Last active
November 25, 2023 23:46
-
-
Save yardstick17/22c02363c5e04763373b588f1a3bceeb to your computer and use it in GitHub Desktop.
Spatial pyramid pooling (SPP) is a pooling strategy to result in an output of fixed size. It will turn a 2D input of arbitrary size into an output of fixed dimension. Hence, the convolutional part of a DNN can be connected to a dense part with a fixed number of nodes even if the dimensions of the input image are unknown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CUSTOM_OUTPUT_CATEGORIES = 2 | |
import keras.backend as K | |
from keras.engine.topology import Layer | |
class SpatialPyramidPooling(Layer): | |
'''Spatial pyramid pooling layer for 2D inputs. | |
See Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, | |
K. He, X. Zhang, S. Ren, J. Sun | |
# Arguments | |
pool_list: list of int | |
List of pooling regions to use. The length of the list is the number of pooling regions, | |
each int in the list is the number of regions in that pool. For example [1,2,4] would be 3 | |
regions with 1, 2x2 and 4x4 max pools, so 21 outputs per feature map | |
# Input shape | |
4D tensor with shape: | |
`(samples, channels, rows, cols)` if dim_ordering='th' | |
or 4D tensor with shape: | |
`(samples, rows, cols, channels)` if dim_ordering='tf'. | |
# Output shape | |
2D tensor with shape: | |
`(samples, channels * sum([i * i for i in pool_list])` | |
''' | |
def __init__(self, pool_list, **kwargs): | |
self.dim_ordering = K.image_dim_ordering() | |
assert self.dim_ordering in {'tf', 'th'}, 'dim_ordering must be in {tf, th}' | |
self.pool_list = pool_list | |
self.num_outputs_per_channel = sum([i * i for i in pool_list]) | |
super(SpatialPyramidPooling, self).__init__(**kwargs) | |
def build(self, input_shape): | |
if self.dim_ordering == 'th': | |
self.nb_channels = input_shape[1] | |
elif self.dim_ordering == 'tf': | |
self.nb_channels = input_shape[3] | |
def get_output_shape_for(self, input_shape): | |
return (input_shape[0], self.nb_channels * self.num_outputs_per_channel) | |
def get_config(self): | |
config = {'pool_list': self.pool_list} | |
base_config = super(SpatialPyramidPooling, self).get_config() | |
return dict(list(base_config.items()) + list(config.items())) | |
def call(self, x, mask=None): | |
input_shape = K.shape(x) | |
if self.dim_ordering == 'th': | |
num_rows = input_shape[2] | |
num_cols = input_shape[3] | |
elif self.dim_ordering == 'tf': | |
num_rows = input_shape[1] | |
num_cols = input_shape[2] | |
row_length = [K.cast(num_rows, 'float32') / i for i in self.pool_list] | |
col_length = [K.cast(num_cols, 'float32') / i for i in self.pool_list] | |
outputs = [] | |
if self.dim_ordering == 'th': | |
for pool_num, num_pool_regions in enumerate(self.pool_list): | |
for jy in range(num_pool_regions): | |
for ix in range(num_pool_regions): | |
x1 = ix * col_length[pool_num] | |
x2 = ix * col_length[pool_num] + col_length[pool_num] | |
y1 = jy * row_length[pool_num] | |
y2 = jy * row_length[pool_num] + row_length[pool_num] | |
x1 = K.cast(K.round(x1), 'int32') | |
x2 = K.cast(K.round(x2), 'int32') | |
y1 = K.cast(K.round(y1), 'int32') | |
y2 = K.cast(K.round(y2), 'int32') | |
new_shape = [input_shape[0], input_shape[1], | |
y2 - y1, x2 - x1] | |
x_crop = x[:, :, y1:y2, x1:x2] | |
xm = K.reshape(x_crop, new_shape) | |
pooled_val = K.max(xm, axis=(2, 3)) | |
outputs.append(pooled_val) | |
elif self.dim_ordering == 'tf': | |
for pool_num, num_pool_regions in enumerate(self.pool_list): | |
for jy in range(num_pool_regions): | |
for ix in range(num_pool_regions): | |
x1 = ix * col_length[pool_num] | |
x2 = ix * col_length[pool_num] + col_length[pool_num] | |
y1 = jy * row_length[pool_num] | |
y2 = jy * row_length[pool_num] + row_length[pool_num] | |
x1 = K.cast(K.round(x1), 'int32') | |
x2 = K.cast(K.round(x2), 'int32') | |
y1 = K.cast(K.round(y1), 'int32') | |
y2 = K.cast(K.round(y2), 'int32') | |
new_shape = [input_shape[0], y2 - y1, | |
x2 - x1, input_shape[3]] | |
x_crop = x[:, y1:y2, x1:x2, :] | |
xm = K.reshape(x_crop, new_shape) | |
pooled_val = K.max(xm, axis=(1, 2)) | |
outputs.append(pooled_val) | |
if self.dim_ordering == 'th': | |
outputs = K.concatenate(outputs) | |
elif self.dim_ordering == 'tf': | |
# outputs = K.concatenate(outputs,axis = 1) | |
outputs = K.concatenate(outputs) | |
# outputs = K.reshape(outputs,(len(self.pool_list),self.num_outputs_per_channel,input_shape[0],input_shape[1])) | |
# outputs = K.permute_dimensions(outputs,(3,1,0,2)) | |
# outputs = K.reshape(outputs,(input_shape[0], self.num_outputs_per_channel * self.nb_channels)) | |
return outputs | |
def Spp(): | |
# uses theano ordering. Note that we leave the image size as None to allow multiple image sizes | |
model = Sequential() | |
model.add(Convolution2D(96, 11, 11, border_mode='same', input_shape=(3, None, None), activation='relu')) | |
model.add(MaxPooling2D(pool_size=(2, 2))) | |
model.add(Convolution2D(32, 3, 3, activation='relu')) | |
model.add(MaxPooling2D(pool_size=(2, 2))) | |
model.add(Convolution2D(64, 3, 3, border_mode='same', activation='relu')) | |
model.add(MaxPooling2D(pool_size=(2, 2))) | |
model.add(Convolution2D(64, 3, 3, activation='relu')) | |
model.add(MaxPooling2D(pool_size=(2, 2))) | |
model.add(SpatialPyramidPooling([1, 2, 4])) | |
model.add(Dense(4096, activation='relu', name='dense_1')) | |
model.add(Dropout(0.5)) | |
model.add(Dense(4096, activation='relu', name='dense_2')) | |
model.add(Dropout(0.5)) | |
model.add(Dense(CUSTOM_OUTPUT_CATEGORIES, name='dense_3')) | |
model.add(Activation('softmax')) | |
return model |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
It builds the following model (output_categories = 1,
input_shape=(None, None, 3)
), so the logits shape is(?,?,?,1)
ValueError: logits and labels must have the same shape ((?, 1) vs (?, ?, ?, ?))