def downscale(old_file_name):
img = cv2.imread(os.path.join(old_file_name))
new_file_name = (old_file_name
.replace('training', 'training_' + str(min_size))
.replace('validation', 'validation_' + str(min_size))
.replace('testing', 'testing_' + str(min_size))
)
height, width, _ = img.shape
if width > height:
new_width = int(1.0 * width / height * min_size)
new_height = min_size
else:
new_height = int(1.0 * height / width * min_size)
new_width = min_size
img_new = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_LINEAR)
cv2.imwrite(new_file_name, img_new)
python类INTER_LINEAR的实例源码
def RandomCrop(rand_seed,img, top,left,height=224, width=224,u=0.5,aug_factor=9/8):
#first zoom in by a factor of aug_factor of input img,then random crop by(height,width)
# if rand_seed < u:
if 1:
# h,w,c = img.shape
# img = cv2.resize(img, (round(aug_factor*w), round(aug_factor*h)), interpolation=cv2.INTER_LINEAR)
# h, w, c = img.shape
new_h, new_w = height,width
# top = np.random.randint(0, h - new_h)
# left = np.random.randint(0, w - new_w)
img = img[top: top + new_h,
left: left + new_w]
return img
def resizeCrop(self, crop, sz):
"""
Resize cropped image
:param crop: crop
:param sz: size
:return: resized image
"""
if self.resizeMethod == self.RESIZE_CV2_NN:
rz = cv2.resize(crop, sz, interpolation=cv2.INTER_NEAREST)
elif self.resizeMethod == self.RESIZE_BILINEAR:
rz = self.bilinearResize(crop, sz, self.getNDValue())
elif self.resizeMethod == self.RESIZE_CV2_LINEAR:
rz = cv2.resize(crop, sz, interpolation=cv2.INTER_LINEAR)
else:
raise NotImplementedError("Unknown resize method!")
return rz
def resize(im, target_size, max_size):
"""
only resize input image to target size and return scale
:param im: BGR image input by opencv
:param target_size: one dimensional size (the short side)
:param max_size: one dimensional max size (the long side)
:return:
"""
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
im_scale = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
return im, im_scale
def resize(im, target_size, max_size):
"""
only resize input image to target size and return scale
:param im: BGR image input by opencv
:param target_size: one dimensional size (the short side)
:param max_size: one dimensional max size (the long side)
:return:
"""
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
im_scale = float(target_size) / float(im_size_min)
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
return im, im_scale
def prep_im_for_blob(im, pixel_means, target_size, max_size):
"""Mean subtract and scale an image for use in a blob."""
im = im.astype(np.float32, copy=False)
im -= pixel_means
im = im / 127.5
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
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) > max_size:
im_scale = float(max_size) / float(im_size_max)
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,
interpolation=cv2.INTER_LINEAR)
return im, im_scale
def resize(im, target_size, max_size):
"""
only resize input image to target size and return scale
:param im: BGR image input by opencv
:param target_size: one dimensional size (the short side)
:param max_size: one dimensional max size (the long side)
:return:
"""
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
im_scale = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
return im, im_scale
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, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
im_scale = cfg.TRAIN.SCALES_BASE[scale_inds[i]]
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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_multiscale(roidb):
"""Builds an input blob from the images in the roidb at multiscales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
scales = cfg.TRAIN.SCALES_BASE
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
for im_scale in scales:
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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 resize(im, target_size, max_size):
"""
only resize input image to target size and return scale
:param im: BGR image input by opencv
:param target_size: one dimensional size (the short side)
:param max_size: one dimensional max size (the long side)
:return:
"""
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
im_scale = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
return im, im_scale
def _get_image_blob(ims, target_size):
"""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_infos(ndarray): a data blob holding input size pyramid
"""
processed_ims = []
for im in ims:
im = im.astype(np.float32, copy = False)
im = im - cfg.PIXEL_MEANS
im_shape = im.shape[0:2]
im = cv2.resize(im, None, None, fx = float(target_size) / im_shape[1], \
fy = float(target_size) / im_shape[0], interpolation = cv2.INTER_LINEAR)
processed_ims.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(processed_ims)
return blob
minibatch2.py 文件源码
项目：Automatic_Group_Photography_Enhancement
作者: Yuliang-Zou
项目源码
文件源码
阅读 30
收藏 0
点赞 0
评论 0
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, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
im_scale = cfg.TRAIN.SCALES_BASE[scale_inds[i]]
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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
minibatch2.py 文件源码
项目：Automatic_Group_Photography_Enhancement
作者: Yuliang-Zou
项目源码
文件源码
阅读 26
收藏 0
点赞 0
评论 0
def _get_image_blob_multiscale(roidb):
"""Builds an input blob from the images in the roidb at multiscales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
scales = cfg.TRAIN.SCALES_BASE
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
for im_scale in scales:
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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_noscale(self, im):
im_orig = im.astype(np.float32, copy=True)
im_orig -= self.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 = []
target_size = self.SCALES[0]
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) > self.MAX_SIZE:
im_scale = float(self.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)
blob = im_list_to_blob(processed_ims)
return blob, np.array(im_scale_factors)
def resizeCrop(self, crop, sz):
"""
Resize cropped image
:param crop: crop
:param sz: size
:return: resized image
"""
if self.resizeMethod == self.RESIZE_CV2_NN:
rz = cv2.resize(crop, sz, interpolation=cv2.INTER_NEAREST)
elif self.resizeMethod == self.RESIZE_BILINEAR:
rz = self.bilinearResize(crop, sz, self.getNDValue())
elif self.resizeMethod == self.RESIZE_CV2_LINEAR:
rz = cv2.resize(crop, sz, interpolation=cv2.INTER_LINEAR)
else:
raise NotImplementedError("Unknown resize method!")
