def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: Tuple (image, target). target is the object returned by ``coco.loadAnns``.
"""
image_id = self.ids[index]
#get all annotation_id exsisted in this image
#ann_ids = self.coco.getAnnIds(imgIds=image_id)
# get all annaotation which fulfil the filter conditions
#anns = self.coco.loadAnns(ann_ids)
#for i in range(len(anns)):
#anns[i]['keypoints'] = [0]*3
# self.cat_ids now stores only one category_id, which is corresponding to the category we chose before,
#if the category_id in this annotations is not the category we choose, we assign it to background
#if self.cat_ids[0] != anns[i]['category_id']:
#index_for_keypoints = 0
#if self.cat_ids[0] == anns[i]['category_id']:
#index_for_keypoints = 1
#if index_for_keypoints = 0, means that it is not the object we want to detect.
#if index_for_keypoints == 0:
#overwrite the keypoints
#anns[i]['keypoints'] = [0]*3
#else:
#anns[i]['keypoints'] = [0]*3
#keypoint_x, keypoint_y, keypoint_v = self.keypoints(anns[i])
#index_for_keypoint_x = 0
#index_for_keypoint_y = 1
#index_for_keypoint_v = 2
#anns[i]['keypoints'][index_for_keypoint_x] = keypoint_x
#anns[i]['keypoints'][index_for_keypoint_y] = keypoint_y
#anns[i]['keypoints'][index_for_keypoint_v] = keypoint_v
# if there is no 'keypoints' in the dict, initialize one and write
# if 'keypoints' not in anns[i] and index_for_keypoints == 1:
# # initialize a list with length of 240, e.g. 3x80
# anns[i]['keypoints'] = [0]*3
# # calculate the keypoint from the bounding box
# keypoint_x, keypoint_y, keypoint_v = self.keypoints(anns[i])
# # corresponding index in the keypoints list
# index_for_keypoint_x = 0
# index_for_keypoint_y = 1
# index_for_keypoint_v = 2
# # write center point of bounding box and visibility to keypoints
# anns[i]['keypoints'][index_for_keypoint_x] = keypoint_x
# anns[i]['keypoints'][index_for_keypoint_y] = keypoint_y
# anns[i]['keypoints'][index_for_keypoint_v] = keypoint_v
# # if there is a 'keypoints' in the dict, just write keypoint information to the list
# elif 'keypoints' in anns[i] and index_for_keypoints == 1:
# keypoint_x, keypoint_y, keypoint_v = self.keypoints(anns[i])
# index_for_keypoint_x = 0
# index_for_keypoint_y = 1
# index_for_keypoint_v = 2
# anns[i]['keypoints'][index_for_keypoint_x] = keypoint_x
# anns[i]['keypoints'][index_for_keypoint_y] = keypoint_y
# anns[i]['keypoints'][index_for_keypoint_v] = keypoint_v
#anns = copy.deepcopy(anns)
image_info = self.coco.loadImgs(image_id)[0]
#print(image_info)
self.log.debug(image_info)
with open(os.path.join(self.root, image_info['file_name']), 'rb') as f:
image = Image.open(f).convert('RGB')
meta = {
'dataset_index': index,
'image_id': image_id,
'file_name': image_info['file_name'],
}
if 'flickr_url' in image_info:
_, flickr_file_name = image_info['flickr_url'].rsplit('/', maxsplit=1)
flickr_id, _ = flickr_file_name.split('_', maxsplit=1)
meta['flickr_full_page'] = 'http://flickr.com/photo.gne?id={}'.format(flickr_id)
#if imaage_id not in self.background_ids:
#image, anns = paste_img(image, self.target_img, image_id) ## image is the COCO
#else:
#ann_ids = self.coco.getAnnIds(imgIds=image_id)
#anns = self.coco.loadAnns(ann_ids)
#for i in range(len(anns)):
#anns[i]['keypoints'] = [0]*3
image, anns = paste_img(image, self.target_img, image_id)
# preprocess image and annotations
image, anns, preprocess_meta = self.preprocess(image, anns)
meta.update(preprocess_meta)
# transform image
original_size = image.size
image = self.image_transform(image)
assert image.size(2) == original_size[0]
assert image.size(1) == original_size[1]
# mask valid
valid_area = meta['valid_area']
utils.mask_valid_image(image, valid_area)
# if there are not target transforms, done here
self.log.debug(meta)
if self.target_transforms is None:
return image, anns, meta
# transform targets
targets = [t(anns, original_size) for t in self.target_transforms]
return image, targets, meta
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: Tuple (image, target). target is the object returned by ``coco.loadAnns``.
