[im_height, im_width, im_scale]
scales : list/tuple of float
- Scales of anchor windoes.
+ Scales of anchor windows.
ratios : list/tuple of float
- Ratios of anchor windoes.
+ Ratios of anchor windows.
feature_stride : int
The size of the receptive field each unit in the convolution layer of the rpn, for example
The last dimension is in format of [w_start, h_start, w_end, h_end, score]
scales : list/tuple of float
- Scales of anchor windoes.
+ Scales of anchor windows.
ratios : list/tuple of float
- Ratios of anchor windoes.
+ Ratios of anchor windows.
feature_stride : int
The size of the receptive field each unit in the convolution layer of the rpn, for example
2-D with shape [batch, 3]
scales : list/tuple of float
- Scales of anchor windoes.
+ Scales of anchor windows.
ratios : list/tuple of float
- Ratios of anchor windoes.
+ Ratios of anchor windows.
feature_stride : int
The size of the receptive field each unit in the convolution layer of the rpn, for example
The last dimension is in format of [w_start, h_start, w_end, h_end, score]
scales : list/tuple of float
- Scales of anchor windoes.
+ Scales of anchor windows.
ratios : list/tuple of float
- Ratios of anchor windoes.
+ Ratios of anchor windows.
feature_stride : int
The size of the receptive field each unit in the convolution layer of the rpn, for example
2-D with shape [batch, 3]
scales : list/tuple of float
- Scales of anchor windoes.
+ Scales of anchor windows.
ratios : list/tuple of float
- Ratios of anchor windoes.
+ Ratios of anchor windows.
feature_stride : int
The size of the receptive field each unit in the convolution layer of the rpn, for example