کانولوشن یک تصویر درتنسورفلو

Question

سلام
من با توجه به اموزش هایgithub می خوام یک تصویر رو به یک لایه کانولشنی در تنسوفلو بدم.عکس من 32*32 و رنگی هست.بنابراین reshape کردم
%matplotlib inline
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
from sklearn.metrics import confusion_matrix
import time
from datetime import timedelta
import math

مشخصات کرنل

filter_size1 = 5 # Convolution filters are 5 x 5 pixels.
num_filters1 = 16 # There are 16 of these filters.

Convolutional Layer 2.

filter_size2 = 5 # Convolution filters are 5 x 5 pixels.
num_filters2 = 36 # There are 36 of these filters.

Fully-connected layer.

fc_size = 128 # Number of neurons in fully-connected layer.

مشخصات عکس

img_size = 32

Images are stored in one-dimensional arrays of this length.

img_size_flat = img_size * img_size

Tuple with height and width of images used to reshape arrays.

img_shape = (img_size, img_size)

Number of colour channels for the images: 1 channel for gray-scale.

num_channels = 3

تابع برای کانوالو کردن

def new_conv_layer(input, # The previous layer.

               num_input_channels, # Num. channels in prev. layer.
               filter_size,        # Width and height of each filter.
               num_filters,        # Number of filters.
               use_pooling=True):  # Use 2x2 max-pooling.

# Shape of the filter-weights for the convolution.
# This format is determined by the TensorFlow API.
shape = [filter_size, filter_size, num_input_channels, num_filters]

# Create new weights aka. filters with the given shape.
weights = new_weights(shape=shape)

# Create new biases, one for each filter.
biases = new_biases(length=num_filters)

# Create the TensorFlow operation for convolution.
# Note the strides are set to 1 in all dimensions.
# The first and last stride must always be 1,
# because the first is for the image-number and
# the last is for the input-channel.
# But e.g. strides=[1, 2, 2, 1] would mean that the filter
# is moved 2 pixels across the x- and y-axis of the image.
# The padding is set to 'SAME' which means the input image
# is padded with zeroes so the size of the output is the same.
layer = tf.nn.conv2d(input=input,
                     filter=weights,
                     strides=[1, 1, 1, 1],
                     padding='SAME')

# Add the biases to the results of the convolution.
# A bias-value is added to each filter-channel.
layer += biases

# Use pooling to down-sample the image resolution?
if use_pooling:
    # This is 2x2 max-pooling, which means that we
    # consider 2x2 windows and select the largest value
    # in each window. Then we move 2 pixels to the next window.
    layer = tf.nn.max_pool(value=layer,
                           ksize=[1, 2, 2, 1],
                           strides=[1, 2, 2, 1],
                           padding='SAME')

# Rectified Linear Unit (ReLU).
# It calculates max(x, 0) for each input pixel x.
# This adds some non-linearity to the formula and allows us
# to learn more complicated functions.
layer = tf.nn.relu(layer)

# Note that ReLU is normally executed before the pooling,
# but since relu(max_pool(x)) == max_pool(relu(x)) we can
# save 75% of the relu-operations by max-pooling first.

# We return both the resulting layer and the filter-weights
# because we will plot the weights later.
return layer, weights

وزن ها

def new_weights(shape):

return tf.Variable(tf.truncated_normal(shape, stddev=0.05))

def new_biases(length):

return tf.Variable(tf.constant(0.05, shape=[length]))

ریختن تصویر در یک placeholder و reshape

x = tf.placeholder(tf.float32, shape=[None, img_size_flat], name='x')
x_image = tf.reshape(x, [-1, img_size, img_size, num_channels])

لایه کانولوشن

layer_conv1, weights_conv1 = \

new_conv_layer(input=x_image,
               num_input_channels=num_channels,
               filter_size=filter_size1,
               num_filters=num_filters1,
               use_pooling=True)

سوال من اینه آیا روند کارم درسته و آیا تصویر رو درست به لایه اول دارم میدم یا خیر؟
ممنون