mirror of
https://github.com/wassname/PSPNet-Keras-tensorflow.git
synced 2026-09-09 11:15:19 +08:00
VladKry
@@ -0,0 +1,4 @@
|
||||
*.npy
|
||||
*.pyc
|
||||
*.png
|
||||
|
||||
@@ -6,7 +6,7 @@ Converted trained weights needed to run the network.
|
||||
|
||||
|
||||
Download converted weights here:
|
||||
[link:pspnet50_ade20k.npy](https://www.dropbox.com/s/2ksp9hvokzk6qc8/pspnet50_ade20k.npy?dl=0)
|
||||
[link:pspnet50_ade20k.npy](https://www.dropbox.com/s/ms8afun494dlh1t/pspnet50_ade20k.npy?dl=0)
|
||||
|
||||
And place in directory with pspnet50_ade20k.npy
|
||||
|
||||
@@ -24,6 +24,8 @@ Was repaired some issues. But the result is not as well as expected compared to
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Pycaffe result
|
||||
|
||||
|
||||
+161
-188
@@ -1,225 +1,198 @@
|
||||
from keras.layers import Conv2D, MaxPooling2D, AveragePooling2D
|
||||
from keras.layers import BatchNormalization, Activation, Input, Dropout, ZeroPadding2D
|
||||
from keras.layers import merge, concatenate, Lambda, Reshape
|
||||
from keras.layers import BatchNormalization, Activation, Input, Dropout, ZeroPadding2D, Lambda
|
||||
from keras.layers.merge import Concatenate, Add
|
||||
from keras.models import Model
|
||||
from keras.optimizers import SGD
|
||||
|
||||
import tensorflow as tf
|
||||
|
||||
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, size=(60,60)):
|
||||
print(x.shape)
|
||||
new_height = size[0]
|
||||
new_width = size[1]
|
||||
resized = tf.image.resize_images(x, [new_height, new_width])
|
||||
print(resized.shape)
|
||||
return resized
|
||||
def Interp(x, shape=(60,60)):
|
||||
new_height,new_width = shape
|
||||
resized = tf.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)
|
||||
|
||||
def Interp_zoom(x, zoom=8):
|
||||
print(x.shape)
|
||||
old_height = int(x.shape[1])
|
||||
old_width = int(x.shape[2])
|
||||
new_height = old_height + (old_height-1) * (zoom - 1)
|
||||
new_width = old_width + (old_width-1) * (zoom - 1)
|
||||
resized = tf.image.resize_images(x, [new_height, new_width])
|
||||
return resized
|
||||
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)
|
||||
|
||||
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), use_bias=False,
|
||||
name=names[0])(prev)
|
||||
elif modify_stride == True:
|
||||
prev = Conv2D(64 * level, (1,1), strides=(2,2), use_bias=False,
|
||||
name=names[0])(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 = BN(name=names[5])(prev)
|
||||
return prev
|
||||
|
||||
prev = BatchNormalization(momentum=0.95, name=names[1], epsilon=1e-5)(prev)
|
||||
prev = Activation('relu')(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"]
|
||||
|
||||
prev = ZeroPadding2D(padding=(pad,pad))(prev)
|
||||
prev = Conv2D(64 * level, (3,3),
|
||||
strides=(1,1), dilation_rate=pad, use_bias=False,
|
||||
name=names[2])(prev)
|
||||
|
||||
|
||||
prev = BatchNormalization(momentum=0.95, name=names[3], epsilon=1e-5)(prev)
|
||||
prev = Activation('relu')(prev)
|
||||
prev = Conv2D(256 * level, (1,1), strides=(1,1), use_bias=False,
|
||||
name=names[4])(prev)
|
||||
prev = BatchNormalization(momentum=0.95, name=names[5], epsilon=1e-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"
|
||||
]
|
||||
|
||||
if modify_stride == False:
|
||||
prev = Conv2D(256 * level ,(1,1), strides=(1,1), use_bias=False,
|
||||
name=names[0])(prev)
|
||||
elif modify_stride == True:
|
||||
prev = Conv2D(256 * level, (1,1), strides=(2,2), use_bias=False,
|
||||
name=names[0])(prev)
|
||||
|
||||
prev = BatchNormalization(momentum=0.95, name=names[1], epsilon=1e-5)(prev)
|
||||
return prev
|
||||
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)
|
||||
|
||||
prev = BN(name=names[1])(prev)
|
||||
return prev
|
||||
|
||||
def empty_branch(prev):
|
||||
return 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)
|
||||
|
||||
block_2 = short_convolution_branch(prev_layer, level,
|
||||
lvl=lvl, sub_lvl=sub_lvl,
|
||||
modify_stride=modify_stride)
|
||||
|
||||
return merge([block_1, block_2], mode='sum')
