def convert_net(args, net, blobs):
@op_filter()
def convert_op_name(op):
if args.device != 'gpu':
if op.engine != 'DEPTHWISE_3x3':
op.engine = ''
op.device_option.CopyFrom(caffe2_pb2.DeviceOption())
reset_names(op.input)
reset_names(op.output)
return [op]
@op_filter(type="Python", inputs=['rpn_cls_probs', 'rpn_bbox_pred', 'im_info'])
def convert_gen_proposal(op_in):
gen_proposals_op, ext_input = convert_gen_proposals(
op_in, blobs,
rpn_min_size=float(cfg.TEST.RPN_MIN_SIZE),
rpn_post_nms_topN=cfg.TEST.RPN_POST_NMS_TOP_N,
rpn_pre_nms_topN=cfg.TEST.RPN_PRE_NMS_TOP_N,
rpn_nms_thres=cfg.TEST.RPN_NMS_THRESH,
)
net.external_input.extend([ext_input])
return [gen_proposals_op]
@op_filter(input_has='rois')
def convert_rpn_rois(op):
for j in range(0, len(op.input)):
if op.input[j] == 'rois':
print('Converting op {} input name: rois -> rpn_rois:\n{}'.format(
op.type, op))
op.input[j] = 'rpn_rois'
return [op]
@op_filter(type_in=['StopGradient', 'Alias'])
def convert_remove_op(op):
print('Removing op {}:\n{}'.format(op.type, op))
return []
convert_op_in_proto(net, convert_op_name)
convert_op_in_proto(net, [
convert_gen_proposal, convert_rpn_rois, convert_remove_op
])
reset_names(net.external_input)
reset_names(net.external_output)
reset_blob_names(blobs)
def convert_net(args, net, blobs):
@op_filter()
def convert_op_name(op):
if args.device != 'gpu':
if op.engine != 'DEPTHWISE_3x3':
op.engine = ''
op.device_option.CopyFrom(caffe2_pb2.DeviceOption())
reset_names(op.input)
reset_names(op.output)
return [op]
@op_filter(type="Python",
inputs=['rpn_cls_probs', 'rpn_bbox_pred', 'im_info'])
def convert_gen_proposal(op_in):
gen_proposals_op, ext_input = convert_gen_proposals(
op_in,
blobs,
rpn_min_size=float(cfg.TEST.RPN_MIN_SIZE),
rpn_post_nms_topN=cfg.TEST.RPN_POST_NMS_TOP_N,
rpn_pre_nms_topN=cfg.TEST.RPN_PRE_NMS_TOP_N,
rpn_nms_thres=cfg.TEST.RPN_NMS_THRESH,
)
net.external_input.extend([ext_input])
return [gen_proposals_op]
@op_filter(input_has='rois')
def convert_rpn_rois(op):
for j in range(0, len(op.input)):
if op.input[j] == 'rois':
print('Converting op {} input name: rois -> rpn_rois:\n{}'.
format(op.type, op))
op.input[j] = 'rpn_rois'
return [op]
@op_filter(type_in=['StopGradient', 'Alias'])
def convert_remove_op(op):
print('Removing op {}:\n{}'.format(op.type, op))
return []
convert_op_in_proto(net, convert_op_name)
convert_op_in_proto(
net, [convert_gen_proposal, convert_rpn_rois, convert_remove_op])
reset_names(net.external_input)
reset_names(net.external_output)
reset_blob_names(blobs)
def convert_model_gpu(args, net, init_net):
assert args.device == 'gpu'
ret_net = copy.deepcopy(net)
ret_init_net = copy.deepcopy(init_net)
cdo_cuda = mutils.get_device_option_cuda()
cdo_cpu = mutils.get_device_option_cpu()
CPU_OPS = [
["CollectAndDistributeFpnRpnProposals", None],
["GenerateProposals", None],
["BBoxTransform", None],
["BoxWithNMSLimit", None],
]
CPU_BLOBS = ["im_info", "anchor"]
@op_filter()
def convert_op_gpu(op):
for x in CPU_OPS:
if mutils.filter_op(op, type=x[0], inputs=x[1]):
return None
op.device_option.CopyFrom(cdo_cuda)
return [op]
@op_filter()
def convert_init_op_gpu(op):
if op.output[0] in CPU_BLOBS:
op.device_option.CopyFrom(cdo_cpu)
else:
op.device_option.CopyFrom(cdo_cuda)