return rz
def resize(im, target_size, max_size):
"""
only resize input image to target size and return scale
:param im: BGR image input by opencv
:param target_size: one dimensional size (the short side)
:param max_size: one dimensional max size (the long side)
:return:
"""
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
im_scale = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
return im, im_scale
def resize(im, target_size, max_size):
"""
only resize input image to target size and return scale
:param im: BGR image input by opencv
:param target_size: one dimensional size (the short side)
:param max_size: one dimensional max size (the long side)
:return:
"""
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
im_scale = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
return im, im_scale
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, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
im_scale = cfg.TRAIN.SCALES_BASE[scale_inds[i]]
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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_multiscale(roidb):
"""Builds an input blob from the images in the roidb at multiscales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
scales = cfg.TRAIN.SCALES_BASE
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
for im_scale in scales:
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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 prep_im_for_blob(im, pixel_means, target_size, max_size):
"""Mean subtract and scale an image for use in a blob."""
im = im.astype(np.float32, copy=False)
im -= pixel_means
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
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) > max_size:
im_scale = float(max_size) / float(im_size_max)
if cfg.TRAIN.RANDOM_DOWNSAMPLE:
r = 0.6 + np.random.rand() * 0.4
im_scale *= r
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,
interpolation=cv2.INTER_LINEAR)
return im, im_scale
def prep_im_for_blob(im, pixel_means, target_size, max_size):
"""Mean subtract and scale an image for use in a blob."""
im = im.astype(np.float32, copy=False)
im -= pixel_means
im_shape = im.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
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) > max_size:
im_scale = float(max_size) / float(im_size_max)
if cfg.TRAIN.RANDOM_DOWNSAMPLE:
r = 0.6 + np.random.rand() * 0.4
im_scale *= r
im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,
interpolation=cv2.INTER_LINEAR)
return im, im_scale
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, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
im_scale = cfg.TRAIN.SCALES_BASE[scale_inds[i]]
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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_multiscale(roidb):
"""Builds an input blob from the images in the roidb at multiscales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
scales = cfg.TRAIN.SCALES_BASE
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
for im_scale in scales:
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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 _aligned(im_ref, im, im_to_align=None, key=None):
w, h = im.shape[:2]
im_ref = cv2.resize(im_ref, (h, w), interpolation=cv2.INTER_CUBIC)
im_ref = _preprocess_for_alignment(im_ref)
if im_to_align is None:
im_to_align = im
im_to_align = _preprocess_for_alignment(im_to_align)
assert im_ref.shape[:2] == im_to_align.shape[:2]
try:
cc, warp_matrix = _get_alignment(im_ref, im_to_align, key)
except cv2.error as e:
logger.info('Error getting alignment: {}'.format(e))
return im, False
else:
im = cv2.warpAffine(im, warp_matrix, (h, w),
flags=cv2.INTER_LINEAR + cv2.WARP_INVERSE_MAP)
im[im == 0] = np.mean(im)
return im, True
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 range(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
im_scale = cfg.TRAIN.SCALES_BASE[scale_inds[i]]
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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_multiscale(roidb):
"""Builds an input blob from the images in the roidb at multiscales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
scales = cfg.TRAIN.SCALES_BASE
for i in range(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
im_orig = im.astype(np.float32, copy=True)
im_orig -= cfg.PIXEL_MEANS
for im_scale in scales:
im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
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 _feature(image):
"""
It's faster but still accurate enough with DSIZE = 14.
~0.9983 precision and recall
:param image:
:return: raw pixels as feature vector
"""
image = cv2.resize(image, None, fx=DSIZE/28, fy=DSIZE/28,
interpolation=cv2.INTER_LINEAR)
ret = image.astype(np.float32) / 255
return ret.ravel()
def prep_im_for_blob(im):
target_size = 224
pixel_means = np.array([[[102.9801, 115.9465, 122.7717]]])
im = im.astype(np.float32, copy=False)
im -= pixel_means
im = cv2.resize(im, (224,224),
interpolation=cv2.INTER_LINEAR)
return im
def resize_blob(blob, dest_shape=None, im_scale=None, method=None):
assert dest_shape != None or im_scale != None
img = blob.transpose((1, 2, 0))
if method is None:
method = cv2.INTER_LINEAR
if dest_shape is not None:
dest_shape = dest_shape[1], dest_shape[0]
img = cv2.resize(img, dest_shape, interpolation=method)
else:
img = cv2.resize(img, None, None, fx=im_scale, fy=im_scale, interpolation=method)
if len(img.shape) == 2:
img = img[:, :, np.newaxis]
blob = img.transpose((2, 0, 1))
return 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
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)