|
||||
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)
|
||||
|
||||
block_2 = short_convolution_branch(prev_layer, level,
|
||||
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)
|
||||
prev_layer = Activation('relu')(prev_layer)
|
||||
|
||||
block_1 = residual_conv(prev_layer, level,
|
||||
pad=pad, lvl=lvl, sub_lvl=sub_lvl)
|
||||
block_2 = empty_branch(prev_layer)
|
||||
return merge([block_1, block_2], mode='sum')
|
||||
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
|
||||
names = ["conv1_1_3x3_s2",
|
||||
"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)
|
||||
|
||||
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"
|
||||
|
||||
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"
|
||||
|
||||
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)
|
||||
for i in range(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)
|
||||
for i in range(3):
|
||||
res = residual_empty(res, 2, pad=1, lvl=3, sub_lvl=i+2)
|
||||
|
||||
#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)
|
||||
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):
|
||||
|
||||
str_lvl = str(str_lvl)
|
||||
str_lvl = str(str_lvl)
|
||||
|
||||
names = [
|
||||
"conv5_3_pool"+str_lvl+"_conv",
|
||||
"conv5_3_pool"+str_lvl+"_conv_bn"
|
||||
]
|
||||
names = [
|
||||
"conv5_3_pool"+str_lvl+"_conv",
|
||||
"conv5_3_pool"+str_lvl+"_conv_bn"
|
||||
]
|
||||
|
||||
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), use_bias=False, name=names[0])(prev_layer)
|
||||
prev_layer = BatchNormalization(momentum=0.95, name=names[1], epsilon=1e-5)(prev_layer)
|
||||
prev_layer = Activation('relu')(prev_layer)
|
||||
prev_layer = Lambda(Interp)(prev_layer)
|
||||
return prev_layer
|
||||
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 = BN(name=names[1])(prev_layer)
|
||||
prev_layer = Activation('relu')(prev_layer)
|
||||
prev_layer = Lambda(Interp)(prev_layer)
|
||||
return prev_layer
|
||||
|
||||
def PSPNet(res):
|
||||
|
||||
def build_pspnet():
|
||||
#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"]
|
||||
#---PSPNet concat layers with Interpolation
|
||||
|
||||
#---Short branch(only start of network)
|
||||
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)
|
||||
|
||||
inp = Input((473,473, 3))
|
||||
#concat all these layers. resulted shape=(1,60,60,4096)
|
||||
res = Concatenate()([res,
|
||||
interp_block6,
|
||||
interp_block3,
|
||||
interp_block2,
|
||||
interp_block1])
|
||||
return res
|
||||
|
||||
cnv1 = ZeroPadding2D(padding=(1,1))(inp)
|
||||
cnv1 = Conv2D(64, (3, 3), strides=(2, 2), use_bias=False, name=names[0])(cnv1) # "conv1_1_3x3_s2"
|
||||
|
||||
bn1 = BatchNormalization(momentum=0.95, name=names[1], epsilon=1e-5)(cnv1) # "conv1_1_3x3_s2/bn"
|
||||
relu1 = Activation('relu')(bn1) #"conv1_1_3x3_s2/relu"
|
||||
def build_pspnet(activation='softmax'):
|
||||
'''
|
||||
Normal PSPNet.
|
||||
'''
|
||||
inp = Input((473,473,3))
|
||||
res = ResNet(inp)
|
||||
psp = PSPNet(res)
|
||||
|
||||
cnv1 = ZeroPadding2D(padding=(1,1))(relu1)
|
||||
cnv1 = Conv2D(64, (3, 3), strides=(1, 1), use_bias=False, name=names[2])(cnv1) #"conv1_2_3x3"
|
||||
|
||||
bn1 = BatchNormalization(momentum=0.95, name=names[3], epsilon=1e-5)(cnv1) #"conv1_2_3x3/bn"
|
||||
relu1 = Activation('relu')(bn1) #"conv1_2_3x3/relu"
|
||||
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)
|
||||
|
||||
cnv1 = ZeroPadding2D(padding=(1,1))(relu1)
|
||||
cnv1 = Conv2D(128, (3, 3), strides=(1, 1), use_bias=False, name=names[4])(cnv1) #"conv1_3_3x3"
|
||||
|
||||
bn1 = BatchNormalization(momentum=0.95, name=names[5], epsilon=1e-5)(cnv1) #"conv1_3_3x3/bn"
|
||||
relu1 = Activation('relu')(bn1) #"conv1_3_3x3/relu"
|
||||
x = Conv2D(150, (1, 1), strides=(1, 1), name="conv6")(x)
|
||||
x = Lambda(Interp, arguments={'shape': (473,473)})(x)
|
||||
x = Activation('softmax')(x)
|
||||
|
||||
res = ZeroPadding2D(padding=(1,1))(relu1)
|
||||
res = MaxPooling2D(pool_size=(3,3), strides=(2,2))(res) #"pool1_3x3_s2"
|
||||
|
||||
model = Model(inputs=inp, outputs=x)
