xta0

main(%input_0: (1, 3, 398, 224, fp32)(Tensor),
     %input_1: (1, 3, fp32)(Tensor)) {
  block0() {
    %185: (1, 3, 398, 224, fp32)(Tensor) = sub(x=%input_0, y=[[[103.52999877929688]], [[116.27999877929688]], [[123.67500305175781]]], name="185")
    %input.1: (1, 3, 398, 224, fp32)(Tensor) = real_div(x=%185, y=[[[57.375]], [[57.119998931884766]], [[58.39500045776367]]], name="input.1")
    %input0.1: (1, 16, 199, 112, fp32)(Tensor) = conv(x=%input.1, weight=%151, bias=%150, strides=[2, 2], pad_type="custom", pad=[1, 1, 1, 1], dilations=[1, 1], groups=1, name="input0.1")
    %192: (1, 16, 199, 112, fp32)(Tensor) = relu(x=%input0.1, name="192")
    %input1.1: (1, 16, 199, 112, fp32)(Tensor) = conv(x=%192, weight=%147, strides=[1, 1], pad_type="custom", pad=[1, 1, 1, 1], dilations=[1, 1], groups=16, name="input1.1")
    %x.1: (1, 16, 199, 112, fp32)(Tensor) = conv(x=%input1.1, weight=%145, bias=%144, strides=[1, 1], pad_type="custom", pad=[0, 0, 0, 0], dilations=[1, 1], groups=1, name="x.1")
    %input2.1: (1, 1

xta0

/*
  The "hello world" of neural networks: a simple 3-layer feed-forward
  network that implements an XOR logic gate.

  The first layer is the input layer. It has two neurons a and b, which
  are the two inputs to the XOR gate.

  The middle layer is the hidden layer. This has two neurons h1, h2 that
  will learn what it means to be an XOR gate.
 

xta0

xta0

#encoding:utf-8

require 'json'
require 'ostruct'

=begin
mock_validation.rb
created by Tao Xu on 02/08/2019 
taoxu.dev@gmail.com

xta0

import os
import string
import argparse
import re
import json
import time
from enum import Enum

"""
mock_validation.py

xta0

- (CGSize)sizeThatFits:(CGSize)size
{
    return CGSizeMake(size.width,
                      [_name sizeThatFits:CGSizeMake(size.width, CGFLOAT_MAX)].height
                      + [_content sizeThatFits:CGSizeMake(size.width, CGFLOAT_MAX)].height
                      + 30 );//padding
}


- (void)layoutSubviews{