mirror of
https://github.com/wassname/PSPNet-Keras-tensorflow.git
synced 2026-09-09 11:15:19 +08:00
Merge pull request #10 from jmtatsch/master
Added support for pspnet100_cityscapes
This commit is contained in:
VladKry
+4
-1
@@ -1,4 +1,7 @@
|
||||
*.npy
|
||||
*.pyc
|
||||
*.png
|
||||
|
||||
*.caffemodel
|
||||
*.prototxt
|
||||
*.h5
|
||||
*.json
|
||||
|
||||
@@ -1,43 +1,57 @@
|
||||
# Keras implementation of [PSPNet(caffe)](https://github.com/hszhao/PSPNet)
|
||||
|
||||
Implemented Architecture of pyramid scene parsing network in Keras
|
||||
Implemented Architecture of Pyramid Scene Parsing Network in Keras.
|
||||
|
||||
Converted trained weights needed to run the network.
|
||||
Converted trained weights are needed to run the network.
|
||||
|
||||
Weights of the original caffemodel can be converted with weight_converter.py as follows:
|
||||
|
||||
Download converted weights here:
|
||||
[link:pspnet50_ade20k.npy](https://www.dropbox.com/s/ms8afun494dlh1t/pspnet50_ade20k.npy?dl=0)
|
||||
|
||||
And place in directory with pspnet50_ade20k.npy
|
||||
|
||||
Weights from caffemodel were converted by, weight_converter.py. The usage of this file is
|
||||
```bash
|
||||
python weight_converter.py <path to .prototxt> <path to .caffemodel>
|
||||
```
|
||||
Running this need to compile the original PSPNet caffe code and pycaffe.
|
||||
|
||||
Interpolation layer is implemented in code as custom layer "Interp"
|
||||
Running this needs the compiled original PSPNet caffe code and pycaffe.
|
||||
Already converted weights can be downloaded here:
|
||||
|
||||
[pspnet50_ade20k.npy](https://www.dropbox.com/s/ms8afun494dlh1t/pspnet50_ade20k.npy?dl=0)
|
||||
[pspnet101_cityscapes.npy](https://www.dropbox.com/s/b21j6hi6qql90l0/pspnet101_cityscapes.npy?dl=0)
|
||||
[pspnet101_voc2012.npy](https://www.dropbox.com/s/xkjmghsbn6sfj9k/pspnet101_voc2012.npy?dl=0)
|
||||
|
||||
npy weights should be placed in the directory weights/npy.
|
||||
|
||||
The interpolation layer is implemented as custom layer "Interp"
|
||||
|
||||
## Important
|
||||
|
||||
Results Keras:
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Pycaffe result
|
||||
|
||||
|
||||
## Dependencies:
|
||||
1. Tensorflow
|
||||
2. Keras
|
||||
3. numpy
|
||||
4. pycaffe(PSPNet)(optional)
|
||||
4. pycaffe(PSPNet)(optional for converting the weights)
|
||||
|
||||
|
||||
## Usage:
|
||||
## Usage:
|
||||
|
||||
```bash
|
||||
python pspnet.py --input-path INPUT_PATH --output-path OUTPUT_PATH
|
||||
python pspnet.py
|
||||
python pspnet.py -m pspnet101_cityscapes -i example_images/cityscapes.png -o example_results/cityscapes.jpg
|
||||
python pspnet.py -m pspnet101_voc2012 -i example_images/pascal_voc.jpg -o example_results/pascal_voc.jpg
|
||||
```
|
||||
|
||||
|
||||
|
Before Width: | Height: | Size: 926 KiB After Width: | Height: | Size: 926 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 103 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 75 KiB |
|
Before Width: | Height: | Size: 89 KiB After Width: | Height: | Size: 89 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 61 KiB After Width: | Height: | Size: 61 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 214 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 75 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 61 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 214 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 89 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 75 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 84 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 150 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 17 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 34 KiB |
+124
-88
@@ -1,3 +1,5 @@
|
||||
