chenghanc

layer     filters    size              input                output
    0 conv     32  3 x 3 / 1   416 x 416 x   3   ->   416 x 416 x  32
    1 conv     64  3 x 3 / 2   416 x 416 x  32   ->   208 x 208 x  64
    2 conv     32  1 x 1 / 1   208 x 208 x  64   ->   208 x 208 x  32
    3 conv     64  3 x 3 / 1   208 x 208 x  32   ->   208 x 208 x  64
    4 Shortcut Layer: 1
    5 conv    128  3 x 3 / 2   208 x 208 x  64   ->   104 x 104 x 128
    6 conv     64  1 x 1 / 1   104 x 104 x 128   ->   104 x 104 x  64
    7 conv    128  3 x 3 / 1   104 x 104 x  64   ->   104 x 104 x 128
    8 Shortcut Layer: 5

chenghanc

import cv2
import time

CONFIDENCE_THRESHOLD = 0.2
NMS_THRESHOLD = 0.4
COLORS = [(0, 255, 255), (255, 255, 0), (0, 255, 0), (255, 0, 0)]

class_names = []
with open("classes.txt", "r") as f:
    class_names = [cname.strip() for cname in f.readlines()]

chenghanc

@url https://major.io/2007/07/05/bintar-argument-list-too-long/

If you find yourself stuck with over 30,000 files in a directory (text files in this example), packing them into a tar file can be tricky. You can get around it with this:

find . -name '*.txt' -print >/tmp/test.manifest
tar -cvzf textfiles.tar.gz --files-from /tmp/test.manifest
find . -name '*.txt' | xargs rm -v

chenghanc

How to install multiple Tensorflow - CUDA versions on the same machine

As Tensorflow is continuously evolving, it is normal to find a situation in which you require multiple versions of Tensorflow to coexist on the same machine. Those versions can be different enough to have different CUDA library dependencies. In this case, you can be tempted to upgrade to the latest release but maybe some of your solutions are still in production or just there are not more holes in your calendar.

In this gist I will cover how to install several CUDA libraries to support different tensorflow verions. However, there are some red lines that you have to respect as the GCC versions, that must be the same, and the nvidia drivers that must support the target CUDA versions. You can check that information in the Tensoroflow website.

The basic idea is to install the CUDA libraries and abuse of the linux system to find the correct libraries when executing the target tensorflow version

chenghanc

# Terminal Cheat Sheet

pwd         # print working directory
ls          # list files in directory
cd          # change directory
~           # home directory
..          # up one directory
-           # previous working directory
help        # get help
-h          # get help