Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Expose seed parameter to weight initialization #15

Merged
merged 2 commits into from
Apr 21, 2024
Merged

Expose seed parameter to weight initialization #15

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e78536d
Expose seed parameter to weight initialization
mhuen Apr 21, 2024
6acd74d
Set seed to dropout
mhuen Apr 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 14 additions & 11 deletions tfscripts/compat/v1/conv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,6 +239,7 @@ def locally_connected_2d(
strides=[1, 1],
padding="SAME",
dilation_rate=None,
seed=None,
):
"""
Like conv2d, but doesn't share weights.
Expand All @@ -261,10 +262,11 @@ def locally_connected_2d(
The stride of the sliding window for each dimension of input.
padding : A string from: "SAME", "VALID".
The type of padding algorithm to use.

dilation_rate : None or list of int of length 2
[dilattion in x, dilation in y]
defines dilattion rate to be used
seed : None or int
Seed for the random number generator.

Returns
-------
Expand Down Expand Up @@ -316,7 +318,9 @@ def locally_connected_2d(
# fast shortcut
if list(filter_size) == [1, 1]:
if kernel is None:
kernel = new_weights(shape=input_shape[1:] + [num_outputs])
kernel = new_weights(
shape=input_shape[1:] + [num_outputs], seed=seed
)
output = tf.reduce_sum(
input_tensor=tf.expand_dims(input, axis=4) * kernel, axis=3
)
Expand Down Expand Up @@ -412,7 +416,7 @@ def locally_connected_2d(
# get kernel
# ------------------
if kernel is None:
kernel = new_weights(shape=kernel_shape)
kernel = new_weights(shape=kernel_shape, seed=seed)

# ------------------
# perform convolution
Expand All @@ -431,6 +435,7 @@ def locally_connected_3d(
strides=[1, 1, 1],
padding="SAME",
dilation_rate=None,
seed=None,
):
"""
Like conv3d, but doesn't share weights.
Expand All @@ -456,6 +461,8 @@ def locally_connected_3d(
dilation_rate : None or list of int of length 3
[dilattion in x, dilation in y, dilation in z]
defines dilattion rate to be used
seed : None or int
Seed for the random number generator.

Returns
-------
Expand Down Expand Up @@ -507,7 +514,9 @@ def locally_connected_3d(
# fast shortcut
if list(filter_size) == [1, 1, 1]:
if kernel is None:
kernel = new_weights(shape=input_shape[1:] + [num_outputs])
kernel = new_weights(
shape=input_shape[1:] + [num_outputs], seed=seed
)
output = tf.reduce_sum(
input_tensor=tf.expand_dims(input, axis=5) * kernel, axis=4
)
Expand Down Expand Up @@ -628,7 +637,7 @@ def locally_connected_3d(
# get kernel
# ------------------
if kernel is None:
kernel = new_weights(shape=kernel_shape)
kernel = new_weights(shape=kernel_shape, seed=seed)

# ------------------
# perform convolution
Expand Down Expand Up @@ -663,30 +672,24 @@ def local_translational3d_trafo(
float32, float64, int64, int32, uint8, uint16, int16, int8, complex64,
complex128, qint8, quint8, qint32, half.
Shape [batch, in_depth, in_height, in_width, in_channels].

num_outputs : int
Number of output channels

filter_size : list of int of size 3
[filter x size, filter y size, filter z size]

fcn : callable: fcn(input_patch)
Defines the transformation:
input_patch -> output
with output.shape = [-1, num_outputs]

weights : None, optional
Description
strides : A list of ints that has length >= 5. 1-D tensor of length 5.
The stride of the sliding window for each dimension of input.
Must have strides[0] = strides[4] = 1.
padding : A string from: "SAME", "VALID".
The type of padding algorithm to use.

dilation_rate :None or list of int of length 3
[dilattion in x, dilation in y, dilation in z]
defines dilattion rate to be used

is_training : bool, optional
Indicates whether currently in training or inference mode.
True: in training mode
Expand Down
26 changes: 17 additions & 9 deletions tfscripts/compat/v1/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,12 @@


def add_residual(
input, residual, strides=None, use_scale_factor=True, scale_factor=0.001
input,
residual,
strides=None,
use_scale_factor=True,
scale_factor=0.001,
seed=None,
):
"""Convenience function to add a residual

Expand All @@ -39,6 +44,8 @@ def add_residual(
scale_factor : float, optional
Defines how much the residuals will be scaled prior to addition if
use_scale_factor is True.
seed : int, optional
Seed for the random number generator.

Returns
-------
Expand Down Expand Up @@ -78,7 +85,7 @@ def add_residual(
# Residuals added over multiple layers accumulate.
# A scale factor < 1 reduces instabilities in beginning
if use_scale_factor:
scale = new_weights([num_outputs], stddev=scale_factor)
scale = new_weights([num_outputs], stddev=scale_factor, seed=seed)
residual = residual * scale
if num_inputs == num_outputs:
output = residual + input
Expand Down Expand Up @@ -115,6 +122,7 @@ def activation(
use_batch_normalisation=False,
is_training=None,
verbose=True,
seed=None,
):
"""
Helper-functions to perform activation on a layer
Expand Down Expand Up @@ -218,16 +226,16 @@ def activation(
)

elif activation_type == "prelu":
slope = new_weights(layer.get_shape().as_list()[1:]) + 1.0
slope = new_weights(layer.get_shape().as_list()[1:], seed=seed) + 1.0
layer = tf.where(
tf.less(layer, tf.constant(0, dtype=FLOAT_PRECISION)),
layer * slope,
layer,
)

elif activation_type == "pelu":
a = new_weights(layer.get_shape().as_list()[1:]) + 1.0
b = new_weights(layer.get_shape().as_list()[1:]) + 1.0
a = new_weights(layer.get_shape().as_list()[1:], seed=seed) + 1.0
b = new_weights(layer.get_shape().as_list()[1:], seed=seed + 1) + 1.0
layer = tf.where(
tf.less(layer, tf.constant(0, dtype=FLOAT_PRECISION)),
(tf.exp(layer / b) - 1) * a,
Expand All @@ -238,10 +246,10 @@ def activation(
layer = tf.exp(-tf.square(layer))

elif activation_type == "pgaussian":
sigma = new_weights(layer.get_shape().as_list()[1:]) + tf.constant(
1.0, dtype=FLOAT_PRECISION
)
mu = new_weights(layer.get_shape().as_list()[1:])
sigma = new_weights(
layer.get_shape().as_list()[1:], seed=seed
) + tf.constant(1.0, dtype=FLOAT_PRECISION)
mu = new_weights(layer.get_shape().as_list()[1:], seed=seed + 1)
layer = tf.exp(
tf.square((layer - mu) / sigma)
* tf.constant(-0.5, dtype=FLOAT_PRECISION)
Expand Down
Loading