from __future__ import print_function
|
||||
from math import ceil
|
||||
from keras.layers import Conv2D, MaxPooling2D, AveragePooling2D
|
||||
from keras.layers import BatchNormalization, Activation, Input, Dropout, ZeroPadding2D, Lambda
|
||||
from keras.layers.merge import Concatenate, Add
|
||||
@@ -6,137 +8,165 @@ from keras.optimizers import SGD
|
||||
|
||||
import tensorflow as tf
|
||||
|
||||
learning_rate = 1e-3 # Layer specific learning rate
|
||||
learning_rate = 1e-3 # Layer specific learning rate
|
||||
# Weight decay not implemented
|
||||
|
||||
|
||||
def BN(name=""):
|
||||
return BatchNormalization(momentum=0.95, name=name, epsilon=1e-5)
|
||||
|
||||
def Interp(x, shape=(60,60)):
|
||||
new_height,new_width = shape
|
||||
resized = tf.image.resize_images(x, [new_height, new_width], align_corners=True)
|
||||
|
||||
def Interp(x, shape):
|
||||
from keras.backend import tf as ktf
|
||||
new_height, new_width = shape
|
||||
resized = ktf.image.resize_images(x, [new_height, new_width],
|
||||
align_corners=True)
|
||||
return resized
|
||||
|
||||
|
||||
def residual_conv(prev, level, pad=1, lvl=1, sub_lvl=1, modify_stride=False):
|
||||
lvl = str(lvl)
|
||||
sub_lvl = str(sub_lvl)
|
||||
names = ["conv"+lvl+"_"+ sub_lvl +"_1x1_reduce" ,
|
||||
"conv"+lvl+"_"+ sub_lvl +"_1x1_reduce_bn",
|
||||
"conv"+lvl+"_"+ sub_lvl +"_3x3",
|
||||
"conv"+lvl+"_"+ sub_lvl +"_3x3_bn",
|
||||
"conv"+lvl+"_"+ sub_lvl +"_1x1_increase",
|
||||
"conv"+lvl+"_"+ sub_lvl +"_1x1_increase_bn"]
|
||||
if modify_stride == False:
|
||||
prev = Conv2D(64 * level, (1,1), strides=(1,1), name=names[0], use_bias=False)(prev)
|
||||
elif modify_stride == True:
|
||||
prev = Conv2D(64 * level, (1,1), strides=(2,2), name=names[0], use_bias=False)(prev)
|
||||
names = ["conv"+lvl+"_" + sub_lvl + "_1x1_reduce",
|
||||
"conv"+lvl+"_" + sub_lvl + "_1x1_reduce_bn",
|
||||
"conv"+lvl+"_" + sub_lvl + "_3x3",
|
||||
"conv"+lvl+"_" + sub_lvl + "_3x3_bn",
|
||||
"conv"+lvl+"_" + sub_lvl + "_1x1_increase",
|
||||
"conv"+lvl+"_" + sub_lvl + "_1x1_increase_bn"]
|
||||
if modify_stride is False:
|
||||
prev = Conv2D(64 * level, (1, 1), strides=(1, 1), name=names[0],
|
||||
use_bias=False)(prev)
|
||||
elif modify_stride is True:
|
||||
prev = Conv2D(64 * level, (1, 1), strides=(2, 2), name=names[0],
|
||||
use_bias=False)(prev)
|
||||
|
||||
prev = BN(name=names[1])(prev)
|
||||
prev = Activation('relu')(prev)
|
||||
|
||||
prev = ZeroPadding2D(padding=(pad,pad))(prev)
|
||||
prev = Conv2D(64 * level, (3,3), strides=(1,1), dilation_rate=pad, name=names[2], use_bias=False)(prev)
|
||||
prev = ZeroPadding2D(padding=(pad, pad))(prev)
|
||||
prev = Conv2D(64 * level, (3, 3), strides=(1, 1), dilation_rate=pad,
|
||||
name=names[2], use_bias=False)(prev)
|
||||
|
||||
prev = BN(name=names[3])(prev)
|
||||
prev = Activation('relu')(prev)
|
||||
prev = Conv2D(256 * level, (1,1), strides=(1,1), name=names[4], use_bias=False)(prev)
|
||||
prev = Conv2D(256 * level, (1, 1), strides=(1, 1), name=names[4],
|
||||
use_bias=False)(prev)
|
||||
prev = BN(name=names[5])(prev)
|
||||
return prev
|
||||
|
||||
|
||||
def short_convolution_branch(prev, level, lvl=1, sub_lvl=1, modify_stride=False):
|
||||
lvl = str(lvl)
|
||||
sub_lvl = str(sub_lvl)
|
||||
names = ["conv"+lvl+"_"+ sub_lvl +"_1x1_proj",
|
||||
"conv"+lvl+"_"+ sub_lvl +"_1x1_proj_bn"]
|
||||
names = ["conv" + lvl+"_" + sub_lvl + "_1x1_proj",
|
||||
"conv" + lvl+"_" + sub_lvl + "_1x1_proj_bn"]
|
||||
|
||||
if modify_stride == False:
|
||||
prev = Conv2D(256 * level ,(1,1), strides=(1,1), name=names[0], use_bias=False)(prev)
|
||||
elif modify_stride == True:
|
||||
prev = Conv2D(256 * level, (1,1), strides=(2,2), name=names[0], use_bias=False)(prev)
|
||||
if modify_stride is False:
|
||||
