def _get_image_blob(roidb, scale_inds, args):
"""Builds an input blob from the images in the roidb at the specified
scales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
crop_box = []
for i in range(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
global_scale = args.scale_list[scale_inds[i]]
im, im_scale, im_crop_box = prep_im_for_blob(im, cfg.PIXEL_MEANS,
global_scale, args)
crop_box.append(im_crop_box)
im_scales.append(im_scale)
processed_ims.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(processed_ims)
return blob, im_scales, crop_box
def _get_image_blob(self, sample):
im_blob = []
labels_blob = []
for i in range(len(sample)):
if config.NUM_CHANNELS == 1:
im = cv2.imread(sample[i], cv2.IMREAD_GRAYSCALE)
else:
im = cv2.imread(sample[i])
im = prep_im_for_blob(im)
im_blob.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(im_blob)
return blob
def _get_image_blob(self,sample):
im_blob = []
labels_blob = []
for i in range(self._batch_size):
im = cv2.imread(config.IMAGEPATH+sample[i])
personname = sample[i].split('@')[0]
#print str(i)+':'+personname+','+str(len(sample))
labels_blob.append(self.data_container._sample_label[personname])
im = prep_im_for_blob(im)
im_blob.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(im_blob)
return blob,labels_blob
def _get_image_blob(self, sample):
im_blob = []
labels_blob = []
for i in range(self._batch_size):
im = cv2.imread(config.IMAGEPATH + sample[i])
personname = sample[i].split('@')[0]
#print str(i)+':'+personname+','+str(len(sample))
labels_blob.append(self.data_container._sample_label[personname])
im = prep_im_for_blob(im)
im_blob.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(im_blob)
return blob, labels_blob
def _get_image_blob(self,sample):
im_blob = []
labels_blob = np.zeros((len(sample), 1), dtype=np.int32)
for i in range(len(sample)):
img_name = osp.join(cfg.IMAGEPATH, sample[i])
#print img_name
im = cv2.imread(img_name)
personname = sample[i].split('/')[0]
#print str(i)+':'+personname+','+str(len(sample))
labels_blob[i, 0] = int(self.data_container._sample_label[personname])
im = prep_im_for_blob(im)
im_blob.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(im_blob)
return blob,labels_blob
def _get_image_blob(im):
"""Converts an image into a network input.
Arguments:
im (ndarray): a color image in BGR order
Returns:
blob (ndarray): a data blob holding an image pyramid
im_scale_factors (list): list of image scales (relative to im) used
in the image pyramid
"""
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS #[[[102.9801 115.9465 122.7717]]]
im_shape = im_orig.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
processed_ims = []
im_scale_factors = []
for target_size in cfg.TEST.SCALES: # cfg.TEST.SCALES = [600]
im_scale = float(target_size) / float(
im_size_min) #600 / 输入图像比较近小的尺寸
# Prevent the biggest axis from being more than MAX_SIZE
if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE: #1000
im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)
im = cv2.resize(im_orig,
None,
None,
fx=im_scale,
fy=im_scale,
interpolation=cv2.INTER_LINEAR)
#fx fy是缩放的比例因子
im_scale_factors.append(im_scale)
processed_ims.append(im)
#以上就是 将 输入的图片 修改尺寸到 600 1000 限定在这个范围内
# processed_ims = [ im ]里面是修改内容图片尺寸在 600 1000 限定在这个范围内
blob = im_list_to_blob(processed_ims)
# im_scale_factors.append(im_scale)
#processed_ims.append(im)
# for i in range(num_images):
# im = ims[i]
# blob[i, 0:im.shape[0], 0:im.shape[1], :] = im
return blob, np.array(im_scale_factors)
def _get_image_blob(roidb, scale_inds):
"""Builds an input blob from the images in the roidb at the specified
scales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
target_size = cfg.TRAIN.SCALES[scale_inds[i]]
im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
cfg.TRAIN.MAX_SIZE)
im_scales.append(im_scale)
processed_ims.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(processed_ims)
return blob, im_scales
def _get_image_blob(im):
"""Converts an image into a network input.
Arguments:
im (ndarray): a color image in BGR order
Returns:
blob (ndarray): a data blob holding an image pyramid
im_scale_factors (list): list of image scales (relative to im) used
in the image pyramid
"""
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
im_shape = im_orig.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
processed_ims = []
im_scale_factors = []
for target_size in cfg.TEST.SCALES:
im_scale = float(target_size) / float(im_size_min)
# Prevent the biggest axis from being more than MAX_SIZE
if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:
im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)
im = cv2.resize(im_orig,
None,
None,
fx=im_scale,
fy=im_scale,
interpolation=cv2.INTER_LINEAR)
im_scale_factors.append(im_scale)
processed_ims.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(processed_ims)
return blob, np.array(im_scale_factors)