"""
image_id = self.ids[index]
ann_ids = self.coco.getAnnIds(imgIds=image_id)
#print("image_id"+len(image_id))
#print("ann_ids"+len(ann_ids))
#ann_idss = self.coco.getAnnIds(imgIds=image_id, catIds=self.cat_ids)
#print(len(ann_idss))
anns = self.coco.loadAnns(ann_ids)
for i in range(len(anns)):
index_new = self.dict[anns[i]['category_id']]
anns[i]['keypoints'] = [0]*240
keypoint_x, keypoint_y, keypoint_v = self.keypoints(anns[i])
index_for_keypoint_x = 3*(index_new-1)
index_for_keypoint_y = index_for_keypoint_x + 1
index_for_keypoint_v = index_for_keypoint_y + 1
anns[i]['keypoints'][index_for_keypoint_x] = keypoint_x
anns[i]['keypoints'][index_for_keypoint_y] = keypoint_y
anns[i]['keypoints'][index_for_keypoint_v] = keypoint_v
# to overwrite the keypoints of 'person' category
# if anns[i]['category_id'] == 1 and ('keypoints' in anns[i]):
# if len(anns[i]['keypoints']) != 240:
# anns[i]['keypoints'] = [0]*240
# # to map the original category_id to our id, e.g. 90->80
# index_new = self.dict[anns[i]['category_id']]
# # if there is no 'keypoints' in the dict, initialize one and write
# if 'keypoints' not in anns[i]:
# # initialize a list with length of 240, e.g. 3x80
# anns[i]['keypoints'] = [0]*240
# # calculate the keypoint from the bounding box
# keypoint_x, keypoint_y, keypoint_v = self.keypoints(anns[i])
# # corresponding index in the keypoints list
# index_for_keypoint_x = 3*(index_new-1)
# index_for_keypoint_y = index_for_keypoint_x + 1
# index_for_keypoint_v = index_for_keypoint_y + 1
# # write center point of bounding box and visibility to keypoints
# anns[i]['keypoints'][index_for_keypoint_x] = keypoint_x
# anns[i]['keypoints'][index_for_keypoint_y] = keypoint_y
# anns[i]['keypoints'][index_for_keypoint_v] = keypoint_v
# # if there is a 'keypoints' in the dict, just write keypoint information to the list
# else:
# keypoint_x, keypoint_y, keypoint_v = self.keypoints(anns[i])
# index_for_keypoint_x = 3*(index_new-1)
# index_for_keypoint_y = index_for_keypoint_x + 1
# index_for_keypoint_v = index_for_keypoint_y + 1
# anns[i]['keypoints'][index_for_keypoint_x] = keypoint_x
# anns[i]['keypoints'][index_for_keypoint_y] = keypoint_y
# anns[i]['keypoints'][index_for_keypoint_v] = keypoint_v
anns = copy.deepcopy(anns)
image_info = self.coco.loadImgs(image_id)[0]
#print(image_info)
self.log.debug(image_info)
with open(os.path.join(self.root, image_info['file_name']), 'rb') as f:
image = Image.open(f).convert('RGB')
meta = {
'dataset_index': index,
'image_id': image_id,
'file_name': image_info['file_name'],
}
if 'flickr_url' in image_info:
_, flickr_file_name = image_info['flickr_url'].rsplit('/', maxsplit=1)
flickr_id, _ = flickr_file_name.split('_', maxsplit=1)
meta['flickr_full_page'] = 'http://flickr.com/photo.gne?id={}'.format(flickr_id)
# preprocess image and annotations
image, anns, preprocess_meta = self.preprocess(image, anns)
meta.update(preprocess_meta)
# transform image
original_size = image.size
image = self.image_transform(image)
assert image.size(2) == original_size[0]
assert image.size(1) == original_size[1]
# mask valid
valid_area = meta['valid_area']
utils.mask_valid_image(image, valid_area)
# if there are not target transforms, done here
self.log.debug(meta)
if self.target_transforms is None:
return image, anns, meta
# transform targets
targets = [t(anns, original_size) for t in self.target_transforms]
return image, targets, meta
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: Tuple (image, target). target is the object returned by ``coco.loadAnns``.
"""
image_id = self.ids[index]
#get all annotation_id exsisted in this image
ann_ids = self.coco.getAnnIds(imgIds=image_id)
# get all annaotation which fulfil the filter conditions
anns = self.coco.loadAnns(ann_ids)
for i in range(len(anns)):
# self.cat_ids now stores only one category_id, which is corresponding to the category we chose before,
#if the category_id in this annotations is not the category we choose, we assign it to background
if self.cat_ids[0] != anns[i]['category_id']:
index_for_keypoints = 0
if self.cat_ids[0] == anns[i]['category_id']:
index_for_keypoints = 1
#if index_for_keypoints = 0, means that it is not the object we want to detect.
if index_for_keypoints == 0:
#overwrite the keypoints
anns[i]['keypoints'] = [0]*3
else:
anns[i]['keypoints'] = [0]*3
keypoint_x, keypoint_y, keypoint_v = self.keypoints(anns[i])
index_for_keypoint_x = 0
index_for_keypoint_y = 1
index_for_keypoint_v = 2
anns[i]['keypoints'][index_for_keypoint_x] = keypoint_x
anns[i]['keypoints'][index_for_keypoint_y] = keypoint_y
anns[i]['keypoints'][index_for_keypoint_v] = keypoint_v
anns = copy.deepcopy(anns)
image_info = self.coco.loadImgs(image_id)[0]
#print(image_info)
self.log.debug(image_info)
with open(os.path.join(self.root, image_info['file_name']), 'rb') as f:
image = Image.open(f).convert('RGB')
#print(np.asarray(image)) not normalized
#print(type(image))
meta = {
'dataset_index': index,
'image_id': image_id,
'file_name': image_info['file_name'],
}
if 'flickr_url' in image_info:
_, flickr_file_name = image_info['flickr_url'].rsplit('/', maxsplit=1)
flickr_id, _ = flickr_file_name.split('_', maxsplit=1)
meta['flickr_full_page'] = 'http://flickr.com/photo.gne?id={}'.format(flickr_id)
# preprocess image and annotations
image, anns, preprocess_meta = self.preprocess(image, anns)
meta.update(preprocess_meta)
# transform image
original_size = image.size
image = self.image_transform(image)
assert image.size(2) == original_size[0]
assert image.size(1) == original_size[1]
# mask valid
valid_area = meta['valid_area']
utils.mask_valid_image(image, valid_area)
# if there are not target transforms, done here
self.log.debug(meta)
if self.target_transforms is None:
return image, anns, meta
# transform targets
targets = [t(anns, original_size) for t in self.target_transforms]
return image, targets, meta