def ResNet_roi_conv5_head_for_masks(dim_in):
"""ResNet "conv5" / "stage5" head for predicting masks."""
dilation = cfg.MRCNN.DILATION
stride_init = cfg.MRCNN.ROI_XFORM_RESOLUTION // 7 # by default: 2
module, dim_out = ResNet.add_stage(dim_in, 2048, 512, 3, dilation,
stride_init)
return module, dim_out
def add_ResNet_roi_conv5_head_for_masks(
model, blob_in, dim_in, spatial_scale, preprefix='_[mask]_',
dilation=1, shared=False):
assert not shared, \
'Using shared ResNet stage not supported (temporarily)'
model.RoIFeatureTransform(
blob_in,
blob_out=preprefix + 'pool5',
blob_rois='mask_rois',
method=cfg.MRCNN.ROI_XFORM_METHOD,
resolution=cfg.MRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.MRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale)
stride_init = int(cfg.MRCNN.ROI_XFORM_RESOLUTION / 7) # by default: 2
if not shared:
s, dim_in = ResNet.add_stage(
model, preprefix + 'res5', preprefix + 'pool5',
3, dim_in, 2048, 512, dilation, stride_init=stride_init)
else:
s, dim_in = ResNet.add_stage_shared(
model, preprefix, 'res5', preprefix + 'pool5',
3, dim_in, 2048, 512, dilation, stride_init=stride_init)
return s, 2048, spatial_scale
def add_ResNet_roi_conv5_head_for_keypoints(model, blob_in, dim_in,
spatial_scale):
"""Add a ResNet "conv5" / "stage5" head for Mask R-CNN keypoint prediction.
"""
model.RoIFeatureTransform(
blob_in,
'_[pose]_pool5',
blob_rois='keypoint_rois',
method=cfg.KRCNN.ROI_XFORM_METHOD,
resolution=cfg.KRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.KRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale)
# Using the prefix '_[pose]_' to 'res5' enables initializing the head's
# parameters using pretrained 'res5' parameters if given (see
# utils.net.initialize_gpu_0_from_weights_file)
s, dim_in = ResNet.add_stage(model,
'_[pose]_res5',
'_[pose]_pool5',
3,
dim_in,
2048,
512,
cfg.KRCNN.DILATION,
stride_init=int(
cfg.KRCNN.ROI_XFORM_RESOLUTION / 7))
return s, 2048
def add_ResNet_roi_conv5_head_for_masks(model, blob_in, dim_in, spatial_scale):
"""Add a ResNet "conv5" / "stage5" head for predicting masks."""
model.RoIFeatureTransform(
blob_in,
blob_out='_[mask]_pool5',
blob_rois='mask_rois',
method=cfg.MRCNN.ROI_XFORM_METHOD,
resolution=cfg.MRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.MRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale)
dilation = cfg.MRCNN.DILATION
stride_init = int(cfg.MRCNN.ROI_XFORM_RESOLUTION / 7) # by default: 2
s, dim_in = ResNet.add_stage(model,
'_[mask]_res5',
'_[mask]_pool5',
3,
dim_in,
2048,
512,
dilation,
stride_init=stride_init)
return s, 2048
def add_ResNet_roi_conv5_head_for_keypoints(
model, blob_in, dim_in, spatial_scale
):
"""Add a ResNet "conv5" / "stage5" head for Mask R-CNN keypoint prediction.
"""
model.RoIFeatureTransform(
blob_in,
'_[pose]_pool5',
blob_rois='keypoint_rois',
method=cfg.KRCNN.ROI_XFORM_METHOD,
resolution=cfg.KRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.KRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale
)
# Using the prefix '_[pose]_' to 'res5' enables initializing the head's
# parameters using pretrained 'res5' parameters if given (see
# utils.net.initialize_gpu_0_from_weights_file)
s, dim_in = ResNet.add_stage(
model,
'_[pose]_res5',
'_[pose]_pool5',
3,
dim_in,
2048,
512,
cfg.KRCNN.DILATION,
stride_init=int(cfg.KRCNN.ROI_XFORM_RESOLUTION / 7)
)
return s, 2048
def add_ResNet_roi_conv5_head_for_masks(model, blob_in, dim_in, spatial_scale):
"""Add a ResNet "conv5" / "stage5" head for predicting masks."""
model.RoIFeatureTransform(
blob_in,
blob_out='_[mask]_pool5',
blob_rois='mask_rois',
method=cfg.MRCNN.ROI_XFORM_METHOD,
resolution=cfg.MRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.MRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale
)
dilation = cfg.MRCNN.DILATION
stride_init = int(cfg.MRCNN.ROI_XFORM_RESOLUTION / 7) # by default: 2
s, dim_in = ResNet.add_stage(
model,
'_[mask]_res5',
'_[mask]_pool5',
3,
dim_in,
2048,
512,
dilation,
stride_init=stride_init
)
return s, 2048
def add_ResNet_roi_conv5_head_for_keypoints(
model, blob_in, dim_in, spatial_scale):
model.RoIFeatureTransform(
blob_in, '_[pose]_pool5',
blob_rois='keypoint_rois',
method=cfg.KRCNN.ROI_XFORM_METHOD,
resolution=cfg.KRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.KRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale)
s, dim_in = ResNet.add_stage(
model, '_[pose]_res5', '_[pose]_pool5',
3, dim_in, 2048, 512, cfg.KRCNN.DILATION,
stride_init=int(cfg.KRCNN.ROI_XFORM_RESOLUTION / 7))
return s, 2048, spatial_scale
def add_ResNet_roi_conv5_head_for_keypoints(model, blob_in, dim_in,
spatial_scale):
model.RoIFeatureTransform(
blob_in,
'_[pose]_pool5',
blob_rois='keypoint_rois',
method=cfg.KRCNN.ROI_XFORM_METHOD,
resolution=cfg.KRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.KRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale)
s, dim_in = ResNet.add_stage(model,
'_[pose]_res5',
'_[pose]_pool5',
3,
dim_in,
2048,
512,
cfg.KRCNN.DILATION,
stride_init=int(
cfg.KRCNN.ROI_XFORM_RESOLUTION / 7))
return s, 2048, spatial_scale
def ResNet_roi_conv5_head_for_masks(dim_in):
"""ResNet "conv5" / "stage5" head for predicting masks."""
dilation = cfg.MRCNN.DILATION
stride_init = cfg.MRCNN.ROI_XFORM_RESOLUTION // 7 # by default: 2
module, dim_out = ResNet.add_stage(dim_in, 2048, 512, 3, dilation, stride_init)
return module, dim_out