{"id":2254,"date":"2020-06-26T23:49:07","date_gmt":"2020-06-26T23:49:07","guid":{"rendered":"http:\/\/elbsolutions.com\/projects\/?p=2254"},"modified":"2022-02-03T11:24:25","modified_gmt":"2022-02-03T17:24:25","slug":"i-think-my-yolov4-training-is-underway-i-will-know-in-12-hours-o","status":"publish","type":"post","link":"https:\/\/elbsolutions.com\/projects\/i-think-my-yolov4-training-is-underway-i-will-know-in-12-hours-o\/","title":{"rendered":"I THINK my A.I. YOLOv4 training is underway … I will know in 12 hours :-O – no make that 16 now"},"content":{"rendered":"\n

I have 13 classes and I followed Ritesh and his gang at Augmented startups<\/a> and bought his course which won’t be ready for 2 more weeks. He is a super nice guy and he and a couple others will work with me to get it running – but I think I just succeeded (there is an 8 hour time difference)! I also followed this guy on medium.com’s tutorial but am NOT using Colab<\/a> – I have set things up per the tutorials online for that course! But I think it is working. I am getting a blur of text scrolling at insane speeds (if you pull up the handle on the scroll window it stops enough for you to read) in my cmd window and it says 12 hours left. I think I got carried away classifying things – I had only intended on 3. <\/p>\n\n\n\n

I tried to follow AlexeyAB\/darknet’s instructions<\/a> but at one point – he starts talking about something – I think it was dragged out of place or he didn’t finish his … SQUIRREL! Not sure. I will document what I did and my performance<\/p>\n\n\n\n\n\n\n\n

Anyway, to document some of this stuff for myself – I have adjusted the yolo-custom.cfg file in the following places (as recommended by the medium.com’s link above):<\/p>\n\n\n\n

\"\"
Performance on 1st go . I am not sure if its using the GPU (or the correct GPU) – add – -gpus 0 (that is a zero) and see very bottom of this article- I think it is indeed working.<\/figcaption><\/figure><\/div>\n\n\n\n

<\/p>\n\n\n\n

batch=16\nwidth=416 # not sure why i need to change this but I don't know enough yet\nheight=416\nmax_batches = 26000 # (classes * 2000)\nsteps=20800,23400 #80% and 90% of 26000\nfilters=54 #(classes + 5) * 3  ... in 3 [yolo] layers\nclasses=13 # number of classes ... in 3 [yolo] layers\nfilters=54\nclasses=13\nfilters=54\nclasses=13<\/pre>\n\n\n\n
I think the above is self-explanatory esp. in light of the medium.com article. THese are the standard things to change except the batch size. <\/p>\n\n\n\n
Also I had to reduce the batch to 8 for it to not complain about running out of CPU ram. I expected it to complain about GPU ram – but it was CPU ram – there IS a message about GPU ram but that didn’t appear.<\/p>\n\n\n\n
My memory is 3GB over normal, my GPU 1 is only at 4% (the NVIDIA CARD) and GPU 0 is at 11-18% (this is the one running the screen I am typing on). I wonder if its using the GPU – Darknet was compiled to use the GPU so I am a little confused but being a Friday night – 12 hours is not going to kill me or the CPU – so lets crack on and see what happens.<\/p>\n\n\n\n
Here is some future reading – I need t0 figure this out. <\/p>\n\n\n\n
https:\/\/cloudxlab.com\/blog\/video-processing-with-yolov4-and-tensorflow\/<\/a>
https:\/\/pjreddie.com\/darknet\/install\/
https:\/\/github.com\/pjreddie\/darknet<\/a><\/p>\n\n\n\n