Tom Runia tomrunia

## filenames_from_queue.py
filename_queue = tf.FIFOQueue(100000, [tf.string], shapes=[[]])

# ...

reader = tf.WholeFileReader()
image_filename, image_raw = reader.read(self._filename_queue)
image = tf.image.decode_jpeg(image_raw, channels=3)

# Image preprocessing
image_preproc = ...

## train_lstm.py
import time

import numpy as np
import matplotlib.pyplot as plt
from Blockchain_test import return_data

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Embedding
from keras.layers import LSTM

## train_lstm.py
import time

import numpy as np
import matplotlib.pyplot as plt
from Blockchain_test import return_data

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Embedding
from keras.layers import LSTM

## test_queue.py
import time
import numpy as np
import threading

import tensorflow as tf
from tensorflow.python.client import timeline


def test_queue():

## gradient_clip.py
# We must calculate the mean of each gradient. Note that this is the
# synchronization point across all towers.
grads_and_vars = average_gradients(t_grads)

# Optionally perform gradient clipping
if config.max_norm_gradient > 0:
    grads, variables = zip(*grads_and_vars)
    grads_clipped, _ = tf.clip_by_global_norm(grads, clip_norm=config.max_norm_gradient)
    grads_and_vars = zip(grads_clipped, variables)

## tf_summary_reader.py
import os
import sys
import pickle
import numpy as np
import tensorflow as tf
from tensorflow.python.summary.event_accumulator import EventAccumulator


event_file = "/home/trunia1/dev/python/LSTMCounting/output/screens/" \
             "summaries/004_rmsprop_0.0005_lstm_512x2_grad_10_batch_128_dropkp_0.75/" \

## barchart.html
<!DOCTYPE html>
<meta charset="utf-8">

<!-- The visual styling of our barchart is in this file -->
<link rel="stylesheet" href="barchart.css">

<!-- This is the main container to which we append all chart elements -->
<svg class="chart"></svg>

<!-- We include D3 from an external location so that we don't have

## Chrome.sublime-build
{
	"cmd": ["open", "-a", "Google Chrome", "$file", "--args", "--allow-file-access-from-files"]
}

## cat-classification-caffe.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                tomrunia
                / cat-classification-caffe.md
            
            
              Created
              March 14, 2016 09:18
            
          
    AlexNet

Classification done in 79.1ms [avg = 79.1ms]
Probabilities and labels:
n02124075 Egyptian cat (0.31)
n02123159 tiger cat (0.18)
n02123045 tabby, tabby cat (0.12)
n02119022 red fox, Vulpes vulpes (0.11)
n02085620 Chihuahua (0.04)

  
## README.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                tomrunia
                / README.md
            
            
              Created
              March 3, 2016 15:23
            
              
                Caffe model benchmarks: average classification time per image on MS-COCO (GPU Titan X)
              
          
    Caffe Classification

Classification Speed Benchmark

Table lists average classification times per image (milliseconds). Averages are
computed over classification of 100 images from MS-COCO validation set. For the VGG networks
a very high variance in classification times was observed, some images were classified fast
while most of them took more processing time that other network configurations.
	filename_queue = tf.FIFOQueue(100000, [tf.string], shapes=[[]])

	# ...

	reader = tf.WholeFileReader()
	image_filename, image_raw = reader.read(self._filename_queue)
	image = tf.image.decode_jpeg(image_raw, channels=3)

	# Image preprocessing
	image_preproc = ...
	import time

	import numpy as np
	import matplotlib.pyplot as plt
	from Blockchain_test import return_data

	from keras.preprocessing import sequence
	from keras.models import Sequential
	from keras.layers import Dense, Embedding
	from keras.layers import LSTM
	import time
	import numpy as np
	import threading

	import tensorflow as tf
	from tensorflow.python.client import timeline


	def test_queue():
	# We must calculate the mean of each gradient. Note that this is the
	# synchronization point across all towers.
	grads_and_vars = average_gradients(t_grads)

	# Optionally perform gradient clipping
	if config.max_norm_gradient > 0:
	grads, variables = zip(*grads_and_vars)
	grads_clipped, _ = tf.clip_by_global_norm(grads, clip_norm=config.max_norm_gradient)
	grads_and_vars = zip(grads_clipped, variables)
	import os
	import sys
	import pickle
	import numpy as np
	import tensorflow as tf
	from tensorflow.python.summary.event_accumulator import EventAccumulator


	event_file = "/home/trunia1/dev/python/LSTMCounting/output/screens/" \
	"summaries/004_rmsprop_0.0005_lstm_512x2_grad_10_batch_128_dropkp_0.75/" \
	<!DOCTYPE html>
	<meta charset="utf-8">

	<!-- The visual styling of our barchart is in this file -->
	<link rel="stylesheet" href="barchart.css">

	<!-- This is the main container to which we append all chart elements -->
	<svg class="chart"></svg>

	<!-- We include D3 from an external location so that we don't have
	{
	"cmd": ["open", "-a", "Google Chrome", "$file", "--args", "--allow-file-access-from-files"]
	}