daa233

#
# A simple makefile for managing build of project composed of C source files.
# References: https://web.stanford.edu/class/cs107/resources/make
#


# It is likely that default C compiler is already gcc, but explicitly
# set, just to be sure
CC = gcc

daa233

# Convert an numpy array image to bytes and decode it with tensorflow.
# Refers to https://stackoverflow.com/questions/50630045/how-to-turn-numpy-array-image-to-bytes/50630390

import numpy as np
import cv2
import tensorflow as tf

# img_bgr is an 16-bit BGR image
img_bgr = (np.random.rand(50, 50, 3)*65536).astype(np.uint16)
cv2.imwrite('demo.png', img_bgr, params=[cv2.CV_16U])

daa233

import numpy as np
from sklearn.manifold import TSNE
from matplotlib import pyplot as plt

def draw_tsne(X, y, save_fig=None, show=False):
    """
    T-SNE visualization by `sklearn.manifold.TSNE`.
    Reference: https://www.scipy-lectures.org/packages/scikit-learn/auto_examples/plot_tsne.html
    :param X: data to be projected
    :param y: data labels

daa233

n02119789 1 kit_fox
n02100735 2 English_setter
n02110185 3 Siberian_husky
n02096294 4 Australian_terrier
n02102040 5 English_springer
n02066245 6 grey_whale
n02509815 7 lesser_panda
n02124075 8 Egyptian_cat
n02417914 9 ibex
n02123394 10 Persian_cat

daa233

#################### MS_SSIM Loss #####################
## ref code: https://stackoverflow.com/questions/39051451/ssim-ms-ssim-for-tensorflow
def _tf_fspecial_gauss(size, sigma):
    """Function to mimic the 'fspecial' gaussian MATLAB function
    """
    x_data, y_data = np.mgrid[-size//2 + 1:size//2 + 1, -size//2 + 1:size//2 + 1]

    x_data = np.expand_dims(x_data, axis=-1)
    x_data = np.expand_dims(x_data, axis=-1)

daa233

TOTAL_VARIATION_SMOOTHING = 1.5

# Compute total variation regularization loss term given a variable image (x) and its shape
def get_total_variation(x, shape):
    with tf.name_scope('get_total_variation'):
        # Get the dimensions of the variable image
        height = shape[1]
        width = shape[2]
        size = reduce(lambda a, b: a * b, shape) ** 2

daa233

# ~/.profile: executed by the command interpreter for login shells.
# This file is not read by bash(1), if ~/.bash_profile or ~/.bash_login
# exists.
# see /usr/share/doc/bash/examples/startup-files for examples.
# the files are located in the bash-doc package.

# the default umask is set in /etc/profile; for setting the umask
# for ssh logins, install and configure the libpam-umask package.
#umask 022

daa233

# ~/.bashrc: executed by bash(1) for non-login shells.
# see /usr/share/doc/bash/examples/startup-files (in the package bash-doc)
# for examples

# If not running interactively, don't do anything
case $- in
    *i*) ;;
      *) return;;
esac

daa233

注意：本文内容适用于 Tmux 2.3 及以上的版本，不计划兼容低版本。

Tmux 快捷键 & 速查表

启动新会话：

tmux [new -s 会话名 -n 窗口名]

恢复会话：

daa233

import numpy as np
from sklearn.manifold import TSNE
from matplotlib import pyplot as plt


def draw_tsne(X, y, save_fig=None, show=False):
    """
    T-SNE visualization by `sklearn.manifold.TSNE`.
    Reference: https://www.scipy-lectures.org/packages/scikit-learn/auto_examples/plot_tsne.html
    :param X: data to be projected