def get_vgg_text_rpn(data, label, bbox_target, bbox_weight, num_anchors=10):
"""
Region Proposal Network with VGG
:param num_anchors: used to determine output size
:return: Symbol
"""
# shared convolutional layers
relu5_3 = get_mobilenet_text_conv(data)
_,relu_shape,_ = relu5_3.infer_shape_partial()
shape = relu_shape[0]
# RPN
rpn_conv = mx.symbol.Convolution(
data=relu5_3, kernel=(3, 3), pad=(1, 1), num_filter=512, name="rpn_conv_3x3")
bilstm = rnn.BidirectionalCell(
rnn.LSTMCell(128, prefix="l_"),
rnn.LSTMCell(128, prefix='r_')
)
#mx.symbol.RNN
rpn_conv_t = mx.symbol.transpose(rpn_conv, axes=(0, 2, 3, 1))
rpn_conv_t = mx.symbol.reshape(rpn_conv_t, shape=(-3, -2))
lstm_o, _ = bilstm.unroll(shape[0] * shape[3], rpn_conv_t, layout='NTC', merge_outputs=True)
pred = mx.sym.FullyConnected(data=lstm_o, num_hidden=512, flatten=False, name='lstm_proj')
pred = mx.sym.reshape(pred, shape=(shape[0], shape[2], shape[3], 512))
pred = mx.symbol.transpose(pred, axes=(0, 3, 1, 2))
rpn_relu = mx.symbol.Activation(data=pred, act_type="relu", name="rpn_relu")
rpn_cls_score = mx.symbol.Convolution(
data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=2 * num_anchors, name="rpn_cls_score")
rpn_bbox_pred = mx.symbol.Convolution(
data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=4 * num_anchors, name="rpn_bbox_pred")
# prepare rpn data
rpn_cls_score_reshape = mx.symbol.Reshape(
data=rpn_cls_score, shape=(0, 2, -1, 0), name="rpn_cls_score_reshape")
# classification
cls_prob = mx.symbol.SoftmaxOutput(data=rpn_cls_score_reshape, label=label, multi_output=True,
normalization='valid', use_ignore=True, ignore_label=-1, name="cls_prob")
# bounding box regression
bbox_loss_ = bbox_weight * mx.symbol.smooth_l1(name='bbox_loss_', scalar=3.0, data=(rpn_bbox_pred - bbox_target))
bbox_loss = mx.sym.MakeLoss(name='bbox_loss', data=bbox_loss_, grad_scale=1.0 / config.TRAIN.RPN_BATCH_SIZE)
# group output
group = mx.symbol.Group([cls_prob, bbox_loss])
return group
def get_vgg_text_rpn_test(data, im_info, num_anchors=10):
"""
Region Proposal Network with VGG
:param num_anchors: used to determine output size
:return: Symbol
"""
# shared convolutional layers
relu5_3 = get_mobilenet_text_conv(data)
_,relu_shape,_ = relu5_3.infer_shape_partial()
shape = relu_shape[0]
# RPN
rpn_conv = mx.symbol.Convolution(
data=relu5_3, kernel=(3, 3), pad=(1, 1), num_filter=512, name="rpn_conv_3x3")
bilstm = rnn.BidirectionalCell(
rnn.LSTMCell(128, prefix="l_"),
rnn.LSTMCell(128, prefix='r_')
)
rpn_conv_t = mx.symbol.transpose(rpn_conv, axes=(0, 2, 3, 1))
rpn_conv_t = mx.symbol.reshape(rpn_conv_t, shape=(-3, -2))
lstm_o, _ = bilstm.unroll(shape[0] * shape[3], rpn_conv_t, layout='NTC', merge_outputs=True)
pred = mx.sym.FullyConnected(data=lstm_o, num_hidden=512, flatten=False, name='lstm_proj')
pred = mx.sym.reshape(pred, shape=(shape[0], shape[2], shape[3], 512))
pred = mx.symbol.transpose(pred, axes=(0, 3, 1, 2))
rpn_relu = mx.symbol.Activation(data=pred, act_type="relu", name="rpn_relu")
rpn_cls_score = mx.symbol.Convolution(
data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=2 * num_anchors, name="rpn_cls_score")
rpn_bbox_pred = mx.symbol.Convolution(
data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=4 * num_anchors, name="rpn_bbox_pred")
# ROI Proposal
rpn_cls_score_reshape = mx.symbol.Reshape(
data=rpn_cls_score, shape=(0, 2, -1, 0), name="rpn_cls_score_reshape")
rpn_cls_prob = mx.symbol.SoftmaxActivation(
data=rpn_cls_score_reshape, mode="channel", name="rpn_cls_prob")
rpn_cls_prob_reshape = mx.symbol.Reshape(
data=rpn_cls_prob, shape=(0, 2 * num_anchors, -1, 0), name='rpn_cls_prob_reshape')
if config.TEST.CXX_PROPOSAL:
rois = mx.symbol.contrib.Proposal(
cls_prob=rpn_cls_prob_reshape, bbox_pred=rpn_bbox_pred, im_info=im_info, name='rois', output_score=True,
feature_stride=config.RPN_FEAT_STRIDE, scales=tuple(config.ANCHOR_SCALES), ratios=tuple(config.ANCHOR_RATIOS),
rpn_pre_nms_top_n=config.TEST.PROPOSAL_PRE_NMS_TOP_N, rpn_post_nms_top_n=config.TEST.PROPOSAL_POST_NMS_TOP_N,
threshold=config.TEST.PROPOSAL_NMS_THRESH, rpn_min_size=config.TEST.PROPOSAL_MIN_SIZE)
else:
rois = mx.symbol.Custom(
cls_prob=rpn_cls_prob_reshape, bbox_pred=rpn_bbox_pred, im_info=im_info, name='rois', output_score=True,
op_type='proposal', feat_stride=config.RPN_FEAT_STRIDE,
scales=tuple(config.ANCHOR_SCALES), ratios=tuple(config.ANCHOR_RATIOS),
rpn_pre_nms_top_n=config.TEST.PROPOSAL_PRE_NMS_TOP_N, rpn_post_nms_top_n=config.TEST.PROPOSAL_POST_NMS_TOP_N,
threshold=config.TEST.PROPOSAL_NMS_THRESH, rpn_min_size=config.TEST.PROPOSAL_MIN_SIZE)
# rois = group[0]
# score = group[1]
group = rois #mx.sym.Group([rois, rpn_cls_prob_reshape, rpn_bbox_pred])
return group