prev = Conv2D(256 * level, (1, 1), strides=(1, 1), name=names[0],
|
||||
use_bias=False)(prev)
|
||||
elif modify_stride is True:
|
||||
prev = Conv2D(256 * level, (1, 1), strides=(2, 2), name=names[0],
|
||||
use_bias=False)(prev)
|
||||
|
||||
prev = BN(name=names[1])(prev)
|
||||
return prev
|
||||
|
||||
|
||||
def empty_branch(prev):
|
||||
return prev
|
||||
|
||||
|
||||
def residual_short(prev_layer, level, pad=1, lvl=1, sub_lvl=1, modify_stride=False):
|
||||
prev_layer = Activation('relu')(prev_layer)
|
||||
block_1 = residual_conv(prev_layer, level,
|
||||
pad=pad, lvl=lvl, sub_lvl=sub_lvl,
|
||||
modify_stride=modify_stride)
|
||||
pad=pad, lvl=lvl, sub_lvl=sub_lvl,
|
||||
modify_stride=modify_stride)
|
||||
|
||||
block_2 = short_convolution_branch(prev_layer, level,
|
||||
lvl=lvl, sub_lvl=sub_lvl,
|
||||
modify_stride=modify_stride)
|
||||
lvl=lvl, sub_lvl=sub_lvl,
|
||||
modify_stride=modify_stride)
|
||||
added = Add()([block_1, block_2])
|
||||
return added
|
||||
|
||||
|
||||
def residual_empty(prev_layer, level, pad=1, lvl=1, sub_lvl=1):
|
||||
prev_layer = Activation('relu')(prev_layer)
|
||||
|
||||
block_1 = residual_conv(prev_layer, level,
|
||||
pad=pad, lvl=lvl, sub_lvl=sub_lvl)
|
||||
block_1 = residual_conv(prev_layer, level, pad=pad,
|
||||
lvl=lvl, sub_lvl=sub_lvl)
|
||||
block_2 = empty_branch(prev_layer)
|
||||
added = Add()([block_1, block_2])
|
||||
return added
|
||||
|
||||
def ResNet(inp):
|
||||
#Names for the first couple layers of model
|
||||
|
||||
def ResNet(inp, layers):
|
||||
# Names for the first couple layers of model
|
||||
names = ["conv1_1_3x3_s2",
|
||||
"conv1_1_3x3_s2_bn",
|
||||
"conv1_2_3x3",
|
||||
"conv1_2_3x3_bn",
|
||||
"conv1_3_3x3",
|
||||
"conv1_3_3x3_bn"]
|
||||
"conv1_1_3x3_s2_bn",
|
||||
"conv1_2_3x3",
|
||||
"conv1_2_3x3_bn",
|
||||
"conv1_3_3x3",
|
||||
"conv1_3_3x3_bn"]
|
||||
|
||||
#---Short branch(only start of network)
|
||||
# Short branch(only start of network)
|
||||
|
||||
cnv1 = Conv2D(64, (3, 3), strides=(2, 2), padding='same', name=names[0], use_bias=False)(inp) # "conv1_1_3x3_s2"
|
||||
cnv1 = Conv2D(64, (3, 3), strides=(2, 2), padding='same', name=names[0],
|
||||
use_bias=False)(inp) # "conv1_1_3x3_s2"
|
||||
bn1 = BN(name=names[1])(cnv1) # "conv1_1_3x3_s2/bn"
|
||||
relu1 = Activation('relu')(bn1) #"conv1_1_3x3_s2/relu"
|
||||
relu1 = Activation('relu')(bn1) # "conv1_1_3x3_s2/relu"
|
||||
|
||||
cnv1 = Conv2D(64, (3, 3), strides=(1, 1), padding='same', name=names[2], use_bias=False)(relu1) #"conv1_2_3x3"
|
||||
bn1 = BN(name=names[3])(cnv1) #"conv1_2_3x3/bn"
|
||||
relu1 = Activation('relu')(bn1) #"conv1_2_3x3/relu"
|
||||
cnv1 = Conv2D(64, (3, 3), strides=(1, 1), padding='same', name=names[2],
|
||||
use_bias=False)(relu1) # "conv1_2_3x3"
|
||||
bn1 = BN(name=names[3])(cnv1) # "conv1_2_3x3/bn"
|
||||
relu1 = Activation('relu')(bn1) # "conv1_2_3x3/relu"
|
||||
|
||||
cnv1 = Conv2D(128, (3, 3), strides=(1, 1), padding='same', name=names[4], use_bias=False)(relu1) #"conv1_3_3x3"
|
||||
bn1 = BN(name=names[5])(cnv1) #"conv1_3_3x3/bn"
|
||||
relu1 = Activation('relu')(bn1) #"conv1_3_3x3/relu"
|
||||
cnv1 = Conv2D(128, (3, 3), strides=(1, 1), padding='same', name=names[4],
|
||||
use_bias=False)(relu1) # "conv1_3_3x3"
|
||||
bn1 = BN(name=names[5])(cnv1) # "conv1_3_3x3/bn"
|
||||
relu1 = Activation('relu')(bn1) # "conv1_3_3x3/relu"
|
||||
|
||||
res = MaxPooling2D(pool_size=(3,3), padding='same', strides=(2,2))(relu1) #"pool1_3x3_s2"
|
||||
|
||||
#---Residual layers(body of network)
|
||||
res = MaxPooling2D(pool_size=(3, 3), padding='same',
|
||||
strides=(2, 2))(relu1) # "pool1_3x3_s2"
|
||||
|
||||
# ---Residual layers(body of network)
|
||||
|
||||
"""
|
||||
Modify_stride --Used only once in first 3_1 convolutions block.
