I am trying to train darknet yolov4-tiny on a custom dataset with 1500 images (1200) for training and 7 classes I have two problems: my iou stays constant (0.07) my MAP is very low (5%-6%). the command I am using to run darknet: !./darknet detector train ./data/obj.data cfg/yolov4-tiny-mine.cfg ./build/darknet/x64/yolov4-tiny.conv.29 -dont_show -map my yolo config file: ..
I have integrated OpenVINO and PyQt5 to do the inference job like this on Windows 11 with openvino_2021.4.689 version. I reference this GitHub to finish YOLOv4 inference with NCS2. The following is my inference engine code. from openvino.inference_engine import IECore import cv2 import numpy as np import global_variable as gv import ngraph as ng import ..
My environment is Windows 11 with openvino_2021.4.752 version. When I try to run object_detection_demo.py in the demos folder of inference engine, N/A result will be occurred using CPU, and the MYRIAD issue I will mention later will happened with my NCS2. [ INFO ] Initializing Inference Engine… [ INFO ] Loading network… [ INFO ] ..
I can’t find a description of these weights used in tutorial for training Yolov4 darknet and I can’t really understand where they came from, Why not 80 or 82 ..? Source: Python..
I am trying to train a YoloV4 model with my own data. I get the following error when i try to fit the model with a custom loss function: ValueError: Cannot reshape a tensor with 2945760 elements to shape [2,76,76,3,36] (1247616 elements) the parameters are: NETWORK_W = 608 NETWORK_H = 608 NB_BOX = 3 NB_CLASS ..
I am using the Yolov4-DeepSORT library in order to identify certain classes of objects in a source video. In the final output video, the image detection boxes are overlayed on the source video. Is there a way to remove the source video, and show just the object detection boxes, without any overlay in any yolo ..
Where to find the .cfg file for YoloV4-tiny model. https://github.com/AlexeyAB/darknet/releases Here I can see the .cfg for normal YoloV4 and .wights file for both YoloV4 and YoloV4-tiny, but no .cfg file for YoloV4-tiny. Also, for normal YoloV4 model I see the new .weights file in latest release (YOLOv4 16 days ago) but no new .cfg ..
I followed the steps on this repo: https://github.com/theAIGuysCode/yolov4-custom-functions The steps: python3 save_model.py –weights ./data/custom.weights –output ./checkpoints/custom.tf –input_size 416 –model yolov4 python3 convert_trt.py –weights ./checkpoints/custom.tf –quantize_mode float16 –output ./checkpoints/custom-trt-fp16-416 but got the error: Traceback (most recent call last): File "convert_trt.py", line 100, in <module> app.run(main) File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 303, in run _run_main(main, args) File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line ..
I wrote a code which runs the object detection(yolo) against bunch of images and writes output of the object detection along with the image into different folders based on the predicted classes. It basically classifies images based on the content into different folders. I created the folders based on the classID. Here is the code: ..
I ran into a memory leak running detect_image(…) which is provided by darknet.py. I was detecting objects in an endless while loop. I’m using Ubuntu 20.04, Python 3.8.10, OpenCV 4.5.2 and Cuda 10.2. Source: Python-3x..