Caffe-HRT/python/caffe/detector.py at master · bjthemost/Caffe-HRT · GitHub

Repository navigation

History

216 lines (191 loc) · 8.34 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

#!/usr/bin/env python

"""

Do windowed detection by classifying a number of images/crops at once,

optionally using the selective search window proposal method.

This implementation follows ideas in

Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik.

Rich feature hierarchies for accurate object detection and semantic

segmentation.

http://arxiv.org/abs/1311.2524

The selective_search_ijcv_with_python code required for the selective search

proposal mode is available at

https://github.com/sergeyk/selective_search_ijcv_with_python

"""

import numpy as np

import os

import caffe

class Detector(caffe.Net):

"""

Detector extends Net for windowed detection by a list of crops or

selective search proposals.

Parameters

----------

mean, input_scale, raw_scale, channel_swap : params for preprocessing

options.

context_pad : amount of surrounding context to take s.t. a `context_pad`

sized border of pixels in the network input image is context, as in

R-CNN feature extraction.

"""

def __init__(self, model_file, pretrained_file, mean=None,

input_scale=None, raw_scale=None, channel_swap=None,

context_pad=None):

caffe.Net.__init__(self, model_file, pretrained_file, caffe.TEST)

# configure pre-processing

in_ = self.inputs[0]

self.transformer = caffe.io.Transformer(

{in_: self.blobs[in_].data.shape})

self.transformer.set_transpose(in_, (2, 0, 1))

if mean is not None:

self.transformer.set_mean(in_, mean)

if input_scale is not None:

self.transformer.set_input_scale(in_, input_scale)

if raw_scale is not None:

self.transformer.set_raw_scale(in_, raw_scale)

if channel_swap is not None:

self.transformer.set_channel_swap(in_, channel_swap)

self.configure_crop(context_pad)

def detect_windows(self, images_windows):

"""

Do windowed detection over given images and windows. Windows are

extracted then warped to the input dimensions of the net.

Parameters

----------

images_windows: (image filename, window list) iterable.

context_crop: size of context border to crop in pixels.

Returns

-------

detections: list of {filename: image filename, window: crop coordinates,

predictions: prediction vector} dicts.

"""

# Extract windows.

window_inputs = []

for image_fname, windows in images_windows:

image = caffe.io.load_image(image_fname).astype(np.float32)

for window in windows:

window_inputs.append(self.crop(image, window))

# Run through the net (warping windows to input dimensions).

in_ = self.inputs[0]

caffe_in = np.zeros((len(window_inputs), window_inputs[0].shape[2])

+ self.blobs[in_].data.shape[2:],

dtype=np.float32)

for ix, window_in in enumerate(window_inputs):

caffe_in[ix] = self.transformer.preprocess(in_, window_in)

out = self.forward_all(**{in_: caffe_in})

predictions = out[self.outputs[0]]

# Package predictions with images and windows.

detections = []

ix = 0

for image_fname, windows in images_windows:

for window in windows:

detections.append({

'window': window,

'prediction': predictions[ix],

'filename': image_fname

})

ix += 1

return detections

def detect_selective_search(self, image_fnames):

"""

Do windowed detection over Selective Search proposals by extracting

the crop and warping to the input dimensions of the net.

Parameters

----------

image_fnames: list

Returns

-------

detections: list of {filename: image filename, window: crop coordinates,

predictions: prediction vector} dicts.

"""

import selective_search_ijcv_with_python as selective_search

# Make absolute paths so MATLAB can find the files.

image_fnames = [os.path.abspath(f) for f in image_fnames]

windows_list = selective_search.get_windows(

image_fnames,

cmd='selective_search_rcnn'

)

# Run windowed detection on the selective search list.

return self.detect_windows(zip(image_fnames, windows_list))

def crop(self, im, window):

"""

Crop a window from the image for detection. Include surrounding context

according to the `context_pad` configuration.

Parameters

----------

im: H x W x K image ndarray to crop.

window: bounding box coordinates as ymin, xmin, ymax, xmax.

Returns

-------

crop: cropped window.

"""

# Crop window from the image.

crop = im[window[0]:window[2], window[1]:window[3]]

if self.context_pad:

box = window.copy()

crop_size = self.blobs[self.inputs[0]].width # assumes square

scale = crop_size / (1. * crop_size - self.context_pad * 2)

# Crop a box + surrounding context.

half_h = (box[2] - box[0] + 1) / 2.

half_w = (box[3] - box[1] + 1) / 2.

center = (box[0] + half_h, box[1] + half_w)

scaled_dims = scale * np.array((-half_h, -half_w, half_h, half_w))

box = np.round(np.tile(center, 2) + scaled_dims)

full_h = box[2] - box[0] + 1

full_w = box[3] - box[1] + 1

scale_h = crop_size / full_h

scale_w = crop_size / full_w

pad_y = round(max(0, -box[0]) * scale_h) # amount out-of-bounds

pad_x = round(max(0, -box[1]) * scale_w)

# Clip box to image dimensions.

im_h, im_w = im.shape[:2]

box = np.clip(box, 0., [im_h, im_w, im_h, im_w])

clip_h = box[2] - box[0] + 1

clip_w = box[3] - box[1] + 1

assert(clip_h > 0 and clip_w > 0)

crop_h = round(clip_h * scale_h)

crop_w = round(clip_w * scale_w)

if pad_y + crop_h > crop_size:

crop_h = crop_size - pad_y

if pad_x + crop_w > crop_size:

crop_w = crop_size - pad_x

# collect with context padding and place in input

# with mean padding

context_crop = im[box[0]:box[2], box[1]:box[3]]

context_crop = caffe.io.resize_image(context_crop, (crop_h, crop_w))

crop = np.ones(self.crop_dims, dtype=np.float32) * self.crop_mean

crop[pad_y:(pad_y + crop_h), pad_x:(pad_x + crop_w)] = context_crop

return crop

def configure_crop(self, context_pad):

"""

Configure crop dimensions and amount of context for cropping.

If context is included, make the special input mean for context padding.

Parameters

----------

context_pad : amount of context for cropping.

"""

# crop dimensions

in_ = self.inputs[0]

tpose = self.transformer.transpose[in_]

inv_tpose = [tpose[t] for t in tpose]

self.crop_dims = np.array(self.blobs[in_].data.shape[1:])[inv_tpose]

#.transpose(inv_tpose)

# context padding

self.context_pad = context_pad

if self.context_pad:

in_ = self.inputs[0]

transpose = self.transformer.transpose.get(in_)

channel_order = self.transformer.channel_swap.get(in_)

raw_scale = self.transformer.raw_scale.get(in_)

# Padding context crops needs the mean in unprocessed input space.

mean = self.transformer.mean.get(in_)

if mean is not None:

inv_transpose = [transpose[t] for t in transpose]

crop_mean = mean.copy().transpose(inv_transpose)

if channel_order is not None:

channel_order_inverse = [channel_order.index(i)

for i in range(crop_mean.shape[2])]

crop_mean = crop_mean[:, :, channel_order_inverse]

if raw_scale is not None:

crop_mean /= raw_scale

self.crop_mean = crop_mean

else:

self.crop_mean = np.zeros(self.crop_dims, dtype=np.float32)

Caffe-HRT/python/caffe/detector.py at master · bjthemost/Caffe-HRT · GitHub

Repository navigation

Expand file tree

Breadcrumbs

detector.py

Latest commit

History

Breadcrumbs

detector.py

File metadata and controls