|
||||
changes stride of first convolution from 1 -> 2
|
||||
"""
|
||||
|
||||
#2_1- 2_3
|
||||
res = residual_short(res, 1, pad=1, lvl=2, sub_lvl=1)
|
||||
# 2_1- 2_3
|
||||
res = residual_short(res, 1, pad=1, lvl=2, sub_lvl=1)
|
||||
for i in range(2):
|
||||
res = residual_empty(res, 1, pad=1, lvl=2, sub_lvl=i+2)
|
||||
res = residual_empty(res, 1, pad=1, lvl=2, sub_lvl=i+2)
|
||||
|
||||
#3_1 - 3_3
|
||||
res = residual_short(res, 2, pad=1, lvl=3, sub_lvl=1, modify_stride=True)
|
||||
# 3_1 - 3_3
|
||||
res = residual_short(res, 2, pad=1, lvl=3, sub_lvl=1, modify_stride=True)
|
||||
for i in range(3):
|
||||
res = residual_empty(res, 2, pad=1, lvl=3, sub_lvl=i+2)
|
||||
res = residual_empty(res, 2, pad=1, lvl=3, sub_lvl=i+2)
|
||||
if layers is 50:
|
||||
# 4_1 - 4_6
|
||||
res = residual_short(res, 4, pad=2, lvl=4, sub_lvl=1)
|
||||
for i in range(5):
|
||||
res = residual_empty(res, 4, pad=2, lvl=4, sub_lvl=i+2)
|
||||
elif layers is 101:
|
||||
# 4_1 - 4_23
|
||||
res = residual_short(res, 4, pad=2, lvl=4, sub_lvl=1)
|
||||
for i in range(22):
|
||||
res = residual_empty(res, 4, pad=2, lvl=4, sub_lvl=i+2)
|
||||
else:
|
||||
print("This ResNet is not implemented")
|
||||
|
||||
#4_1 - 4_6
|
||||
res = residual_short(res, 4, pad=2, lvl=4, sub_lvl=1)
|
||||
for i in range(5):
|
||||
res = residual_empty(res, 4, pad=2, lvl=4, sub_lvl=i+2)
|
||||
|
||||
#5_1 - 5_3
|
||||
res = residual_short(res, 8, pad=4, lvl=5, sub_lvl=1)
|
||||
# 5_1 - 5_3
|
||||
res = residual_short(res, 8, pad=4, lvl=5, sub_lvl=1)
|
||||
for i in range(2):
|
||||
res = residual_empty(res, 8, pad=4, lvl=5, sub_lvl=i+2)
|
||||
|
||||
res = Activation('relu')(res)
|
||||
return res
|
||||
|
||||
def interp_block(prev_layer, level, str_lvl=1):
|
||||
|
||||
def interp_block(prev_layer, level, feature_map_shape, str_lvl=1, ):
|
||||
|
||||
str_lvl = str(str_lvl)
|
||||
|
||||
@@ -147,45 +177,51 @@ def interp_block(prev_layer, level, str_lvl=1):
|
||||
|
||||
kernel = (10*level, 10*level)
|
||||
strides = (10*level, 10*level)
|
||||
prev_layer = AveragePooling2D(kernel,strides=strides)(prev_layer)
|
||||
prev_layer = Conv2D(512, (1,1), strides=(1,1), name=names[0], use_bias=False)(prev_layer)
|
||||
prev_layer = AveragePooling2D(kernel, strides=strides)(prev_layer)
|
||||
prev_layer = Conv2D(512, (1, 1), strides=(1, 1), name=names[0],
|
||||
use_bias=False)(prev_layer)
|
||||
prev_layer = BN(name=names[1])(prev_layer)
|
||||
prev_layer = Activation('relu')(prev_layer)
|
||||
prev_layer = Lambda(Interp)(prev_layer)
|
||||
prev_layer = Lambda(Interp, arguments={'shape': feature_map_shape})(prev_layer)
|
||||
return prev_layer
|
||||
|
||||
def PSPNet(res):
|
||||
|
||||
#---PSPNet concat layers with Interpolation
|
||||
def PSPNet(res, input_shape):
|
||||
"""Build the Pyramid Pooling Module."""
