def get_minibatch_mul(roidb):
"""Given a roidb, construct a minibatch sampled from it."""
# We collect blobs from each image onto a list and then concat them into a
# single tensor, hence we initialize each blob to an empty list
blobs = {k: [] for k in get_minibatch_blob_names()}
#print("minibatch.py 157 ---------{}".format(len(roidb)))
# Get the input image blob, formatted for caffe2
im_blob, im_scales, roidb_ = _get_img_blob_mul(roidb)
blobs['data'] = im_blob
if cfg.RPN.RPN_ON:
# # RPN-only or end-to-end Faster/Mask R-CNN
valid = rpn_roi_data.add_rpn_blobs(blobs, im_scales, roidb_)
return blobs, valid
if cfg.RETINANET.RETINANET_ON:
im_width, im_height = im_blob.shape[3], im_blob.shape[2]
# im_width, im_height corresponds to the network input: padded image
# (if needed) width and height. We pass it as input and slice the data
# accordingly so that we don't need to use SampleAsOp
valid = retinanet_roi_data.add_retinanet_blobs(blobs, im_scales,
roidb_, im_width,
im_height)
else:
# Fast R-CNN like models trained on
# precomputed proposals
valid = fast_rcnn_roi_data.add_fast_rcnn_blobs(blobs, im_scales,
roidb_)
return blobs, valid
def get_minibatch_s6(roidb, roidb_noclass):
"""Given a roidb, construct a minibatch sampled from it."""
# We collect blobs from each image onto a list and then concat them into a
# single tensor, hence we initialize each blob to an empty list
if 0:
random_bbox = dict()
random_bbox['kernel_size'] = 224
random_bbox['tl_x'] = random.randint(0, 800)
random_bbox['tl_y'] = random.randint(0, 800)
blobs = {k: [] for k in get_minibatch_blob_names()}
# Get the input image blob, formatted for caffe2
im_blob, im_scales, error_flag = _get_image_blob_s6(roidb, roidb_noclass)
blobs['data'] = im_blob
if cfg.RPN.RPN_ON:
# RPN-only or end-to-end Faster/Mask R-CNN
valid = rpn_roi_data.add_rpn_blobs(blobs, im_scales, roidb)
elif cfg.RETINANET.RETINANET_ON:
im_width, im_height = im_blob.shape[3], im_blob.shape[2]
# im_width, im_height corresponds to the network input: padded image
# (if needed) width and height. We pass it as input and slice the data
# accordingly so that we don't need to use SampleAsOp
valid = retinanet_roi_data.add_retinanet_blobs(blobs, im_scales, roidb,
im_width, im_height)
else:
# Fast R-CNN like models trained on precomputed proposals
valid = fast_rcnn_roi_data.add_fast_rcnn_blobs(blobs, im_scales, roidb)
return blobs, valid
def get_minibatch(roidb):
"""载入roidb,构建一个minibatch采样."""
# We collect blobs from each image onto a list and then concat them into a
# single tensor, hence we initialize each blob to an empty list
# 生成空字典数据 如 {'data': [], 'fpn_labels_int32_wide_fpn1': []}等
#print("现在执行的是无扩增版本")
blobs = {k: [] for k in get_minibatch_blob_names()}
print("blobs is ", blobs)
# Get the input image blob, formatted for caffe2
im_blob, im_scales = _get_image_blob(roidb)
blobs['data'] = im_blob
if cfg.RPN.RPN_ON:
# RPN-only or end-to-end Faster/Mask R-CNN
valid = rpn_roi_data.add_rpn_blobs(blobs, im_scales, roidb)
elif cfg.RETINANET.RETINANET_ON:
im_width, im_height = im_blob.shape[3], im_blob.shape[2]
# im_width, im_height corresponds to the network input: padded image
# (if needed) width and height. We pass it as input and slice the data
# accordingly so that we don't need to use SampleAsOp
valid = retinanet_roi_data.add_retinanet_blobs(blobs, im_scales, roidb,
im_width, im_height)
else:
# Fast R-CNN like models trained on precomputed proposals
valid = fast_rcnn_roi_data.add_fast_rcnn_blobs(blobs, im_scales, roidb)
return blobs, valid
def get_minibatch(roidb):
"""Given a roidb, construct a minibatch sampled from it."""
# We collect blobs from each image onto a list and then concat them into a
# single tensor, hence we initialize each blob to an empty list
blobs = {k: [] for k in get_minibatch_blob_names()}
# Get the input image blob, formatted for caffe2
im_blob, im_scales = _get_image_blob(roidb)
blobs['data'] = im_blob
# Calculate tracking metadata if using pre-calculated blobs
if len(cfg.DATA_LOADER.EXTRA_BLOBS):
blobs_extra = _get_extra_blobs(roidb)
blobs.update(blobs_extra)
if 'track_n_rois' in cfg.DATA_LOADER.EXTRA_BLOBS:
blobs.update({
'track_n_rois_one': [blobs_extra['track_n_rois'][0]],
'track_n_rois_two': [blobs_extra['track_n_rois'][1]],
})
if cfg.RPN.RPN_ON:
# RPN-only or end-to-end Faster/Mask R-CNN
valid = rpn_roi_data.add_rpn_blobs(blobs, im_scales, roidb)
elif cfg.RETINANET.RETINANET_ON:
im_width, im_height = im_blob.shape[3], im_blob.shape[2]
# im_width, im_height corresponds to the network input: padded image
# (if needed) width and height. We pass it as input and slice the data
# accordingly so that we don't need to use SampleAsOp
valid = retinanet_roi_data.add_retinanet_blobs(blobs, im_scales, roidb,
im_width, im_height)
else:
# Fast R-CNN like models trained on precomputed proposals
valid = fast_rcnn_roi_data.add_fast_rcnn_blobs(blobs, im_scales, roidb)
return blobs, valid
def get_minibatch(roidb):
"""Given a roidb, construct a minibatch sampled from it."""
