def gen_worker(q_in, q_out):
while True:
deq = q_in.get()
if deq is None:
break
_roidb = deq
data, label = get_crop_batch(_roidb)
print('generated')
q_out.put((data, label))
def get_batch(self):
# slice roidb
cur_from = self.cur
cur_to = min(cur_from + self.batch_size, self.size)
assert cur_to==cur_from+self.batch_size
roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]
# decide multi device slice
work_load_list = self.work_load_list
ctx = self.ctx
if work_load_list is None:
work_load_list = [1] * len(ctx)
assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
"Invalid settings for work load. "
slices = _split_input_slice(self.batch_size, work_load_list)
# get testing data for multigpu
data_list = []
label_list = []
for islice in slices:
iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
data, label = get_crop_batch(iroidb)
data_list += data
label_list += label
#data_list.append(data)
#label_list.append(label)
# pad data first and then assign anchor (read label)
#data_tensor = tensor_vstack([batch['data'] for batch in data_list])
#for i_card in range(len(data_list)):
# data_list[i_card]['data'] = data_tensor[
# i_card * config.TRAIN.BATCH_IMAGES:(1 + i_card) * config.TRAIN.BATCH_IMAGES]
for data, label in zip(data_list, label_list):
data_shape = {k: v.shape for k, v in data.items()}
del data_shape['im_info']
feat_shape_list = []
for s in range(len(self.feat_stride)):
_, feat_shape, _ = self.feat_sym[s].infer_shape(**data_shape)
feat_shape = [int(i) for i in feat_shape[0]]
feat_shape_list.append(feat_shape)
#for k in self.label_name:
# label[k] = [0 for i in range(config.TRAIN.BATCH_IMAGES)]
im_info = data['im_info']
gt_boxes = label['gt_boxes']
gt_points = label['gt_points']
#print('im_info', im_info.shape)
#print(gt_boxes.shape)
label_dict = assign_anchor_fpn(feat_shape_list, gt_boxes, gt_points, im_info)
for k in self.label_name:
label[k] = label_dict[k]
all_data = dict()
for key in self.data_name:
all_data[key] = tensor_vstack([batch[key] for batch in data_list])
all_label = dict()
for key in self.label_name:
pad = 0 if key.startswith('bbox_') or key.startswith('kpoint_') else -1
#print('label vstack', key, pad, len(label_list), file=sys.stderr)
all_label[key] = tensor_vstack([batch[key] for batch in label_list], pad=pad)
self.data = [mx.nd.array(all_data[key]) for key in self.data_name]
self.label = [mx.nd.array(all_label[key]) for key in self.label_name]
def get_batch(self):
# slice roidb
cur_from = self.cur
cur_to = min(cur_from + self.batch_size, self.size)
assert cur_to == cur_from + self.batch_size
roidb = [self.roidb[self.index[i]] for i in range(cur_from, cur_to)]
# decide multi device slice
work_load_list = self.work_load_list
ctx = self.ctx
if work_load_list is None:
work_load_list = [1] * len(ctx)
assert isinstance(work_load_list, list) and len(work_load_list) == len(ctx), \
"Invalid settings for work load. "
slices = _split_input_slice(self.batch_size, work_load_list)
# get testing data for multigpu
data_list = []
label_list = []
for islice in slices:
iroidb = [roidb[i] for i in range(islice.start, islice.stop)]
data, label = get_crop_batch(iroidb)
data_list += data
label_list += label
#data_list.append(data)
#label_list.append(label)
# pad data first and then assign anchor (read label)
#data_tensor = tensor_vstack([batch['data'] for batch in data_list])
#for i_card in range(len(data_list)):
# data_list[i_card]['data'] = data_tensor[
# i_card * config.TRAIN.BATCH_IMAGES:(1 + i_card) * config.TRAIN.BATCH_IMAGES]
#iiddxx = 0
select_stride = 0
if config.RANDOM_FEAT_STRIDE:
select_stride = random.choice(config.RPN_FEAT_STRIDE)
for data, label in zip(data_list, label_list):
data_shape = {k: v.shape for k, v in data.items()}
del data_shape['im_info']
feat_shape_list = []
for s in range(len(self.feat_stride)):
_, feat_shape, _ = self.feat_sym[s].infer_shape(**data_shape)
feat_shape = [int(i) for i in feat_shape[0]]
feat_shape_list.append(feat_shape)
im_info = data['im_info']
gt_boxes = label['gt_boxes']
gt_label = {'gt_boxes': gt_boxes}
if config.USE_BLUR:
gt_blur = label['gt_blur']
gt_label['gt_blur'] = gt_blur
if self._debug:
img = data['data'].copy()[0].transpose(
(1, 2, 0))[:, :, ::-1].copy()
print('DEBUG SHAPE', data['data'].shape,
label['gt_boxes'].shape)
box = label['gt_boxes'].copy()[0][0:4].astype(np.int)
cv2.rectangle(img, (box[0], box[1]), (box[2], box[3]),