|
||||
|
||||
#---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)
|
||||
for i in range(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)
|
||||
for i in range(3): #for i in range(2): old wrong code
|
||||
res = residual_empty(res, 2, pad=1, lvl=3, sub_lvl=i+2)
|
||||
|
||||
#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)
|
||||
for i in range(2):
|
||||
res = residual_empty(res, 8, pad=4, lvl=5, sub_lvl=i+2)
|
||||
|
||||
#---Head of network
|
||||
#---PSPNet concat layers with Interpolation
|
||||
|
||||
res = Activation('relu')(res)
|
||||
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_block4 = interp_block(res, 1, str_lvl=6)
|
||||
|
||||
#concat all these layers by 4th axis(3+1). resulted shape=(1,60,60,4096)
|
||||
res = concatenate([res,
|
||||
interp_block1,
|
||||
interp_block2,
|
||||
interp_block3,
|
||||
interp_block4], axis=3)
|
||||
|
||||
res = ZeroPadding2D(padding=(1,1))(res)
|
||||
res = Conv2D(512, (3, 3), strides=(1, 1), use_bias=False, name="conv5_4")(res)
|
||||
|
||||
res = BatchNormalization(momentum=0.95, name="conv5_4_bn", epsilon=1e-5)(res)
|
||||
res = Activation('relu')(res)
|
||||
#res = Dropout(0.1)(res) #used only in training
|
||||
res = Conv2D(150, (1, 1), strides=(1, 1), name="conv6")(res)
|
||||
res = Lambda(Interp_zoom)(res)
|
||||
|
||||
|
||||
#Use softmax layer for pixelwise prediction
|
||||
curr_width, curr_height, curr_channels = res._shape_as_list()[1:]
|
||||
|
||||
reshape = Reshape((curr_width*curr_height, curr_channels))(res)
|
||||
activation = Activation('softmax')(reshape)
|
||||
reshape = Reshape((curr_width, curr_height, curr_channels))(activation)
|
||||
|
||||
#End of model
|
||||
model = Model(inputs=inp, outputs=reshape)
|
||||
return model
|
||||
# Solver
|
||||
sgd = SGD(lr=learning_rate, momentum=0.9, nesterov=True)
|
||||
model.compile(optimizer=sgd,
|
||||
loss='categorical_crossentropy',
|
||||
metrics=['accuracy'])
|
||||
return model
|
||||
|
||||
@@ -1,112 +1,96 @@
|
||||
from keras import backend as K
|
||||
from PIL import Image
|
||||
|
||||
import layers_builder as pspnet
|
||||
import tensorflow as tf
|
||||
import numpy as np
|
||||
import drawImage
|
||||
import os
|
||||
import argparse
|
||||
import time
|
||||
import numpy as np
|
||||
from scipy import misc, ndimage
|
||||
|
||||
from keras import backend as K
|
||||
import tensorflow as tf
|
||||
|
||||
import layers_builder as layers
|
||||
import utils
|
||||
|
||||
def load_weights():
|
||||
w = np.load('pspnet50_ade20k.npy').item()
|
||||
return w
|
||||
WEIGHTS = 'pspnet50_ade20k.npy'
|
||||
DATA_MEAN = np.array([[[123.68, 116.779, 103.939]]]) # RGB
|
||||
|
||||
class PSPNet:
|
||||
|
||||
def set_weights(model, weights):
|
||||
print 'weights set start'
|
||||
for layer in model.layers:
|
||||
if layer.name[:4] == 'conv' and layer.name[-2:] == 'bn':
|
||||
print layer.name
|
||||
scale = weights[layer.name]['scale'].reshape(-1)
|
||||
def __init__(self):
|
||||
self.model = layers.build_pspnet()
|
||||
set_npy_weights(self.model, WEIGHTS)
|
||||
|
||||
offset = weights[layer.name]['offset'].reshape(-1)
|
||||
mean = weights[layer.name]['mean'].reshape(-1)
|
||||
variance = weights[layer.name]['variance'].reshape(-1)
|
||||
def predict(self, img):
|
||||
'''
|
||||
Arguments:
|
||||
img: must be 473x473x3
|
||||
'''
|
||||
h_ori,w_ori = img.shape[:2]
|
||||
|
||||
# mean *= scale
|
||||
# variance *= scale
|
||||
|
||||
# model.get_layer(layer.name).set_weights([mean, variance,
|
||||
# scale, offset])
|
||||
model.get_layer(layer.name).set_weights([scale, offset,
|
||||
mean, variance])
|
||||
# model.get_layer(layer.name).set_weights([scale, offset,
|
||||
# mean, variance])
|
||||
# Preprocess
|
||||
img = misc.imresize(img, (473, 473))
|
||||
img = img - DATA_MEAN
|
||||
img = img[:,:,::-1] # RGB => BGR
|
||||
img = img.astype('float32')
|
||||
|
||||
elif layer.name[:4] == 'conv' and not layer.name[-4:] == 'relu':
|
||||
print layer.name
|
||||
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])