return [op]
convert_op_in_proto(ret_init_net.Proto(), convert_init_op_gpu)
convert_op_in_proto(ret_net.Proto(), convert_op_gpu)
ret = core.InjectDeviceCopiesAmongNets([ret_init_net, ret_net])
return [ret[0][1], ret[0][0]]
def convert_model_gpu(args, net, init_net):
assert args.device == 'gpu'
ret_net = copy.deepcopy(net)
ret_init_net = copy.deepcopy(init_net)
cdo_cuda = mutils.get_device_option_cuda()
cdo_cpu = mutils.get_device_option_cpu()
CPU_OPS = [
["CollectAndDistributeFpnRpnProposals", None],
["GenerateProposals", None],
["BBoxTransform", None],
["BoxWithNMSLimit", None],
]
CPU_BLOBS = ["im_info", "anchor"]
@op_filter()
def convert_op_gpu(op):
for x in CPU_OPS:
if mutils.filter_op(op, type=x[0], inputs=x[1]):
return None
op.device_option.CopyFrom(cdo_cuda)
return [op]
@op_filter()
def convert_init_op_gpu(op):
if op.output[0] in CPU_BLOBS:
op.device_option.CopyFrom(cdo_cpu)
else:
op.device_option.CopyFrom(cdo_cuda)
return [op]
convert_op_in_proto(ret_init_net.Proto(), convert_init_op_gpu)
convert_op_in_proto(ret_net.Proto(), convert_op_gpu)
ret = core.InjectDeviceCopiesAmongNets([ret_init_net, ret_net])
return [ret[0][1], ret[0][0]]
def convert_net(args, net, blobs):
@op_filter()
def convert_op_name(op):
if args.device != 'gpu':
if op.engine != 'DEPTHWISE_3x3':
op.engine = ''
op.device_option.CopyFrom(caffe2_pb2.DeviceOption())
reset_names(op.input)
reset_names(op.output)
return [op]
@op_filter(type='Python')
def convert_python(op):
if op.name.startswith('GenerateProposalsOp'):
gen_proposals_op, ext_input = convert_gen_proposals(
op, blobs,
rpn_min_size=float(cfg.TEST.RPN_MIN_SIZE),
rpn_post_nms_topN=cfg.TEST.RPN_POST_NMS_TOP_N,
rpn_pre_nms_topN=cfg.TEST.RPN_PRE_NMS_TOP_N,
rpn_nms_thresh=cfg.TEST.RPN_NMS_THRESH,
)
net.external_input.extend([ext_input])
return [gen_proposals_op]
elif op.name.startswith('CollectAndDistributeFpnRpnProposalsOp'):
collect_dist_op = convert_collect_and_distribute(
op, blobs,
roi_canonical_scale=cfg.FPN.ROI_CANONICAL_SCALE,
roi_canonical_level=cfg.FPN.ROI_CANONICAL_LEVEL,
roi_max_level=cfg.FPN.ROI_MAX_LEVEL,
roi_min_level=cfg.FPN.ROI_MIN_LEVEL,
rpn_max_level=cfg.FPN.RPN_MAX_LEVEL,
rpn_min_level=cfg.FPN.RPN_MIN_LEVEL,
rpn_post_nms_topN=cfg.TEST.RPN_POST_NMS_TOP_N,
)
return [collect_dist_op]
else:
raise ValueError('Failed to convert Python op {}'.format(
op.name))
# Only convert UpsampleNearest to ResizeNearest when converting to pb so that the existing models is unchanged
# https://github.com/facebookresearch/Detectron/pull/372#issuecomment-410248561
@op_filter(type='UpsampleNearest')
def convert_upsample_nearest(op):
for arg in op.arg:
if arg.name == 'scale':
scale = arg.i
break
else:
raise KeyError('No attribute "scale" in UpsampleNearest op')
resize_nearest_op = core.CreateOperator('ResizeNearest',
list(op.input),
list(op.output),
name=op.name,
width_scale=float(scale),
height_scale=float(scale))
return resize_nearest_op
@op_filter()
def convert_rpn_rois(op):
for j in range(len(op.input)):
if op.input[j] == 'rois':
print('Converting op {} input name: rois -> rpn_rois:\n{}'.format(
op.type, op))
op.input[j] = 'rpn_rois'
for j in range(len(op.output)):
if op.output[j] == 'rois':
print('Converting op {} output name: rois -> rpn_rois:\n{}'.format(
