request
    rv = self.dispatch_request()
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/flask/app.py", line 1936, in dispatch_request
    return self.view_functions[rule.endpoint](**req.view_args)
  File "main.py", line 102, in predict
    outputs = streamer.predict(im)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 132, in predict
    ret = self._output(task_id)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 122, in _output
    batch_result = future.result(WORKER_TIMEOUT)
  File "/home/ubuntu/virtpy3/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 41, in result
    raise TimeoutError("Task: %d Timeout" % self._id)
TimeoutError: Task: 0 Timeout
127.0.0.1 - - [25/Feb/2021 01:08:08] "POST /predict HTTP/1.1" 500 -

any clue on how to use predictor()