|
||||
# ---PSPNet concat layers with Interpolation
|
||||
feature_map_size = tuple(int(ceil(input_dim / 8.0)) for input_dim in input_shape)
|
||||
print("PSP module will interpolate to a final feature map size of %s" % (feature_map_size, ))
|
||||
|
||||
interp_block1 = interp_block(res, 6, str_lvl=1)
|
||||
interp_block2 = interp_block(res, 3, str_lvl=2)
|
||||
interp_block3 = interp_block(res, 2, str_lvl=3)
|
||||
interp_block6 = interp_block(res, 1, str_lvl=6)
|
||||
interp_block1 = interp_block(res, 6, feature_map_size, str_lvl=1)
|
||||
interp_block2 = interp_block(res, 3, feature_map_size, str_lvl=2)
|
||||
interp_block3 = interp_block(res, 2, feature_map_size, str_lvl=3)
|
||||
interp_block6 = interp_block(res, 1, feature_map_size, str_lvl=6)
|
||||
|
||||
#concat all these layers. resulted shape=(1,60,60,4096)
|
||||
# concat all these layers. resulted shape=(1,60,60,4096)
|
||||
res = Concatenate()([res,
|
||||
interp_block6,
|
||||
interp_block3,
|
||||
interp_block2,
|
||||
interp_block1])
|
||||
interp_block6,
|
||||
interp_block3,
|
||||
interp_block2,
|
||||
interp_block1])
|
||||
return res
|
||||
|
||||
def build_pspnet(activation='softmax'):
|
||||
'''
|
||||
Normal PSPNet.
|
||||
'''
|
||||
inp = Input((473,473,3))
|
||||
res = ResNet(inp)
|
||||
psp = PSPNet(res)
|
||||
|
||||
x = Conv2D(512, (3, 3), strides=(1, 1), padding="same", name="conv5_4", use_bias=False)(psp)
|
||||
def build_pspnet(nb_classes, resnet_layers, input_shape, activation='softmax'):
|
||||
"""Build PSPNet."""
|
||||
print("Building a PSPNet based on ResNet %i expecting inputs of shape %s predicting %i classes" % (resnet_layers, input_shape, nb_classes))
|
||||
|
||||
inp = Input((input_shape[0], input_shape[1], 3))
|
||||
res = ResNet(inp, layers=resnet_layers)
|
||||
psp = PSPNet(res, input_shape)
|
||||
|
||||
x = Conv2D(512, (3, 3), strides=(1, 1), padding="same", name="conv5_4",
|
||||
use_bias=False)(psp)
|
||||
x = BN(name="conv5_4_bn")(x)
|
||||
x = Activation('relu')(x)
|
||||
x = Dropout(0.1)(x)
|
||||
|
||||
x = Conv2D(150, (1, 1), strides=(1, 1), name="conv6")(x)
|
||||
x = Lambda(Interp, arguments={'shape': (473,473)})(x)
|
||||
x = Conv2D(nb_classes, (1, 1), strides=(1, 1), name="conv6")(x)
|
||||
x = Lambda(Interp, arguments={'shape': (input_shape[0], input_shape[1])})(x)
|
||||
x = Activation('softmax')(x)
|
||||
|
||||
model = Model(inputs=inp, outputs=x)
|
||||
@@ -193,6 +229,6 @@ def build_pspnet(activation='softmax'):
|
||||
# Solver
|
||||
sgd = SGD(lr=learning_rate, momentum=0.9, nesterov=True)
|
||||
model.compile(optimizer=sgd,
|
||||
loss='categorical_crossentropy',
|
||||
metrics=['accuracy'])
|
||||
loss='categorical_crossentropy',
|
||||
metrics=['accuracy'])
|
||||
return model
|
||||
|
||||
@@ -1,79 +1,136 @@
|
||||
#!/usr/bin/env python
|
||||
from __future__ import print_function
|
||||
import os
|
||||
from os.path import splitext, join
|
||||
import argparse
|
||||
import numpy as np
|
||||
from scipy import misc, ndimage
|
||||
|
||||
from keras import backend as K
|
||||
from keras.models import model_from_json
|
||||
import tensorflow as tf
|
||||
|
||||
import layers_builder as layers
|
||||
import utils
|
||||
|
||||
WEIGHTS = 'pspnet50_ade20k.npy'
|
||||
DATA_MEAN = np.array([[[123.68, 116.779, 103.939]]]) # RGB
|
||||
# These are the means for the ImageNet pretrained ResNet
|
||||
DATA_MEAN = np.array([[[123.68, 116.779, 103.939]]]) # RGB order
|
||||
|
||||
class PSPNet:
|
||||
|
||||
def __init__(self):
|
||||
self.model = layers.build_pspnet()
|
||||
set_npy_weights(self.model, WEIGHTS)
|
||||
class PSPNet(object):
|
||||
"""Pyramid Scene Parsing Network by Hengshuang Zhao et al 2017"""
|
||||
|
||||
def __init__(self, nb_classes, resnet_layers, input_shape, weights):
|
||||
self.input_shape = input_shape
|
||||
json_path = join("weights", "keras", weights + ".json")
|
||||
h5_path = join("weights", "keras", weights + ".h5")
|
||||
if os.path.isfile(json_path) and os.path.isfile(h5_path):
|
||||
print("Keras model & weights found, loading...")