(0, 255, 0), 2)
filename = './debugout/%d.png' % (self._debug_id)
print('debug write', filename)
cv2.imwrite(filename, img)
self._debug_id += 1
#print('DEBUG', img.shape, bbox.shape)
label_dict = {}
if config.HEAD_BOX:
head_label_dict = self.aa.assign_anchor_fpn(
gt_label,
im_info,
False,
prefix='head',
select_stride=select_stride)
label_dict.update(head_label_dict)
if config.FACE_LANDMARK:
gt_landmarks = label['gt_landmarks']
gt_label['gt_landmarks'] = gt_landmarks
#ta = datetime.datetime.now()
#face_label_dict = assign_anchor_fpn(feat_shape_list, gt_label, im_info, config.FACE_LANDMARK, prefix='face', select_stride = select_stride)
face_label_dict = self.aa.assign_anchor_fpn(
gt_label,
im_info,
config.FACE_LANDMARK,
prefix='face',
select_stride=select_stride)
#tb = datetime.datetime.now()
#self._times[0] += (tb-ta).total_seconds()
label_dict.update(face_label_dict)
#for k in label_dict:
# print(k, label_dict[k].shape)
if config.CASCADE > 0:
pad_gt_boxes = np.empty(
(1, config.TRAIN.MAX_BBOX_PER_IMAGE, 5), dtype=np.float32)
pad_gt_boxes.fill(-1)
pad_gt_boxes[0, 0:gt_boxes.shape[0], :] = gt_boxes
label_dict['gt_boxes'] = pad_gt_boxes
#print('im_info', im_info.shape)
#print(gt_boxes.shape)
for k in self.label_name:
label[k] = label_dict[k]
all_data = dict()
for key in self.data_name:
all_data[key] = tensor_vstack([batch[key] for batch in data_list])
all_label = dict()
for key in self.label_name:
pad = 0 if key.startswith('bbox_') else -1
#print('label vstack', key, pad, len(label_list), file=sys.stderr)
all_label[key] = tensor_vstack(
[batch[key] for batch in label_list], pad=pad)
self.data = [mx.nd.array(all_data[key]) for key in self.data_name]
self.label = [mx.nd.array(all_label[key]) for key in self.label_name]
def get_batch(self, roidb):
label_name = config.label_name
data_name = config.data_name
# get testing data for multigpu
data_list = []
label_list = []
# TODO：获取单个GPU的rpn_batch，data = {'data': im_array, 'im_info': im_info}，label = {'gt_landmarks'，'gt_boxes'}
data, label = get_crop_batch(roidb) # 返回真实label
# print('core/loader: label.shape = ', np.array(label).shape,'\n')
data_list += data
label_list += label # 每个元素为一张图片
# print('core/loader: label_list.shape = ',np.array(label_list).shape)
# print('core/loader: before!! label_list[0] = ',label_list[0])
select_stride = 0
for data, label in zip(data_list, label_list):
# 这里的label是dict
data_shape = {k: v.shape for k, v in data.items()}
del data_shape['im_info']
im_info = data['im_info']
gt_boxes = label['gt_boxes']
# print('loader/get_batch: in the gt_label! gt_bboxes.shape=',gt_boxes.shape)
gt_label = {'gt_boxes': gt_boxes}
label_dict = {}
if config.FACE_LANDMARK:
gt_landmarks = label['gt_landmarks']
# print('loader/get_batch: in the gt_label! gt_landmarks.shape=', gt_landmarks.shape)
gt_label['gt_landmarks'] = gt_landmarks
# TODO 上面把label赋值给gt_label的操作好像是没有意义的，gt_label与label没有区别. but, 后面label好像变了，但是否影响这里呢？
# ta = datetime.datetime.now()
# TODO：产生训练label
face_label_dict = self.aa.assign_anchor_fpn(
gt_label,
im_info,
config.FACE_LANDMARK,
prefix='face',
select_stride=select_stride)
# print('face_label_dict.keys = ',face_label_dict.keys())
# tb = datetime.datetime.now()
# self._times[0] += (tb-ta).total_seconds()
label_dict.update(face_label_dict)
# print('im_info', im_info.shape)
# print(gt_boxes.shape)
for k in label_name:
label[k] = label_dict[
k] # TODO 这里实际上是在更新label_list, 由zip函数返回的label应该是引用关系
# print('core/loader: after!! label_list[0] = ', label_list[0])
all_data = dict()
for key in data_name:
all_data[key] = tensor_vstack([batch[key] for batch in data_list])
all_label = dict()
for key in label_name:
pad = 0 if key.startswith('bbox_') else -1
# print('label vstack', key, pad, len(label_list), file=sys.stderr)
all_label[key] = tensor_vstack(
[batch[key] for batch in label_list],
pad=pad) # 这里的batch其实就是dict，这个函数的作用是将所有的图片的相同key的list叠起来
# print('batch_key_list len = ',len([batch['gt_boxes'] for batch in label_list]))
labels = {}
data = [np.array(all_data[key]) for key in data_name]
# print('label_list len = ', len([np.array(all_label[key])for key in label_name]))
label_d = {}
for key in label_name:
label_d[key] = all_label[key]
# label = [np.array()for key in label_name] #该list是按照顺序存的，要记住label和本list中的array的对应顺序
# for key in label_d.keys():
# print('{}: {}'.format(key,label_d[key].shape))
return data, label_d
