Skip to content

Instantly share code, notes, and snippets.

Avatar

BigsnarfDude bigsnarfdude

View GitHub Profile
@bigsnarfdude
bigsnarfdude / gist:dbf7064fa9ed08fd9f22
Last active Nov 26, 2015 — forked from debasishg/gist:8172796
A collection of links for streaming algorithms and data structures
View gist:dbf7064fa9ed08fd9f22
  1. General Background and Overview
View classifier_from_little_data_script_1.py
"""
ubuntu@red:~/dev/catDogs$ THEANO_FLAGS=device=gpu,floatX=float32 python script_1.py
"""
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
View classifier_from_little_data_script_2.py
"""
ubuntu@red:~/dev/catDogs$ THEANO_FLAGS=device=gpu,floatX=float32 python script_2.py
"""
import os
import h5py
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
View classifier_from_little_data_script_3.py
'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
@bigsnarfdude
bigsnarfdude / deep_drive_model.prototxt
Created Apr 6, 2017 — forked from aiworld/deep_drive_model.prototxt
DeepDrive - Vision model that drives in GTAV
View deep_drive_model.prototxt
name: "GTANet"
# Can be used with pretrained Caffenet (AlexNet architecture).
# Layers with names containing 'gtanet' are not transferred from Caffenet.
layer {
name: "gta_frames_input_layer"
type: "HDF5Data"
top: "images"
top: "targets"
@bigsnarfdude
bigsnarfdude / kitti_lidar.py
Created May 15, 2017 — forked from ronrest/kitti_lidar.py
Visualize Lidar Data in Kitti Data
View kitti_lidar.py
"""
VISUALISE THE LIDAR DATA FROM THE KITTI DATASET
Based on the sample code from
https://github.com/utiasSTARS/pykitti/blob/master/demos/demo_raw.py
And:
http://stackoverflow.com/a/37863912
Contains two methods of visualizing lidar data interactively.
- Matplotlib - very slow, and likely to crash, so only 1 out of every 100
You can’t perform that action at this time.