|
||||
with open(json_path, 'r') as file_handle:
|
||||
self.model = model_from_json(file_handle.read())
|
||||
self.model.load_weights(h5_path)
|
||||
else:
|
||||
print("No Keras model & weights found, import from npy weights.")
|
||||
self.model = layers.build_pspnet(nb_classes=nb_classes,
|
||||
resnet_layers=resnet_layers,
|
||||
input_shape=self.input_shape)
|
||||
self.set_npy_weights(weights)
|
||||
|
||||
def predict(self, img):
|
||||
'''
|
||||
"""
|
||||
Predict segementation for an image.
|
||||
|
||||
Arguments:
|
||||
img: must be 473x473x3
|
||||
'''
|
||||
h_ori,w_ori = img.shape[:2]
|
||||
img: must be rowsxcolsx3
|
||||
"""
|
||||
h_ori, w_ori = img.shape[:2]
|
||||
|
||||
# Preprocess
|
||||
img = misc.imresize(img, (473, 473))
|
||||
img = misc.imresize(img, self.input_shape)
|
||||
|
||||
img = img - DATA_MEAN
|
||||
img = img[:,:,::-1] # RGB => BGR
|
||||
img = img[:, :, ::-1] # RGB => BGR
|
||||
img = img.astype('float32')
|
||||
print("Predicting...")
|
||||
|
||||
probs = self.feed_forward(img)
|
||||
h,w = probs.shape[:2]
|
||||
probs = ndimage.zoom(probs, (1.*h_ori/h,1.*w_ori/w,1.), order=1, prefilter=False)
|
||||
h, w = probs.shape[:2]
|
||||
probs = ndimage.zoom(probs, (1.*h_ori/h, 1.*w_ori/w, 1.),
|
||||
order=1, prefilter=False)
|
||||
print("Finished prediction...")
|
||||
|
||||
return probs
|
||||
|
||||
def predict_sliding_window(self, img):
|
||||
pass
|
||||
|
||||
def feed_forward(self, data):
|
||||
assert data.shape == (473,473,3)
|
||||
data = data[np.newaxis,:,:,:]
|
||||
assert data.shape == (self.input_shape[0], self.input_shape[1], 3)
|
||||
data = data[np.newaxis, :, :, :]
|
||||
|
||||
# utils.debug(self.model, data)
|
||||
pred = self.model.predict(data)
|
||||
return pred[0]
|
||||
|
||||
def set_npy_weights(model, npy_weights):
|
||||
weights = np.load(npy_weights).item()
|
||||
def set_npy_weights(self, weights_path):
|
||||
npy_weights_path = join("weights", "npy", weights_path + ".npy")
|
||||
json_path = join("weights", "keras", weights_path + ".json")
|
||||
h5_path = join("weights", "keras", weights_path + ".h5")
|
||||
|
||||
for layer in model.layers:
|
||||
print layer.name
|
||||
if layer.name[:4] == 'conv' and layer.name[-2:] == 'bn':
|
||||
mean = weights[layer.name]['mean'].reshape(-1)
|
||||
variance = weights[layer.name]['variance'].reshape(-1)
|
||||
scale = weights[layer.name]['scale'].reshape(-1)
|
||||
offset = weights[layer.name]['offset'].reshape(-1)
|
||||
|
||||
model.get_layer(layer.name).set_weights([mean, variance, scale, offset])
|
||||
print("Importing weights from %s" % npy_weights_path)
|
||||
weights = np.load(npy_weights_path).item()
|
||||
|
||||
for layer in self.model.layers:
|
||||
print(layer.name)
|
||||
if layer.name[:4] == 'conv' and layer.name[-2:] == 'bn':
|
||||
mean = weights[layer.name]['mean'].reshape(-1)
|
||||
variance = weights[layer.name]['variance'].reshape(-1)
|
||||
scale = weights[layer.name]['scale'].reshape(-1)
|
||||
offset = weights[layer.name]['offset'].reshape(-1)
|
||||
|
||||
self.model.get_layer(layer.name).set_weights([mean, variance,
|
||||
scale, offset])
|
||||
|
||||
elif layer.name[:4] == 'conv' and not layer.name[-4:] == 'relu':
|
||||
try:
|
||||
weight = weights[layer.name]['weights']
|
||||
self.model.get_layer(layer.name).set_weights([weight])
|
||||
except Exception as err:
|
||||
biases = weights[layer.name]['biases']
|
||||
self.model.get_layer(layer.name).set_weights([weight,
|
||||
biases])
|
||||
print('Finished importing weights.')
