akhtar303 / vehicle-detection-and-tracking-usig-yolo-and-deep-sort-with-keras-and-tensorflow Goto Github PK

Hi Akhtar,

how do you use people_count_app.py ?

Hello,

Thanks for your code, I have run this code successfully.
I just want get direction of Individual ID's? I am using pyimagesearch.com repo for direction. link below.
https://www.pyimagesearch.com/2015/09/21/opencv-track-object-movement/

Please help me to implementation this code in your repo.

i change the words in demo.py
model_filename = 'model_data/yolo.h5'
video_capture = cv2.VideoCapture('4.avi')
two line
and run out
KeyError: "The name 'net/images:0' refers to a Tensor which does not exist. The operation, 'net/images', does not exist in the graph."
what happen?
sorry my Englsih is poor im from Taiwan

Thanks for your implementation for vehicle detection and tracking by YOLO&DeepSort. I had a question that why you still use the pre-trained weight on MARS dataset (pedestrian dataset) to compare appearance between vehicles?

Do you think about training on vehicle dataset with proposed network (cosine metric learning)?

Let me know if you have any improvement. Thank you!

ValueError: Dimension size must be evenly divisible by 2059125 but is 153425 for 'Reshape_3' (op: 'Reshape') with input shapes: [19,19,425], [5] and with input tensors computed as partial shapes: input[1] = [?,19,425,3,85].
(yl) PS D:\Documents\Downloads\Compressed\Vehicle-Detection-and-Tracking-Usig-YOLO-and-Deep-Sort-with-Keras-and-Tensorflow-master>

from yolo3.model import yolo_eval

ImportError: bad magic number in 'yolo3': b'\x03\xf3\r\n'