Skip to content
Snippets Groups Projects
Commit 20433b52 authored by tomrink's avatar tomrink
Browse files

snapshot...

parent 57f221e8
No related branches found
No related tags found
No related merge requests found
...@@ -104,6 +104,32 @@ def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn. ...@@ -104,6 +104,32 @@ def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.
return conv return conv
def build_residual_block_1x1(input_layer, num_filters, activation, block_name, padding='SAME', drop_rate=0.5,
do_drop_out=True, do_batch_norm=True):
with tf.name_scope(block_name):
skip = input_layer
if do_drop_out:
input_layer = tf.keras.layers.Dropout(drop_rate)(input_layer)
if do_batch_norm:
input_layer = tf.keras.layers.BatchNormalization()(input_layer)
conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=activation)(input_layer)
print(conv.shape)
if do_drop_out:
conv = tf.keras.layers.Dropout(drop_rate)(conv)
if do_batch_norm:
conv = tf.keras.layers.BatchNormalization()(conv)
conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=None)(conv)
conv = conv + skip
conv = tf.keras.layers.LeakyReLU()(conv)
print(conv.shape)
return conv
class CNN: class CNN:
def __init__(self): def __init__(self):
...@@ -286,15 +312,15 @@ class CNN: ...@@ -286,15 +312,15 @@ class CNN:
if np.sum(np.isnan(cell)) == 0: if np.sum(np.isnan(cell)) == 0:
cnt = np.sum(cell[t, :, ] == 1.0) cnt = np.sum(cell[t, :, ] == 1.0)
if cnt == 0: if cnt == 0:
grd_down_2x[t, j, i] = 1 grd_down_2x[t, j, i] = 0
elif cnt == 1: elif cnt == 1:
grd_down_2x[t, j, i] = 2 grd_down_2x[t, j, i] = 1
elif cnt == 2: elif cnt == 2:
grd_down_2x[t, j, i] = 3 grd_down_2x[t, j, i] = 2
elif cnt == 3: elif cnt == 3:
grd_down_2x[t, j, i] = 4 grd_down_2x[t, j, i] = 3
elif cnt == 4: elif cnt == 4:
grd_down_2x[t, j, i] = 5 grd_down_2x[t, j, i] = 4
pass pass
else: else:
grd_down_2x[t, j, i] = 0 grd_down_2x[t, j, i] = 0
...@@ -407,7 +433,7 @@ class CNN: ...@@ -407,7 +433,7 @@ class CNN:
activation = tf.nn.relu activation = tf.nn.relu
momentum = 0.99 momentum = 0.99
num_filters = 64 num_filters = 32
input_2d = self.inputs[0] input_2d = self.inputs[0]
print('input: ', input_2d.shape) print('input: ', input_2d.shape)
...@@ -415,7 +441,7 @@ class CNN: ...@@ -415,7 +441,7 @@ class CNN:
conv = input_2d conv = input_2d
print('input: ', conv.shape) print('input: ', conv.shape)
conv = conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, kernel_initializer='he_uniform', activation=activation, padding='SAME')(input_2d) conv = conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=2, strides=1, kernel_initializer='he_uniform', activation=activation, padding='SAME')(input_2d)
print(conv.shape) print(conv.shape)
if NOISE_TRAINING: if NOISE_TRAINING:
...@@ -423,22 +449,17 @@ class CNN: ...@@ -423,22 +449,17 @@ class CNN:
scale = 0.2 scale = 0.2
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_1', scale=scale) conv_b = build_residual_block_1x1(conv_b, num_filters, 'Residual_Block_1')
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_2', scale=scale)
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_3', scale=scale)
# conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_4', scale=scale)
# conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_5', scale=scale) conv_b = build_residual_block_1x1(conv_b, num_filters, 'Residual_Block_2')
conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, kernel_initializer='he_uniform', padding=padding)(conv_b) conv_b = build_residual_block_1x1(conv_b, num_filters, 'Residual_Block_3')
conv = conv + conv_b # conv = conv + conv_b
conv = conv_b
print(conv.shape) print(conv.shape)
self.logits = tf.keras.layers.Conv2D(1, kernel_size=3, strides=1, padding=padding, name='regression')(conv) self.logits = tf.keras.layers.Conv2D(NumLogits, kernel_size=1, strides=1, padding=padding, name='regression')(conv)
print(self.logits.shape) print(self.logits.shape)
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment