lijiansong

The Computer Language Benchmarks Game - Mandelbrot

Source code: https://github.com/mrange/benchmarksgame/tree/master/src/mandelbrot

1. Update 2017-06-25 - Decided I could do a bit better with F# so I added an improved F# program that uses the .NET SSE
2. Update 2017-07-01 - Reduced the overhead of bitmap allocation saving 9ms for 16000x16000 bitmaps
3. Update 2017-07-06 - Improved the fast F# program by removing overy redundancy

Recently I discovered The Computer Language Benchmarks Game which intrigued me, especially the mandelbrot version.

lijiansong

lijiansong

import math
import datetime

from tqdm import tqdm

import pandas as pd
import numpy as np

import tensorflow as tf

lijiansong

"""TensorFlow 2.0 implementation of vanilla Autoencoder."""
import numpy as np
import tensorflow as tf

__author__ = "Abien Fred Agarap"

np.random.seed(1)
tf.random.set_seed(1)
batch_size = 128
epochs = 10

lijiansong

Build TF 2.0 from source

Step 1:

从anaconda的base环境中创建新的环境：

$ conda create -n tf2-source python=3.6
$ conda activate tf2-source

lijiansong

name: "ZF"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 720 #770 725
  dim: 1280 #683 1285
}

input: "im_info"

lijiansong

name: "MOBILENET_V2"
#  transform_param {
#    scale: 0.017
#    mirror: false
#    crop_size: 224
#    mean_value: [103.94,116.78,123.68]
#  }
input: "data"
input_shape {
  dim: 1

lijiansong

name: "VGG_VOC0712_SSD_300x300_deploy"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 300
  dim: 300
}

layer {

lijiansong

name: "MobileNet-SSD"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 300
  dim: 300
}

layer {

lijiansong

name: "DENSENET_121"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 224
  dim: 224
}
layer {
  name: "conv1"