def TranslateModel(cls, caffe_net, pretrained_net,
net_state=caffe_pb2.NetState()):
net = caffe2_pb2.NetDef()
net.name = caffe_net.name
net_params = caffe2_pb2.TensorProtos()
if len(caffe_net.layer) == 0:
raise ValueError('I think something is wrong. This translation script '
'only accepts new style layers that are stored in the '
'layer field.')
for layer in caffe_net.layer:
if not _ShouldInclude(net_state, layer):
print 'Current net state does not need layer', layer.name
continue
print 'Translate layer', layer.name
# Get pretrained one
pretrained_layers = (
[l for l in pretrained_net.layer if l.name == layer.name] +
[l for l in pretrained_net.layers if l.name == layer.name])
if len(pretrained_layers) > 1:
raise ValueError('huh? more than one pretrained layer of one name?')
elif len(pretrained_layers) == 1:
pretrained_blobs = [utils.CaffeBlobToNumpyArray(blob)
for blob in pretrained_layers[0].blobs]
else:
# No pretrained layer for the given layer name. We'll just pass no
# parameter blobs.
# print 'No pretrained layer for layer', layer.name
pretrained_blobs = []
operators, params = cls.TranslateLayer(layer, pretrained_blobs)
net.op.extend(operators)
net_params.protos.extend(params)
return net, net_params
def TranslateModel(
cls,
caffe_net,
pretrained_net,
is_test=False,
net_state=None,
remove_legacy_pad=False,
input_dims=None
):
net_state = caffe_pb2.NetState() if net_state is None else net_state
net = caffe2_pb2.NetDef()
net.name = caffe_net.name
net_params = caffe2_pb2.TensorProtos()
if len(caffe_net.layers) > 0:
raise ValueError(
'I think something is wrong. This translation script '
'only accepts new style layers that are stored in the '
'layer field.'
)
if not input_dims:
input_dims = _GetInputDims(caffe_net)
for layer in caffe_net.layer:
if not _ShouldInclude(net_state, layer):
log.info('Current net state does not need layer {}'
.format(layer.name))
continue
log.info('Translate layer {}'.format(layer.name))
# Get pretrained one
pretrained_layers = (
[l for l in pretrained_net.layer
if l.name == layer.name] + [l
for l in pretrained_net.layers
if l.name == layer.name]
)
if len(pretrained_layers) > 1:
raise ValueError(
'huh? more than one pretrained layer of one name?')
elif len(pretrained_layers) == 1:
pretrained_blobs = [
utils.CaffeBlobToNumpyArray(blob)
for blob in pretrained_layers[0].blobs
]
else:
# No pretrained layer for the given layer name. We'll just pass
# no parameter blobs.
# print 'No pretrained layer for layer', layer.name
pretrained_blobs = []
operators, params = cls.TranslateLayer(
layer, pretrained_blobs, is_test, net=net,
net_params=net_params, input_dims=input_dims)
net.op.extend(operators)
net_params.protos.extend(params)
if remove_legacy_pad:
assert input_dims, \
'Please specify input_dims to remove legacy_pad'
net = _RemoveLegacyPad(net, net_params, input_dims)
return net, net_params
def TranslateModel(
cls,
caffe_net,
pretrained_net,
is_test=False,
input_mean=None,
net_state=None,
):
net_state = caffe_pb2.NetState() if net_state is None else net_state
net = caffe2_pb2.NetDef()
net.name = caffe_net.name
net_params = caffe2_pb2.TensorProtos()
if len(caffe_net.layer) == 0:
raise ValueError(
'I think something is wrong. This translation script '
'only accepts new style layers that are stored in the '
'layer field.')
if input_mean:
caffenet_mean = caffe_pb2.BlobProto()
caffenet_mean.ParseFromString(open(input_mean, 'rb').read())
mean_ = utils.CaffeBlobToNumpyArray(caffenet_mean)
mean_tensor = utils.NumpyArrayToCaffe2Tensor(mean_, 'mean_')
net_params.protos.extend([mean_tensor])
mean_op = caffe2_pb2.OperatorDef()
mean_op.type = 'Sub'
mean_op.input.extend(['data_', 'mean_'])
# Assume that input blob's name is "data"
mean_op.output.extend(['data'])
net.op.extend([mean_op])
i = 0
while i < len(caffe_net.layer):
if not _ShouldInclude(net_state, caffe_net.layer[i]):
log.info('Current net state does not need layer {}'.format(
caffe_net.layer[i].name))
continue
log.info('Translate layer {}'.format(caffe_net.layer[i].name))
# Get pretrained one
pretrained_layers_index = ([
l for l in xrange(len(pretrained_net.layer))
if pretrained_net.layer[l].name == caffe_net.layer[i].name
] + [
l for l in xrange(len(pretrained_net.layers))
if pretrained_net.layers[l].name == caffe_net.layer[i].name
])
is_bn = False
if len(pretrained_layers_index) > 1:
raise ValueError(
'huh? more than one pretrained layer of one name?')
