Skip to content

Instantly share code, notes, and snippets.

View bpinaya's full-sized avatar
🤖
yes HelloWorld | head -10

Benjamin Pinaya bpinaya

🤖
yes HelloWorld | head -10
View GitHub Profile
<link rel="import" href="../core-icons/core-icons.html">
<link rel="import" href="../paper-item/paper-item.html">
<polymer-element name="my-element">
<template>
<style>
:host {
position: absolute;
width: 100%;
variables:
ROS_DISTRO: "indigo"
CI_SOURCE_PATH: "$CI_PROJECT_DIR"
ROS_PARALLEL_JOBS: "-j8 -l6"
before_script:
# before install
- mkdir -p ~/catkin_ws/src
- cd ~/catkin_ws/src
- if [ ! -f CMakeLists.txt ]; then catkin_init_workspace; else echo "CMakeList file already there";fi
@bpinaya
bpinaya / CarDetection.py
Created February 22, 2017 23:49
Detectnet on a video video input. Call: python CarDetection.py yourSnap.caffemodel deplot.prototxt input.mp4 output.mp4
# Based on
# https://gist.github.com/lukeyeager/777087991419d98700054cade2f755e6
#--------------------------------------------------------------------
# CarDetection runs Detectnet on a video pipeline (TX1 Tested)
# This might be run only once if no ffmpeg is installed
#import imageio
#imageio.plugins.ffmpeg.download()
import cv2
name: 'FCN 16s'
layer {
type: 'data'
name: 'data'
top: 'data'
input_param {
shape {
dim: 1
dim: 3
dim: 500
@bpinaya
bpinaya / LeNet-MNIST.prototxt
Last active August 9, 2018 12:00
LeNet MNIST deploy prototxt for netscope visualization check https://ethereon.github.io/netscope/#/gist/5166ee1d07cd3521cdfbe8aa8ffc5693
name: "LeNet"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 64 dim: 1 dim: 28 dim: 28 } }
}
layer {
name: "conv1"
type: "Convolution"
@bpinaya
bpinaya / FastRCNN.prototxt
Created August 6, 2018 08:15
FastRCNN VGG16 for Netscope visualization, not supporting certain layers.
name: "FastRCNN VGG16"
input: "data"
input_shape {
dim: 2
dim: 3
dim: 375
dim: 500
}
@bpinaya
bpinaya / FCNAlexnet.prototxt
Last active August 6, 2018 15:23
FCNAlexnet deploy network for Netscope visualization. Check https://ethereon.github.io/netscope/#/gist/a927a54a5bd8d319242f763030a2d890
name: "FCN AlexNet"
input: "data"
input_shape {
dim: 1
dim: 3
dim: 1024
dim: 2048
}
layer {
name: "shift"
@bpinaya
bpinaya / FCNAlexNetTraining.prototxt
Created August 6, 2018 15:22
FCNAlexNet prototxt file for training. Tested on digits.
# data layers
layer {
name: "data"
type: "Data"
top: "data"
include {
phase: TRAIN
}
data_param {
batch_size: 1
name: "AlexNet"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }
}
layer {
name: "conv1"
type: "Convolution"
@bpinaya
bpinaya / imagenet-labels.txt
Created August 13, 2018 09:36
ImageNet 1000 class ids, c++ friendly.
"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"
"ostrich, Struthio camelus"