Empty output file, Detectron2

Question

I want to create body pose estimator with Detectron2. I have been trying to run following code locally to read a video file, make the prediction frame by frame and record a video with the processed frames. But it doesn`t work properly. It creates empty file and shows such error (following picture)error, if i can say like that. So i ask for help, because i don't understand what is wrong.

import detectron2
from detectron2.utils.logger import setup_logger
setup_logger()
# import some common libraries
import numpy as np
import tqdm
import cv2
# import some common detectron2 utilities
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.video_visualizer import VideoVisualizer
from detectron2.utils.visualizer import ColorMode, Visualizer
from detectron2.data import MetadataCatalog
import time

# Extract video properties
video = cv2.VideoCapture('D:/video-input.mp4')
width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
frames_per_second = video.get(cv2.CAP_PROP_FPS)
num_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))

# Initialize video writer
video_writer = cv2.VideoWriter('D:/out.mp4', fourcc=cv2.VideoWriter_fourcc(*"mp4v"), fps=float(frames_per_second), frameSize=(width, height), isColor=True)

# Initialize predictor
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 = 0.7  # 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)

# Initialize visualizer
v = VideoVisualizer(MetadataCatalog.get(cfg.DATASETS.TRAIN[0]), ColorMode.IMAGE)

def runOnVideo(video, maxFrames):
    """ Runs the predictor on every frame in the video (unless maxFrames is given),
    and returns the frame with the predictions drawn.
    """

    readFrames = 0
    while True:
        hasFrame, frame = video.read()
        if not hasFrame:
            break

        # Get prediction results for this frame
        outputs = predictor(frame)

        # Make sure the frame is colored
        frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)

        # Draw a visualization of the predictions using the video visualizer
        visualization = v.draw_instance_predictions(frame, outputs["instances"].to("cpu"))

        # Convert Matplotlib RGB format to OpenCV BGR format
        visualization = cv2.cvtColor(visualization.get_image(), cv2.COLOR_RGB2BGR)

        yield visualization

        readFrames += 1
        if readFrames > maxFrames:
            break

# Create a cut-off for debugging
num_frames = 120

# Enumerate the frames of the video
for visualization in tqdm.tqdm(runOnVideo(video, num_frames), total=num_frames):

    # Write test image
    cv2.imwrite('POSE detectron2.png', visualization)

    # Write to video file
    video_writer.write(visualization)

# Release resources
video.release()
video_writer.release()
cv2.destroyAllWindows()

Answer 1

I think the reason is that your model does not learn well. Check out MODEL.ROI_HEADS.SCORE_THRESH_TEST in the configuration. If it is large, reduce it to 0.2 and see if you get output or not.