|
||||
|
||||
print("Writing keras model & weights")
|
||||
json_string = self.model.to_json()
|
||||
with open(json_path, 'w') as file_handle:
|
||||
file_handle.write(json_string)
|
||||
self.model.save_weights(h5_path)
|
||||
print("Finished writing Keras model & weights")
|
||||
|
||||
|
||||
class PSPNet50(PSPNet):
|
||||
"""Build a PSPNet based on a 50-Layer ResNet."""
|
||||
|
||||
def __init__(self, nb_classes, weights, input_shape):
|
||||
PSPNet.__init__(self, nb_classes=nb_classes, resnet_layers=50,
|
||||
input_shape=input_shape, weights=weights)
|
||||
|
||||
|
||||
class PSPNet101(PSPNet):
|
||||
"""Build a PSPNet based on a 101-Layer ResNet."""
|
||||
|
||||
def __init__(self, nb_classes, weights, input_shape):
|
||||
PSPNet.__init__(self, nb_classes=nb_classes, resnet_layers=101,
|
||||
input_shape=input_shape, weights=weights)
|
||||
|
||||
elif layer.name[:4] == 'conv' and not layer.name[-4:] == 'relu':
|
||||
try:
|
||||
weight = weights[layer.name]['weights']
|
||||
model.get_layer(layer.name).set_weights([weight])
|
||||
except Exception as err:
|
||||
biases = weights[layer.name]['biases']
|
||||
model.get_layer(layer.name).set_weights([weight, biases])
|
||||
print 'Finished.'
|
||||
return model
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--input_path', type=str, default='', required=True, help='Path the input image')
|
||||
parser.add_argument('--output_path', type=str, default='', required=True, help='Path to output')
|
||||
parser.add_argument('-m', '--model', type=str, default='pspnet50_ade20k',
|
||||
help='Model/Weights to use',
|
||||
choices=['pspnet50_ade20k',
|
||||
'pspnet101_cityscapes',
|
||||
'pspnet101_voc2012'])
|
||||
parser.add_argument('-i', '--input_path', type=str, default='example_images/ade20k.jpg',
|
||||
help='Path the input image')
|
||||
parser.add_argument('-o', '--output_path', type=str, default='example_results/ade20k.jpg',
|
||||
help='Path to output')
|
||||
parser.add_argument('--id', default="0")
|
||||
args = parser.parse_args()
|
||||
|
||||
@@ -84,13 +141,31 @@ if __name__ == "__main__":
|
||||
|
||||
with sess.as_default():
|
||||
img = misc.imread(args.input_path)
|
||||
|
||||
pspnet = PSPNet()
|
||||
print(args)
|
||||
|
||||
if "pspnet50" in args.model:
|
||||
pspnet = PSPNet50(nb_classes=150, input_shape=(473, 473),
|
||||
weights=args.model)
|
||||
elif "pspnet101" in args.model:
|
||||
if "cityscapes" in args.model:
|
||||
pspnet = PSPNet101(nb_classes=19, input_shape=(713, 713),
|
||||
weights=args.model)
|
||||
if "voc2012" in args.model:
|
||||
pspnet = PSPNet101(nb_classes=21, input_shape=(473, 473),
|
||||
weights=args.model)
|
||||
|
||||
else:
|
||||
print("Network architecture not implemented.")
|
||||
|
||||
probs = pspnet.predict(img)
|
||||
print("Writing results...")
