solaris33

# -*- coding: utf-8 -*-

# MNIST 데이터를 다운로드 한다.
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

# TensorFlow 라이브러리를 추가한다.
import tensorflow as tf

# 변수들을 설정한다.

solaris33

# -*- coding: utf-8 -*-

# 절대 임포트 설정
from __future__ import absolute_import
from __future__ import print_function

# 필요한 라이브러리들을 임포트
import collections
import math
import os

solaris33

# -*- coding: utf-8 -*-
# Inception-v3 모델을 이용한 Image Classification

# 절대 임포트 설정
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

# 필요한 라이브러리들을 임포트
import os.path

solaris33

"""
  TensorFlow translation of the torch example found here (written by SeanNaren).
  https://github.com/SeanNaren/TorchQLearningExample

  Original keras example found here (written by Eder Santana).
  https://gist.github.com/EderSantana/c7222daa328f0e885093#file-qlearn-py-L164

  The agent plays a game of catch. Fruits drop from the sky and the agent can choose the actions
  left/stay/right to catch the fruit before it reaches the ground.
"""

solaris33

# To run this code you must use iPython. Also you can use the .ipynb file in ipython notebook mode.

%matplotlib
%matplotlib inline

from TrainCatchGame import CatchEnvironment, X, W1, b1, input_layer, W2, b2, hidden_layer, W3, b3, output_layer, Y, cost, optimizer
from IPython import display
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import pylab as pl

solaris33

# boilerplate code
from __future__ import print_function
import os
from io import BytesIO
import numpy as np
from functools import partial
import PIL.Image
from IPython.display import clear_output, Image, display, HTML

import tensorflow as tf

solaris33

model_fn = 'tensorflow_inception_graph.pb'

# creating TensorFlow session and loading the model
graph = tf.Graph()
sess = tf.InteractiveSession(graph=graph)
with tf.gfile.FastGFile(model_fn, 'rb') as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())
t_input = tf.placeholder(np.float32, name='input') # define the input tensor
imagenet_mean = 117.0

solaris33

layers = [op.name for op in graph.get_operations() if op.type=='Conv2D' and 'import/' in op.name]
feature_nums = [int(graph.get_tensor_by_name(name+':0').get_shape()[-1]) for name in layers]

print('Number of layers', len(layers))
print('Total number of feature channels:', sum(feature_nums))


# Helper functions for TF Graph visualization

def strip_consts(graph_def, max_const_size=32):

solaris33

# Picking some internal layer. Note that we use outputs before applying the ReLU nonlinearity
# to have non-zero gradients for features with negative initial activations.
layer = 'mixed4d_3x3_bottleneck_pre_relu'
channel = 139 # picking some feature channel to visualize

# start with a gray image with a little noise
img_noise = np.random.uniform(size=(224,224,3)) + 100.0

def showarray(a, fmt='jpeg'):
    a = np.uint8(np.clip(a, 0, 1)*255)

solaris33

def tffunc(*argtypes):
    '''Helper that transforms TF-graph generating function into a regular one.
    See "resize" function below.
    '''
    placeholders = list(map(tf.placeholder, argtypes))
    def wrap(f):
        out = f(*placeholders)
        def wrapper(*args, **kw):
            return out.eval(dict(zip(placeholders, args)), session=kw.get('session'))
        return wrapper