Image Detection with YOLO v2 (pt 5) Custom Object Detection Get Images
Why Stack Overflow recommends it
Stack Overflow users cite it as the tutorial they followed for building a custom YOLO training set, usually when its Google Images scraping script fails with an HTTP 400 error.
Recommended by 1 people across 1 different months, 2018 to 2018.
What it is
Part 5 of a Python tutorial series on YOLO v2 object detection with darkflow, focused on building a custom dataset. The presenter, Mark Jay, walks through scripts that scrape Google Images for training pictures and rename the downloaded files.
What people said
Recommends Sirbot · 2018-07 · Stack Overflow · on “urllib.error.HTTPError: HTTP Error 400: Bad Request from trying to get a set of images”
I was trying to get a set of images for a dataset to train tiny-yolo on so I followed this tutorial [this video] The first file that was written in the tutorial goes like this: import os import urllib.request as ulib from bs4 import BeautifulSoup as Soup import json url_a = ' [LINK] ' url_b = '\&tbm=isch&ved=0ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ&start={}' url_c = '\&yv=2&vet=10ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ.1m7NWePfFYaGmQG51q7IBg' url_d = '\.i&ijn=1&asearch=ichunk&async=_id:rg_s,_pms:s' url_base = ''.join((url_a, url_b, url_c, url_d)) headers = {'User-Agent': 'Chrome/67.0.3396.99 Safari/537.36'} def get_links(search_name): search_name = search_name.replace(' ', '+') url = url_ba
Cites Bhavul · 2018-05 · Stack Overflow · on “Yolo Darknet Detecting Only Specific Class like Person, Cat, Dog etc”
If you just follow the steps that @JP Kim has mentioned - you will get a video out with just your labels, however it would also output other objects as one of your labels. There's a specific section of the darkflow repo [LINK] which exactly tells what to do if you wish to have a different output. TLDR - you should retrain your model. They show this by taking up an example of 3 classes. But, let me walk you through the process anyway. Let's consider that you have a video and you just need to track all people in it. So, we only need to track 1 type of object - 'person'. We make a copy of tiny-yolo-voc.cfg file in cfg directory. Let's follow their convention and name this tiny-yolo-voc-1c.cfg w
Cites Zef · 2018-06 · Stack Overflow · on “Raise HTTPError(req.full_url, code, msg, hdrs, fp) urllib.error.HTTPError: HTTP Error 400: Bad Request”
So i was trying to follow this tutorial [this video] to achieve image detection with YOLO. and when trying to run this code to auto download images of cell phones but it didn't work import os import urllib.request as ulib from bs4 import BeautifulSoup as Soup import json url_a = ' [LINK] ' url_b = '\&tbm=isch&ved=0ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ&start={}' url_c = '\&yv=2&vet=10ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ.1m7NWePfFYaGmQG51q7IBg' url_d = '\.i&ijn=1&asearch=ichunk&async=_id:rg_s,_pms:s' url_base = ''.join((url_a, url_b, url_c, url_d)) headers = {'User-Agent': 'Chrome/41.0.2228.0 Safari/537.36'} def get_links(search_name): search_name = search_name.replace(' ', '+') url = ur
Cites Ajeje_Brazorf · 2018-08 · Stack Overflow · on “Python error downloading image from web (HTTP Error 400: Bad Request)”
we are new to Python and we're currently trying to download from Google image using a specific keyword some images in order to make a dataset. We found a good tutorial here [this video] , but we couldn't manage to make the code work. We're using Python 3.6 and Google Chrome 68.0.3440.84 on Windows 10. The code is: import os import urllib.request as ulib from bs4 import BeautifulSoup as Soup import json url_a = ' [LINK] ' url_b = '\&tbm=isch&ved=0ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ&start={}' url_c = '\&yv=2&vet=10ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ.1m7NWePfFYaGmQG51q7IBg' url_d = '\.i&ijn=1&asearch=ichunk&async=_id:rg_s,_pms:s' url_base = ''.join((url_a, url_b, url_c, url_d)) headers