mlzxy

I use the first


—– BEGIN LICENSE —–
Michael Barnes
Single User License
EA7E-821385
8A353C41 872A0D5C DF9B2950 AFF6F667
C458EA6D 8EA3C286 98D1D650 131A97AB
AA919AEC EF20E143 B361B1E7 4C8B7F04

mlzxy

"""
make trainable
"""
def make_trainable(net, val):
    pass
    net.trainable = val
    for l in net.layers:
        l.trainable = val
        

mlzxy

What forces layout / reflow

All of the below properties or methods, when requested/called in JavaScript, will trigger the browser to synchronously calculate the style and layout*. This is also called reflow or layout thrashing, and is common performance bottleneck.

Element

Box metrics

• elem.offsetLeft, elem.offsetTop, elem.offsetWidth, elem.offsetHeight, elem.offsetParent
• elem.clientLeft, elem.clientTop, elem.clientWidth, elem.clientHeight
• elem.getClientRects(), elem.getBoundingClientRect()

mlzxy

/**
 * 1. install nodejs from https://nodejs.org/en/download/
 * 2. run `npm install -g serve-static filehandler serve-index` in terminal
 * 3. run `node mediaserver.js`
 */
var http = require('http'),
    fs = require('fs'),
    util = require('util'),
    url = require('url'),
    path = require('path'),

mlzxy

export http_proxy='http://127.0.0.1:8123'  
export https_proxy='http://127.0.0.1:8123'  

mlzxy

export http_proxy='http://127.0.0.1:8123'  
export https_proxy='http://127.0.0.1:8123'  

mlzxy

import tensorflow as tf
from tensorflow.python.framework import ops
import numpy as np

# Define custom py_func which takes also a grad op as argument:
def py_func(func, inp, Tout, stateful=True, name=None, grad=None):
    
    # Need to generate a unique name to avoid duplicates:
    rnd_name = 'PyFuncGrad' + str(np.random.randint(0, 1E+8))
    

mlzxy

from util import *
from tf_util import *
from matplotlib import pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
# %matplotlib inline

"""
Parameter Sections
"""
model_name = 'basic_gan_mnist'

mlzxy

import tensorflow as tf
from util import model_save_temp_folder__, join, isfile, datetime, list_prod, to_list, mkdir, tqdm
from tensorflow.python.ops import seq2seq as s2s
from tensorflow.contrib import layers
import numpy as np
import random

PADDING_SAME = 'SAME'
PADDING_VALID = 'VALID'
tf_sigmoid = tf.nn.sigmoid

mlzxy

import tensorflow as tf    
import numpy as np

if __name__ == '__main__':
  np.random.seed(1)  
  # the size of the hidden state for the lstm (notice the lstm uses 2x of this amount so actually lstm will have state of size 2)
  size = 1
  # 2 different sequences total
  batch_size= 2
  # the maximum steps for both sequences is 10