Skip to content

Instantly share code, notes, and snippets.

View d3rezz's full-sized avatar

Francisco Salgado d3rezz

16 followers · 25 following
View GitHub Profile
@d3rezz
d3rezz / kinect_body_tracking.txt
Created December 10, 2016 18:46
Kinect Skeleton tracking with Openni_tracker on ROS Indigo
#Download openni_tracker
cd ~/catkin_ws/src/
git clone https://github.com/ros-drivers/openni_tracker
source ~/catkin_ws/devel/setup.bash
#Create new launcher that passes the correct params
vim ~/catkin_ws/src/openni_tracker/tracker.launch
#Paste this (taken from: http://pastebin.com/NuJEYaf0)
<launch>
@d3rezz
d3rezz / imagenet_1001_labels.txt
Created March 21, 2019 13:46
Class labels for tf-slim models. Although ImageNet has 1000 classes, tf-slim models are trained with one additional class for unknown classes.
dont know (background)
tench, Tinca tinca
goldfish, Carassius auratus
great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias
tiger shark, Galeocerdo cuvieri
hammerhead, hammerhead shark
electric ray, crampfish, numbfish, torpedo
stingray
cock
hen
@d3rezz
d3rezz / finetune.py
Last active June 7, 2019 16:39
Finetuning a tensorflow slim model (Resnet v1 50) with a dataset in TFRecord format
# Finetune a tensorflow slim model (Resnet v1 50) on the flowers dataset in TFRecord format
# TFRecord files created using the script from https://github.com/kwotsin/create_tfrecords
# Trainining done in a Keras like way, where training and validation accuracy are computed every epoch
# Download resnet checkpoint from: http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz
import tensorflow as tf
import numpy as np
import os
import glob
from tqdm import tqdm
@d3rezz
d3rezz / resident_advisor_podcast_mp3_links.txt
Created October 5, 2019 20:26
Resident Advisor Podcasts mp3 download links
@d3rezz
d3rezz / 2d_rgb_to_3d.py
Created August 10, 2019 08:38
"""Estimating 3d coordinates from an RGB image
Support for the "Estimating 3d coordinates from an RGB image"
blog post in d3rezz.github.io
"""
import cv2
import numpy as np
import time
import matplotlib.pyplot as plt