Eugeny

OpenCV's VideoCapture is broken and hasn't been fixed for the last 5 years: opencv/opencv#9053

This is a PyAV based replacement. Unlike other implementations it can seek at any time.

How to use:

reader = VideoReader('video.mp4')
reader.seek(reader.total_frames - 100)  # frame number 
while True:

rdipietro

    class ClockworkLayer(RNNLayer):
      """ A clockwork RNN layer.
    
      As done in the original paper, we restrict ourselves to an exponential
      series of periods. As noted in the paper, this lets W_H and W_I be
      contiguous, and the implementation is therefore much simpler.
    
      This is based on Jan Koutnik et al.: A Clockwork RNN.
      arXiv preprint arXiv:1402.3511. 2014.
    

batzner

import sys, getopt

import tensorflow as tf

usage_str = 'python tensorflow_rename_variables.py --checkpoint_dir=path/to/dir/ ' \
            '--replace_from=substr --replace_to=substr --add_prefix=abc --dry_run'


def rename(checkpoint_dir, replace_from, replace_to, add_prefix, dry_run):
    checkpoint = tf.train.get_checkpoint_state(checkpoint_dir)

pebbie

"""
author: Peb Ruswono Aryan

Binarization Algorithm by Su et al.

@inproceedings{Su:2010:BHD:1815330.1815351,
 author = {Su, Bolan and Lu, Shijian and Tan, Chew Lim},
 title = {Binarization of Historical Document Images Using the Local Maximum and Minimum},
 booktitle = {Proceedings of the 9th IAPR International Workshop on Document Analysis Systems},
 series = {DAS '10},

myme5261314

import tensorflow as tf
import numpy as np
import input_data
import Image
from util import tile_raster_images


def sample_prob(probs):
    return tf.nn.relu(
        tf.sign(

nikitakit

This gist has been superceded by Meta Graph functionality that has since been added to tensorflow core.

See: https://www.tensorflow.org/versions/master/api_docs/python/state_ops.html#exporting-and-importing-meta-graphs

The code remains posted for archival purposes only.

saliksyed

""" Deep Auto-Encoder implementation
	
	An auto-encoder works as follows:

	Data of dimension k is reduced to a lower dimension j using a matrix multiplication:
	softmax(W*x + b)  = x'
	
	where W is matrix from R^k --> R^j

	A reconstruction matrix W' maps back from R^j --> R^k

baraldilorenzo

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

vsoch

from sklearn.externals import joblib
import time
import numpy
import pickle

bigarray = numpy.zeros([190,91,190])
bigarray = bigarray.flatten()


### Saving

alexland

import time
import numpy as NP
from redis import StrictRedis as redis

# a 2D array to serialize
A = 10 * NP.random.randn(10000).reshape(1000, 10)

# flatten the 2D NumPy array and save it as a binary string
array_dtype = str(A.dtype)