|
||||
|
||||
cm = np.argmax(probs, axis=2) + 1
|
||||
pm = np.max(probs, axis=2)
|
||||
color_cm = utils.add_color(cm)
|
||||
misc.imsave(args.output_path, color_cm)
|
||||
misc.imsave("probs.jpg", pm)
|
||||
|
||||
# color cm is [0.0-1.0] img is [0-255]
|
||||
alpha_blended = 0.5 * color_cm * 255 + 0.5 * img
|
||||
filename, ext = splitext(args.output_path)
|
||||
misc.imsave(filename + "_seg" + ext, color_cm)
|
||||
misc.imsave(filename + "_probs" + ext, pm)
|
||||
misc.imsave(filename + "_seg_blended" + ext, alpha_blended)
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 78 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 221 KiB |
@@ -1,20 +1,23 @@
|
||||
from __future__ import print_function
|
||||
import colorsys
|
||||
import numpy as np
|
||||
|
||||
from keras.models import Model
|
||||
|
||||
|
||||
def add_color(img):
|
||||
h,w = img.shape
|
||||
img_color = np.zeros((h,w,3))
|
||||
for i in xrange(1,151):
|
||||
h, w = img.shape
|
||||
img_color = np.zeros((h, w, 3))
|
||||
for i in xrange(1, 151):
|
||||
img_color[img == i] = to_color(i)
|
||||
return img_color
|
||||
|
||||
|
||||
def to_color(category):
|
||||
# Maps each category a good distance away
|
||||
# from each other on the HSV color space
|
||||
v = (category-1)*(137.5/360)
|
||||
return colorsys.hsv_to_rgb(v,1,1)
|
||||
return colorsys.hsv_to_rgb(v, 1, 1)
|
||||
|
||||
|
||||
# For printing the activations in each layer
|
||||
@@ -23,10 +26,15 @@ def debug(model, data):
|
||||
names = [layer.name for layer in model.layers]
|
||||
for name in names[:]:
|
||||
print_activation(model, name, data)
|
||||
|
||||
|
||||
def print_activation(model, layer_name, data):
|
||||
intermediate_layer_model = Model(inputs=model.input,
|
||||
outputs=model.get_layer(layer_name).output)
|
||||
io = intermediate_layer_model.predict(data)
|
||||
print layer_name, array_to_str(io)
|
||||
print(layer_name, array_to_str(io))
|
||||
|
||||
|
||||
def array_to_str(a):
|
||||
return "{} {} {} {} {}".format(a.dtype, a.shape, np.min(a), np.max(a), np.mean(a))
|
||||
return "{} {} {} {} {}".format(a.dtype, a.shape, np.min(a),
|
||||
np.max(a), np.mean(a))
|
||||
|
||||
+33
-25
@@ -1,42 +1,50 @@
|
||||
import os
|
||||
#!/usr/bin/env python
|
||||
|
||||
from __future__ import print_function
|
||||
|
||||
import sys
|
||||
from os.path import splitext
|
||||
import numpy as np
|
||||
|
||||
import caffe
|
||||
|
||||
# Not needed because Tensorflow and Caffe do convolution the same way
|
||||
# Needed for conversion to Theano
|
||||
|
||||
|
||||
def rot90(W):
|
||||
for i in range(W.shape[0]):
|
||||
for j in range(W.shape[1]):
|
||||
W[i, j] = np.rot90(W[i, j], 2)
|
||||
return W
|
||||
|
||||
|
||||
weights = {}
|
||||
assert "prototxt" in splitext(sys.argv[1])[1], "First argument must be caffe prototxt %s" % sys.argv[1]
|
||||
assert "caffemodel" in splitext(sys.argv[2])[1], "Second argument must be caffe weights %s" % sys.argv[2]
|
||||
net = caffe.Net(sys.argv[1], sys.argv[2], caffe.TEST)
|
||||
for k,v in net.params.items():
|
||||
print "Layer %s, has %d params." % (k, len(v))
|
||||
if len(v) == 1:
|
||||
W = v[0].data[...]
|
||||
W = np.transpose(W, (2,3,1,0))
|
||||
weights[k] = {"weights": W}
|
||||
elif len(v) == 2:
|
||||
W = v[0].data[...]
|
||||
W = np.transpose(W, (2,3,1,0))
|
||||
b = v[1].data[...]
|
||||
weights[k] = {"weights": W, "biases": b}
|
||||
elif len(v) == 4:
|
||||
k = k.replace('/', '_')
|
||||
mean = v[0].data[...]
|
||||
variance = v[1].data[...]
|
||||
scale = v[2].data[...]
|
||||
offset = v[3].data[...]
|
||||
weights[k] = {"mean": mean, "variance": variance, "scale": scale, "offset": offset}
|
||||
else:
|
||||
print "Undefined layer"
|
||||
exit()
|
||||
for k, v in net.params.items():
|
||||
print ("Layer %s, has %d params." % (k, len(v)))
|
||||
if len(v) == 1:
|
||||
W = v[0].data[...]
|
||||
W = np.transpose(W, (2, 3, 1, 0))
|
||||
weights[k] = {"weights": W}
|
||||
elif len(v) == 2:
|
||||
W = v[0].data[...]
|
||||
W = np.transpose(W, (2, 3, 1, 0))
|
||||
b = v[1].data[...]
|
||||
weights[k] = {"weights": W, "biases": b}
|
||||
elif len(v) == 4:
|
||||
k = k.replace('/', '_')
|
||||
mean = v[0].data[...]
|
||||
variance = v[1].data[...]
|
||||
scale = v[2].data[...]
|
||||
offset = v[3].data[...]
|
||||
weights[k] = {"mean": mean, "variance": variance, "scale": scale, "offset": offset}
|
||||
else:
|
||||
print("Undefined layer")
|
||||
exit()
|
||||
|
||||
arr = np.asarray(weights)
|
||||
np.save("pspnet50_ade20k.npy", arr)
|
||||
|
||||
|
||||
weights_name = splitext(sys.argv[2])[0]+".npy"
|
||||
np.save(weights_name.lower(), arr)
|
||||
|
||||
Reference in New Issue
Block a user