total_train = []
total_regions = []
total_asfmap = []
bbox = [(45, 90), (90, 45), (64, 64), (90, 180), (180, 90), (128, 128),
(181, 362), (362, 181), (256, 256), (362, 724), (724, 362), (512, 512)]
conv_height = 14
conv_width = 14
height = 600
width = 800
k = 12
gt_num = 10
feat_input = tf.placeholder(tf.float32, [None, conv_height, conv_width, 512])
with tf.variable_scope('rcnn', reuse=None):
W_conv6 = weight_variable([3, 3, 512, 256], name="W_conv6")
b_conv6 = bias_variable([256], name="b_conv6")
feat = conv2d(feat_input, W_conv6) + b_conv6
W_offset = weight_variable([1, 1, 256, k * 4], name="W_offset")
b_offset = bias_variable([k * 4], name="b_offset")
offset = conv2d(feat, W_offset) + b_offset
offset = tf.reshape(offset, [k * conv_height * conv_width, 4])
W_score = weight_variable([1, 1, 256, k], name="W_score")
b_score = bias_variable([k], name="b_score")
score = conv2d(feat, W_score) + b_score
score = tf.reshape(score, [k * conv_height * conv_width])
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
# Weights and biases
weights = {
'wc1': func.weight_variable([5,5,1,10], 0.2, 0.0),
'wi1': {
'direct1x1': func.weight_variable([1,1,10,20], 0.2, 0.0),
'1x1pre3x3': func.weight_variable([1,1,10,10], 0.2, 0.0),
'1x1pre5x5': func.weight_variable([1,1,10,5], 0.2, 0.0),
'3x3': func.weight_variable([3,3,10,30], 0.2, 0.0),
'5x5': func.weight_variable([5,5,5,10], 0.2, 0.0)
},
'wd1': func.weight_variable([7*7*(20+30+10), 100], 0.2, 0.1),
'out': func.weight_variable([100,n_classes], 0.2, 0.1)
}
biases = {
'bc1': func.bias_variable([10]),
'bi1': {
'direct1x1': func.bias_variable([20]),
'1x1pre3x3': func.bias_variable([10]),
'1x1pre5x5': func.bias_variable([5]),
'3x3': func.bias_variable([30]),
'5x5': func.bias_variable([10])
},
'bd1': func.bias_variable([100]),
'out': func.bias_variable([10])
}
# Construct the model
pred = func.inception_net(x, weights, biases, keep_prob)
# Definte loss and optimizer
# Weights and biases
weights = {
"wc1": func.weight_variable([3, 3, 1, 10], 0.2, 0.0),
"wc2": func.weight_variable([3, 3, 60, 60], 0.2, 0.0),
"wi1": {
"direct1x1": func.weight_variable([1, 1, 10, 20], 0.2, 0.0),
"1x1pre3x3": func.weight_variable([1, 1, 10, 10], 0.2, 0.0),
"1x1pre5x5": func.weight_variable([1, 1, 10, 5], 0.2, 0.0),
"3x3": func.weight_variable([3, 3, 10, 30], 0.2, 0.0),
"5x5": func.weight_variable([5, 5, 5, 10], 0.2, 0.0),
},
"out": func.weight_variable([5 * 5 * (20 + 30 + 10), dim_mask], 0.2, 0.1),
}
biases = {
"bc1": func.bias_variable([10]),
"bc2": func.bias_variable([60]),
"bi1": {
"direct1x1": func.bias_variable([20]),
"1x1pre3x3": func.bias_variable([10]),
"1x1pre5x5": func.bias_variable([5]),
"3x3": func.bias_variable([30]),
"5x5": func.bias_variable([10]),
},
"out": func.bias_variable([dim_mask]),
}
# Construct the model
mask_output = func.detection_network(x, weights, biases, keep_prob)
# Definte loss and optimizer
if arg else white[m]) > (0.99 * black_max if arg else 0.99 *
white_max): # 0.95这个参数请多调整，对应下面的0.05
end_ = m
break
return end_
#########################前向网络##########################################
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 28, 28, 1]) # 28x28
x_image = tf.reshape(xs, [-1, 28, 28, 1])
## conv1 layer ##
W_conv1 = func.weight_variable([5, 5, 1,
32]) # patch 5x5, in size 1, out size 32
b_conv1 = func.bias_variable([32])
h_conv1 = tf.nn.relu(func.conv2d(x_image, W_conv1) +
b_conv1) # output size 28x28x32
h_pool1 = func.max_pool_2x2(h_conv1) # output size 14x14x32
## conv2 layer ##
W_conv2 = func.weight_variable([5, 5, 32,
64]) # patch 5x5, in size 32, out size 64
b_conv2 = func.bias_variable([64])
h_conv2 = tf.nn.relu(func.conv2d(h_pool1, W_conv2) +
b_conv2) # output size 14x14x64
h_pool2 = func.max_pool_2x2(h_conv2) # output size 7x7x64
## fc1 layer ##
W_fc1 = func.weight_variable([7 * 7 * 64, 1024])
b_fc1 = func.bias_variable([1024])
# Weights and biases
weights = {
'wc1': func.weight_variable([3,3,1,10], 0.2, 0.0),
'wc2': func.weight_variable([3,3,60,60], 0.2, 0.0),
'wi1': {
'direct1x1': func.weight_variable([1,1,10,20], 0.2, 0.0),
'1x1pre3x3': func.weight_variable([1,1,10,10], 0.2, 0.0),
'1x1pre5x5': func.weight_variable([1,1,10,5], 0.2, 0.0),
'3x3': func.weight_variable([3,3,10,30], 0.2, 0.0),
'5x5': func.weight_variable([5,5,5,10], 0.2, 0.0)
},
'out': func.weight_variable([5*5*(20+30+10), dim_mask], 0.2, 0.1),
}
biases = {
'bc1': func.bias_variable([10]),
'bc2': func.bias_variable([60]),
'bi1': {
'direct1x1': func.bias_variable([20]),
'1x1pre3x3': func.bias_variable([10]),
'1x1pre5x5': func.bias_variable([5]),
'3x3': func.bias_variable([30]),
'5x5': func.bias_variable([10])
},
'out': func.bias_variable([dim_mask])
}
# Construct the model
mask_output = func.detection_network(x, weights, biases, keep_prob)
# Definte loss and optimizer