elif len(pretrained_layers_index) == 1:
if pretrained_net.layer[
pretrained_layers_index[0]].type == "BatchNorm":
# A Scale layer should follow BatchNorm layer
# according to paper https://arxiv.org/abs/1502.03167.
assert pretrained_net.layer[pretrained_layers_index[0] +
1].type == "Scale"
pretrained_blobs = [utils.CaffeBlobToNumpyArray(blob)
for blob in pretrained_net.layer[pretrained_layers_index[0]].blobs] + \
[utils.CaffeBlobToNumpyArray(blob)
for blob in pretrained_net.layer[pretrained_layers_index[0] + 1].blobs]
is_bn = True
else:
pretrained_blobs = [
utils.CaffeBlobToNumpyArray(blob) for blob in
pretrained_net.layer[pretrained_layers_index[0]].blobs
]
else:
# No pretrained layer for the given layer name. We'll just pass
# no parameter blobs.
# print 'No pretrained layer for layer', layer.name
pretrained_blobs = []
operators, params = cls.TranslateLayer(caffe_net.layer[i],
pretrained_blobs, is_test)
net.op.extend(operators)
net_params.protos.extend(params)
if is_bn:
i += 2
else:
i += 1
return net, net_params
def TranslateModel(cls,
caffe_net,
pretrained_net,
is_test=False,
net_state=None,
remove_legacy_pad=False,
input_dims=None):
net_state = caffe_pb2.NetState() if net_state is None else net_state
net = caffe2_pb2.NetDef()
net.name = caffe_net.name
net_params = caffe2_pb2.TensorProtos()
if len(caffe_net.layers) > 0:
raise ValueError(
'I think something is wrong. This translation script '
'only accepts new style layers that are stored in the '
'layer field.')
if not input_dims:
input_dims = _GetInputDims(caffe_net)
for layer in caffe_net.layer:
if not _ShouldInclude(net_state, layer):
log.info('Current net state does not need layer {}'.format(
layer.name))
continue
log.info('Translate layer {}'.format(layer.name))
# Get pretrained one
pretrained_layers = (
[l for l in pretrained_net.layer if l.name == layer.name] +
[l for l in pretrained_net.layers if l.name == layer.name])
if len(pretrained_layers) > 1:
print('>>> huh? more than one pretrained layer of one name?')
print(
'>>> Assuming these layers have no trainable parameters (e.g relu or pooling)'
)
print([(pt.name, pt.type) for pt in pretrained_layers])
pt_types = [pt.type for pt in pretrained_layers]
if len(set(pt_types)) == len(pt_types):
print(
'>>> But, just in case, try to match layer types since types are unique. If not, do not transfer params.'
)
for pt in pretrained_layers:
if pt.type == layer.type:
print ' Found matching type {}'.format(layer.type)
print ' Setting pretrained blobs'
pretrained_blobs = [
utils.CaffeBlobToNumpyArray(blob)
for blob in pt.blobs
]
#print pretrained_blobs
else:
print('>>> Setting pretrained blobs = []')
pretrained_blobs = []
#raise ValueError(
# 'huh? more than one pretrained layer of one name?')
elif len(pretrained_layers) == 1:
pretrained_blobs = [
utils.CaffeBlobToNumpyArray(blob)
for blob in pretrained_layers[0].blobs
]
else:
# No pretrained layer for the given layer name. We'll just pass
# no parameter blobs.
# print 'No pretrained layer for layer', layer.name
pretrained_blobs = []
operators, params = cls.TranslateLayer(layer,
pretrained_blobs,
is_test,
net=net,
net_params=net_params,
input_dims=input_dims)
net.op.extend(operators)
net_params.protos.extend(params)
if remove_legacy_pad:
assert input_dims, \
'Please specify input_dims to remove legacy_pad'
net = _RemoveLegacyPad(net, net_params, input_dims)
return net, net_params
