rocking5566

import sys

sys.path.append("/opt/tf_model/research")
sys.path.append("/opt/tf_model/research/object_detection")

import os
import cv2
import numpy as np
import tensorflow as tf
from utils import label_map_util

rocking5566

#include <math.h>

using namespace std;
using namespace cv;

cv::Mat GetMask(const Mat& img)
{
    Mat ret;
    Mat imgGray;
    cvtColor(img, imgGray, CV_BGR2GRAY);

rocking5566

#include <iostream>
#include <vector>

using namespace std;
typedef vector< vector<float>> matrix;

void PrintMatrix(const matrix& mat)
{
    for (int i = 0, row = mat.size(); i < row; ++i)
    {

rocking5566

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import sys

from PIL import Image
import numpy as np
import tensorflow as tf

rocking5566

import numpy as np
import tensorflow as tf
from tensorflow.keras.datasets import mnist
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation, Conv2D, Flatten
from tensorflow.keras.optimizers import RMSprop

# download the mnist to the path '~/.keras/datasets/' if it is the first time to be called
# X shape (60,000 28x28), y shape (10,000, )

rocking5566

import numpy as np


def batchnorm_forward(x, gamma, beta, eps):
    N, D = x.shape

    # step1: calculate mean
    mu = 1./N * np.sum(x, axis=0)

    # step2: subtract mean vector of every trainings example

rocking5566

import numpy as np
import torch


def layernorm_forward(x, gamma, beta, eps):
    out, cache = None, None
    M, _ = x.shape
    x_mean = np.mean(x, axis=1).reshape(M, 1)
    x_var = np.var(x, axis=1).reshape(M, 1)