# We collect blobs from each image onto a list and then concat them into a
# single tensor, hence we initialize each blob to an empty list
blobs = {k: [] for k in get_minibatch_blob_names()}
# Get the input image blob, formatted for caffe2
im_blob, im_scales, im_crops = _get_image_blob(roidb)
blobs['data'] = im_blob
# row col row col to x1 y1 x2 y2
im_crops = np.array(im_crops, dtype=np.int32)
im_crops = im_crops[:, (1, 0, 3, 2)]
if cfg.REID.APM:
valid = reid_apm_roi_data.add_reid_blobs(blobs, im_scales, im_crops,
roidb)
else:
valid = reid_roi_data.add_reid_blobs(blobs, im_scales, roidb)
return blobs, valid
if cfg.RPN.RPN_ON:
# RPN-only or end-to-end Faster/Mask R-CNN
valid = rpn_roi_data.add_rpn_blobs(blobs, im_scales, roidb)
elif cfg.RETINANET.RETINANET_ON:
im_width, im_height = im_blob.shape[3], im_blob.shape[2]
# im_width, im_height corresponds to the network input: padded image
# (if needed) width and height. We pass it as input and slice the data
# accordingly so that we don't need to use SampleAsOp
valid = retinanet_roi_data.add_retinanet_blobs(blobs, im_scales, roidb,
im_width, im_height)
else:
# Fast R-CNN like models trained on precomputed proposals
valid = fast_rcnn_roi_data.add_fast_rcnn_blobs(blobs, im_scales, roidb)
return blobs, valid
def get_minibatch(roidb):
"""Given a roidb, construct a minibatch sampled from it."""
# We collect blobs from each image onto a list and then concat them into a
# single tensor, hence we initialize each blob to an empty list
blobs = {k: [] for k in get_minibatch_blob_names()}
# Get the input image blob, formatted for caffe2
im_blob, im_scales = _get_image_blob(roidb)
blobs['data'] = im_blob
if cfg.RPN.RPN_ON:
# RPN-only or end-to-end Faster/Mask R-CNN
valid = rpn_roi_data.add_rpn_blobs(blobs, im_scales, roidb)
elif cfg.RETINANET.RETINANET_ON:
im_width, im_height = im_blob.shape[3], im_blob.shape[2]
# im_width, im_height corresponds to the network input: padded image
# (if needed) width and height. We pass it as input and slice the data
# accordingly so that we don't need to use SampleAsOp
valid = retinanet_roi_data.add_retinanet_blobs(
blobs, im_scales, roidb, im_width, im_height
)
else:
# Fast R-CNN like models trained on precomputed proposals
valid = fast_rcnn_roi_data.add_fast_rcnn_blobs(blobs, im_scales, roidb)
return blobs, valid
def get_minibatch(roidb):
"""Given a roidb, construct a minibatch sampled from it."""
# We collect blobs from each image onto a list and then concat them into a
# single tensor, hence we initialize each blob to an empty list
blobs = {k: [] for k in get_minibatch_blob_names()}
# Get the input image blob, formatted for caffe2
# im_blob, im_scales = _get_image_blob(roidb)
im_blob, im_scales, pose_pred, pose_line, blobs['seg_gt_label'] = _get_image_pose_blob(roidb) # pose_pred the same shape with im_blob
blobs['data'] = im_blob
blobs['normalizer'] = np.array([100], dtype=np.float32)
if 'LIP' in cfg.TRAIN.DATASETS[0]:
blobs['pose_pred_4'], blobs['pose_pred_8'], blobs['pose_pred_16'], blobs['pose_pred_32'] = _resize_pose_blob(pose_pred, channel=26)
else:
blobs['pose_pred_4'], blobs['pose_pred_8'], blobs['pose_pred_16'], blobs['pose_pred_32'] = _resize_pose_blob(pose_pred, channel=26)
# blobs['pose_pred_8'], blobs['pose_pred_16'] = _resize_pose_blob_to13(pose_pred) # pose 16 to 13 channel
# blobs['pose_sum_8'], blobs['pose_sum_16'] = pose_sum_to_onehotmap(blobs['pose_pred_8'], blobs['pose_pred_16'])
blobs['pose_line_8'], blobs['pose_line_16'] = _resize_poseline_blob(pose_line)
if cfg.RPN.RPN_ON:
# RPN-only or end-to-end Faster/Mask R-CNN
valid = rpn_roi_data.add_rpn_blobs(blobs, im_scales, roidb)
elif cfg.RETINANET.RETINANET_ON:
im_width, im_height = im_blob.shape[3], im_blob.shape[2]
# im_width, im_height corresponds to the network input: padded image
# (if needed) width and height. We pass it as input and slice the data
# accordingly so that we don't need to use SampleAsOp
valid = retinanet_roi_data.add_retinanet_blobs(
blobs, im_scales, roidb, im_width, im_height
)
else:
# Fast R-CNN like models trained on precomputed proposals
valid = fast_rcnn_roi_data.add_fast_rcnn_blobs(blobs, im_scales, roidb)
# blobs['pose_pred'] = pose_pred_model.pred_pose_batch(roidb)
# pose_pred_model.draw_batch(blobs['pose_pred'], roidb)
# blobs['pose_pred'] = _get_pose_pred(roidb)
# logger.info(blobs['pose_pred'].shape)
return blobs, valid
