多线程会降低GPU性能

from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg

import threading
from typing import List
import numpy as np
import timeit
import cv2

# Prepare the configuration file
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7  # set threshold for this model
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml")

cfg.MODEL.DEVICE = "cuda"
predictor = DefaultPredictor(cfg)


def get_frames(video: cv2.VideoCapture):
    frames = list()
    while True:
        has_frame, frame = video.read()
        if not has_frame:
            break
        frames.append(frame)
    return frames

class CodeTimer:
    # Source: https://stackoverflow.com/a/52749808/9977758
    def __init__(self, name=None):
        self.name = " '" + name + "'" if name else ''

    def __enter__(self):
        self.start = timeit.default_timer()

    def __exit__(self, exc_type, exc_value, traceback):
        self.took = (timeit.default_timer() - self.start) * 1000.0
        print('Code block' + self.name + ' took: ' + str(self.took) + ' ms')

video = cv2.VideoCapture('DemoVideo.mp4')
num_frames = round(video.get(cv2.CAP_PROP_FRAME_COUNT))
frames_buffer = list()
predictions = list()

def send_frames():
    # This function emulates the stream, so here we "get" a frame and add it to our buffer
    for frame in get_frames(video):
        frames_buffer.append(frame)
        # Simulate delays between frames
        time.sleep(random.uniform(0.3, 2.1))

def predict_frames():
    predicted_frames = 0  # The number of frames predicted so far
    while predicted_frames < num_frames:  # Stop after we predicted all frames
        buffer_length = len(frames_buffer)
        if buffer_length <= predicted_frames:
            continue  # Wait until we get a new frame

        # Read all the frames from the point we stopped
        for frame in frames_buffer[predicted_frames:]:
            # Measure the prediction time
            with CodeTimer('In stream prediction'):
                predictions.append(predictor(frame))
            predicted_frames += 1


t1 = threading.Thread(target=send_frames)
t1.start()
t2 = threading.Thread(target=predict_frames)
t2.start()
t1.join()
t2.join()

# first create your virtual env
virtualenv -p python3 detectron_gpu
source detectron_gpu/bin/activate

#torch for jetson
wget https://nvidia.box.com/shared/static/p57jwntv436lfrd78inwl7iml6p13fzh.whl -O torch-1.8.0-cp36-cp36m-linux_aarch64.whl
sudo apt-get install python3-pip libopenblas-base libopenmpi-dev 
pip3 install Cython
pip3 install numpy torch-1.8.0-cp36-cp36m-linux_aarch64.whl

# torchvision
pip install 'git+https://github.com/pytorch/vision.git@v0.9.0'

# detectron
python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'

# ipython bindings (optional)
pip install ipykernel cloudpickle 

# opencv
pip install opencv-python

Code block 'In stream prediction' took: 2932.241764000537 ms
Code block 'In stream prediction' took: 409.69691300051636 ms
Code block 'In stream prediction' took: 410.03823099981673 ms
Code block 'In stream prediction' took: 409.4023269999525 ms