|
||||
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)
|
||||
return probs
|
||||
|
||||
print 'weights set finish'
|
||||
return model
|
||||
def predict_sliding_window(self, img):
|
||||
pass
|
||||
|
||||
def feed_forward(self, data):
|
||||
assert data.shape == (473,473,3)
|
||||
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()
|
||||
|
||||
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])
|
||||
|
||||
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('--id', default="0")
|
||||
args = parser.parse_args()
|
||||
|
||||
settings = None
|
||||
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')
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = args.id
|
||||
|
||||
settings, unparsed = parser.parse_known_args()
|
||||
mean_r = 123.68
|
||||
mean_g = 116.779
|
||||
mean_b = 103.939
|
||||
sess = tf.Session()
|
||||
K.set_session(sess)
|
||||
|
||||
model = pspnet.build_pspnet()
|
||||
|
||||
sess = tf.Session()
|
||||
K.set_session(sess)
|
||||
|
||||
with sess.as_default():
|
||||
#Load weights into variable
|
||||
npy_weights = load_weights()
|
||||
#Set weights to each laye by name
|
||||
model = set_weights(model, npy_weights)
|
||||
|
||||
#Load image, resize and paste into 4D tensor
|
||||
image = Image.open(settings.input_path)
|
||||
im = image.resize((473, 473))
|
||||
input_ = np.array(im, dtype=np.float32)
|
||||
input_ = input_[:,:,::-1]
|
||||
input_ -= np.array((mean_b, mean_g, mean_r))
|
||||
data = np.zeros([1,473,473,3])
|
||||
|
||||
data[0] = input_
|
||||
|
||||
#predict
|
||||
|
||||
startForward = time.time()
|
||||
pred = model.predict(data, batch_size=1, verbose=0)
|
||||
finishForward = (time.time() - startForward)
|
||||
print "Time used: %f" % finishForward
|
||||
# pred = np.transpose(pred[0], (2, 1, 0))
|
||||
print np.shape(pred)
|
||||
pred = pred[0]
|
||||
predicted_classes = np.argmax(pred, axis=2)
|
||||
|
||||
proto = 'utils/model/pspnet.prototxt'
|
||||
weights = 'utils/model/pspnet.caffemodel'
|
||||
colors = 'utils/colorization/color150.mat'
|
||||
objects = 'utils/colorization/objectName150.mat'
|
||||
|
||||
|
||||
im_Width = predicted_classes.shape[0]
|
||||
im_Height = predicted_classes.shape[1]
|
||||
draw = drawImage.BaseDraw(colors, objects,
|
||||
image, (im_Width, im_Height),
|
||||
predicted_classes)
|
||||
simpleSegmentImage = draw.drawSimpleSegment();
|
||||
simpleSegmentImage.save(settings.output_path,"JPEG")
|
||||
with sess.as_default():
|
||||
img = misc.imread(args.input_path)
|
||||
|
||||
pspnet = PSPNet()
|
||||
probs = pspnet.predict(img)
|
||||
|
||||
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)
|
||||
|
||||
|
||||
@@ -0,0 +1,32 @@
|
||||
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):
|
||||
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)
|
||||
|
||||
|
||||
# For printing the activations in each layer
|
||||
# Useful for debugging
|
||||
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)
|
||||
def array_to_str(a):
|
||||
return "{} {} {} {} {}".format(a.dtype, a.shape, np.min(a), np.max(a), np.mean(a))
|
||||
+28
-6
@@ -1,20 +1,42 @@
|
||||
import caffe
|
||||
import os
|
||||
import sys
|
||||
import numpy as np
|
||||
import os, sys
|
||||
|
||||
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 = {}
|
||||
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:
|
||||
weights[k] = {"weights": np.transpose(v[0].data[...], (2,3,1,0))}
|
||||
W = v[0].data[...]
|
||||
W = np.transpose(W, (2,3,1,0))
|
||||
weights[k] = {"weights": W}
|
||||
elif len(v) == 2:
|
||||
weights[k] = {"weights": np.transpose(v[0].data[...], (2,3,1,0)), "biases": v[1].data[...]}
|
||||
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:
|
||||
weights[k.replace('/', '_')] = {"scale": v[0].data[...], "offset": v[1].data[...], "mean": v[2].data[...], "variance": v[3].data[...]}
|
||||
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)
|
||||
np.save("pspnet50_ade20k.npy", arr)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user