op.type, op))
op.output[j] = 'rpn_rois'
return [op]
@op_filter(type_in=['StopGradient', 'Alias'])
def convert_remove_op(op):
print('Removing op {}:\n{}'.format(op.type, op))
return []
# We want to apply to all operators, including converted
# so run separately
convert_op_in_proto(net, convert_remove_op)
convert_op_in_proto(net, convert_upsample_nearest)
convert_op_in_proto(net, convert_python)
convert_op_in_proto(net, convert_op_name)
convert_op_in_proto(net, convert_rpn_rois)
reset_names(net.external_input)
reset_names(net.external_output)
reset_blob_names(blobs)
def convert_net(args, net, blobs):
@op_filter()
def convert_op_name(op):
if args.device != 'gpu':
if op.engine != 'DEPTHWISE_3x3':
op.engine = ''
op.device_option.CopyFrom(caffe2_pb2.DeviceOption())
reset_names(op.input)
reset_names(op.output)
return [op]
@op_filter(type='Python')
def convert_python(op):
if op.name.startswith('GenerateProposalsOp'):
gen_proposals_op, ext_input = convert_gen_proposals(
op, blobs,
rpn_min_size=float(cfg.TEST.RPN_MIN_SIZE),
rpn_post_nms_topN=cfg.TEST.RPN_POST_NMS_TOP_N,
rpn_pre_nms_topN=cfg.TEST.RPN_PRE_NMS_TOP_N,
rpn_nms_thresh=cfg.TEST.RPN_NMS_THRESH,
)
net.external_input.extend([ext_input])
return [gen_proposals_op]
elif op.name.startswith('CollectAndDistributeFpnRpnProposalsOp'):
collect_dist_op = convert_collect_and_distribute(
op, blobs,
roi_canonical_scale=cfg.FPN.ROI_CANONICAL_SCALE,
roi_canonical_level=cfg.FPN.ROI_CANONICAL_LEVEL,
roi_max_level=cfg.FPN.ROI_MAX_LEVEL,
roi_min_level=cfg.FPN.ROI_MIN_LEVEL,
rpn_max_level=cfg.FPN.RPN_MAX_LEVEL,
rpn_min_level=cfg.FPN.RPN_MIN_LEVEL,
rpn_post_nms_topN=cfg.TEST.RPN_POST_NMS_TOP_N,
)
return [collect_dist_op]
else:
raise ValueError('Failed to convert Python op {}'.format(
op.name))
# Only convert UpsampleNearest to ResizeNearest when converting to pb so that the existing models is unchanged
# https://github.com/facebookresearch/Detectron/pull/372#issuecomment-410248561
@op_filter(type='UpsampleNearest')
def convert_upsample_nearest(op):
for arg in op.arg:
if arg.name == 'scale':
scale = arg.i
break
else:
raise KeyError('No attribute "scale" in UpsampleNearest op')
resize_nearest_op = core.CreateOperator('ResizeNearest',
list(op.input),
list(op.output),
name=op.name,
width_scale=float(scale),
height_scale=float(scale))
return resize_nearest_op
@op_filter()
def convert_rpn_rois(op):
for j in range(len(op.input)):
if op.input[j] == 'rois':
print('Converting op {} input name: rois -> rpn_rois:\n{}'.format(
op.type, op))
op.input[j] = 'rpn_rois'
for j in range(len(op.output)):
if op.output[j] == 'rois':
print('Converting op {} output name: rois -> rpn_rois:\n{}'.format(
op.type, op))
op.output[j] = 'rpn_rois'
return [op]
@op_filter(type_in=['StopGradient', 'Alias'])
def convert_remove_op(op):
print('Removing op {}:\n{}'.format(op.type, op))
return []
# We want to apply to all operators, including converted
# so run separately
convert_op_in_proto(net, convert_remove_op)
convert_op_in_proto(net, convert_upsample_nearest)
convert_op_in_proto(net, convert_python)
convert_op_in_proto(net, convert_op_name)
convert_op_in_proto(net, convert_rpn_rois)
reset_names(net.external_input)
reset_names(net.external_output)
reset_blob_names(blobs)
