One Paragraph of project description goes here
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
Renaud Bouckenooghe iraadit
iraadit
/ augmentation.py
Created
February 22, 2018 14:25
— forked from mlgruby/augmentation.py
code snippet for image augmentation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from skimage.transform import rotate | |
| from skimage.transform import warp | |
| from skimage.transform import ProjectiveTransform | |
| def rotate(Xb, intensity, batch_size): | |
| """ | |
| Random Rotation to Image | |
| """ | |
| for i in Xb.shape[0]: |
iraadit
/ gist:b8ca1e502ba6fe62a0d2ead2953c3069
Created
February 22, 2018 14:26
— forked from Grabber/gist:de8a2b7de587cf8e58f4e3f6bb55cf23
calculating priori anchors with k-means
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # -*- coding: utf-8 -*- | |
| import time | |
| import numpy as np | |
| from random import randint | |
| iou_vals = [] | |
| iou_count = 0 | |
| class Test: |
iraadit
/ tensorflow_confusion_metrics.py
Created
February 22, 2018 14:28
— forked from Mistobaan/tensorflow_confusion_metrics.py
Confusion Metrics written in tensorflow format
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # from https://cloud.google.com/solutions/machine-learning-with-financial-time-series-data | |
| def tf_confusion_metrics(model, actual_classes, session, feed_dict): | |
| predictions = tf.argmax(model, 1) | |
| actuals = tf.argmax(actual_classes, 1) | |
| ones_like_actuals = tf.ones_like(actuals) | |
| zeros_like_actuals = tf.zeros_like(actuals) | |
| ones_like_predictions = tf.ones_like(predictions) | |
| zeros_like_predictions = tf.zeros_like(predictions) |
iraadit
/ README-Template.md
Created
February 22, 2018 14:28
— forked from PurpleBooth/README-Template.md
A template to make good README.md
iraadit
/ Extract all frames from a 24 fps movie using ffmpeg
Created
February 22, 2018 14:29
— forked from bertbalcaen/Extract all frames from a 24 fps movie using ffmpeg
Extract all frames from a 24 fps movie using ffmpeg
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ffmpeg -i shame-run.mov -r 24/1 test/output%03d.jpg |
iraadit
/ reinstall.sh
Created
February 23, 2018 15:51
— forked from 8enmann/reinstall.sh
Reinstall NVIDIA drivers without opengl Ubuntu 16.04 GTX 1080ti
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Download installers | |
| mkdir ~/Downloads/nvidia | |
| cd ~/Downloads/nvidia | |
| wget https://developer.nvidia.com/compute/cuda/8.0/Prod2/local_installers/cuda_8.0.61_375.26_linux-run | |
| wget http://us.download.nvidia.com/XFree86/Linux-x86_64/384.59/NVIDIA-Linux-x86_64-384.59.run | |
| sudo chmod +x NVIDIA-Linux-x86_64-384.59.run | |
| sudo chmod +x cuda_8.0.61_375.26_linux-run | |
| ./cuda_8.0.61_375.26_linux-run -extract=~/Downloads/nvidia/ | |
| # Uninstall old stuff | |
| sudo apt-get --purge remove nvidia-* |
iraadit
/ genesis_public_key
Created
February 27, 2018 10:59
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 047d20b52defb3c86ecf1ddf2e84ae8847d18abfde3e3542b4a0a1f11b6f12614778fe3399a95e951ac367c6a9daf56a1cd93880504d47c487a50e1a0f2623c936 |
iraadit
/ convert_voc_to_yolo.md
Created
January 14, 2019 21:07
— forked from vdalv/convert_voc_to_yolo.md
This script reads PascalVOC xml files, and converts them to YOLO txt files.
Note: This script was written and tested on Ubuntu. YMMV on other OS's.
Disclaimer: This code is a modified version of Joseph Redmon's voc_label.py
- Place the convert_voc_to_yolo.py file into your data folder.
iraadit
/ crop_classes.md
Created
January 14, 2019 21:10
— forked from vdalv/crop_classes.md
This script reads PascalVOC xml files, and crops the class instances into seperate image files.
This script reads PascalVOC xml files, and crops the class instances into seperate image files.
Note: This script relies on ImageMagick for the crop (convert) functionality. It comes pre-installed on most recent versions of Ubuntu.
Disclaimer: This code is a modified version of Dat Tran's xml_to_csv.py
Let's say we have this image in our train folder:
iraadit
/ bulk_dl_specific_filenames.md
Created
January 14, 2019 21:12
— forked from vdalv/bulk_dl_specific_filenames.md
After a few hours of searching, I've finally found a convenient way to download a large amount of files in a bulk/multi-threaded/parallel manner, while still having the ability to specify the saved files' names.
Many thanks to Diego Torres Milano
bird_4345_543.jpg https://example.com/pictures/5351/image.jpg
bird_4345_544.jpg https://example.com/5352/pictures/image.jpg
OlderNewer