wassname/PSPNet-Keras-tensorflow
1
0
Fork 0
mirror of https://github.com/wassname/PSPNet-Keras-tensorflow.git synced 2026-09-10 11:40:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Repaired code issue

Browse Source
This commit is contained in:
Chaoyue Wang
2017-07-19 21:06:59 -04:00
parent ed32c508ea
commit eeb48562e1
6 changed files with 65 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
drawImage/__init__.pyc
BIN
View File
Binary file not shown.
drawImage/drawModule.py
+3 -2
View File
@@ -16,8 +16,8 @@ class BaseDraw:
self.original_W = self.im.size[0]
self.original_H = self.im.size[1]
self.output_W = 1920
self.output_H = 1080
self.output_W = self.original_W
self.output_H = self.original_H
def dumpArray(self, array, i):
@@ -70,5 +70,6 @@ class BaseDraw:
#Resize to original size and save
self.coef, self.h_pad, self.w_pad = self.calculateResize()
FullHdOutImage = self.resizeToOutput(prediction_image, self.coef, self.h_pad, self.w_pad)
FullHdOutImage = Image.blend(FullHdOutImage, self.im, 0.5)
return FullHdOutImage
drawImage/drawModule.pyc
BIN
View File
Binary file not shown.
layers_builder.py
+11 -11
View File
@@ -44,7 +44,7 @@ def residual_conv(prev, level,
prev = Conv2D(64 * level, (1,1), strides=(2,2), use_bias=False,
name=names[0])(prev)
prev = BatchNormalization(momentum=0.95, name=names[1])(prev)
prev = BatchNormalization(momentum=0.95, name=names[1], epsilon=1e-5)(prev)
prev = Activation('relu')(prev)
prev = ZeroPadding2D(padding=(pad,pad))(prev)
@@ -53,11 +53,11 @@ def residual_conv(prev, level,
name=names[2])(prev)
prev = BatchNormalization(momentum=0.95, name=names[3])(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])(prev)
prev = BatchNormalization(momentum=0.95, name=names[5], epsilon=1e-5)(prev)
return prev
@@ -76,7 +76,7 @@ def short_convolution_branch(prev, level,
prev = Conv2D(256 * level, (1,1), strides=(2,2), use_bias=False,
name=names[0])(prev)
prev = BatchNormalization(momentum=0.95, name=names[1])(prev)
prev = BatchNormalization(momentum=0.95, name=names[1], epsilon=1e-5)(prev)
return prev
@@ -85,7 +85,7 @@ def empty_branch(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)
@@ -119,7 +119,7 @@ def interp_block(prev_layer, level, str_lvl=1):
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])(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
@@ -141,19 +141,19 @@ def build_pspnet():
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])(cnv1) # "conv1_1_3x3_s2/bn"
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"
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])(cnv1) #"conv1_2_3x3/bn"
bn1 = BatchNormalization(momentum=0.95, name=names[3], epsilon=1e-5)(cnv1) #"conv1_2_3x3/bn"
relu1 = Activation('relu')(bn1) #"conv1_2_3x3/relu"
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])(cnv1) #"conv1_3_3x3/bn"
bn1 = BatchNormalization(momentum=0.95, name=names[5], epsilon=1e-5)(cnv1) #"conv1_3_3x3/bn"
relu1 = Activation('relu')(bn1) #"conv1_3_3x3/relu"
res = ZeroPadding2D(padding=(1,1))(relu1)
@@ -174,7 +174,7 @@ def build_pspnet():
#3_1 - 3_3
res = residual_short(res, 2, pad=1, lvl=3, sub_lvl=1, modify_stride=True)
for i in range(2):
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
@@ -206,7 +206,7 @@ def build_pspnet():
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")(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)
pspnet.py
+31 -19
View File
@@ -25,9 +25,16 @@ def set_weights(model, weights):
offset = weights[layer.name]['offset'].reshape(-1)
mean = weights[layer.name]['mean'].reshape(-1)
variance = weights[layer.name]['variance'].reshape(-1)
# 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])
elif layer.name[:4] == 'conv' and not layer.name[-4:] == 'relu':
print layer.name
@@ -52,7 +59,9 @@ if __name__ == "__main__":
required=True, help='Path to output')
settings, unparsed = parser.parse_known_args()
mean_r = 123.68
mean_g = 116.779
mean_b = 103.939
model = pspnet.build_pspnet()
@@ -67,34 +76,37 @@ if __name__ == "__main__":
#Load image, resize and paste into 4D tensor
image = Image.open(settings.input_path)
data_im = np.asarray(image)
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_im = np.resize(data_im, [473, 473, 3])
data[0] = data_im
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)
pred = np.transpose(pred[0], (2, 1, 0))
predicted_classes = np.argmax(pred, axis=0)
proto = 'utils/model/pspnet.prototxt'
weights = 'utils/model/pspnet.caffemodel'
colors = 'utils/colorization/color150.mat'
objects = 'utils/colorization/objectName150.mat'
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[1]
im_Height = predicted_classes.shape[0]
draw = drawImage.BaseDraw(colors, objects,
image, (im_Width, im_Height),
predicted_classes)
simpleSegmentImage = draw.drawSimpleSegment();
simpleSegmentImage.save(settings.output_path,"JPEG")
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")
weight_converter.py
+20
View File
@@ -0,0 +1,20 @@
import caffe
import numpy as np
import os, sys
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))}
elif len(v) == 2:
weights[k] = {"weights": np.transpose(v[0].data[...], (2,3,1,0)), "biases": v[1].data[...]}
elif len(v) == 4:
weights[k.replace('/', '_')] = {"scale": v[0].data[...], "offset": v[1].data[...], "mean": v[2].data[...], "variance": v[3].data[...]}
else:
print "Undefined layer"
exit()
arr = np.asarray(weights)
np.save("pspnet50_ade20k.npy", arr)