Python caffe.proto.caffe_pb2.BlobProto() Examples

The following are 20 code examples of caffe.proto.caffe_pb2.BlobProto(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module caffe.proto.caffe_pb2 , or try the search function .
Example #1
Source File: pickle_caffe_blobs.py    From masktextspotter.caffe2 with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #2
Source File: convert.py    From tensorflow-resnet with MIT License 5 votes vote down vote up 
def load_mean_bgr():
    """ bgr mean pixel value image, [0, 255]. [height, width, 3] """
    with open("data/ResNet_mean.binaryproto", mode='rb') as f:
        data = f.read()
    blob = caffe_pb2.BlobProto()
    blob.ParseFromString(data)

    mean_bgr = caffe.io.blobproto_to_array(blob)[0]
    assert mean_bgr.shape == (3, 224, 224)

    return mean_bgr.transpose((1, 2, 0))
Example #3
Source File: io.py    From TF2 with Apache License 2.0 5 votes vote down vote up 
def array_to_blobproto(arr, diff=None):
    """Converts a N-dimensional array to blob proto. If diff is given, also
    convert the diff. You need to make sure that arr and diff have the same
    shape, and this function does not do sanity check.
    """
    blob = caffe_pb2.BlobProto()
    blob.shape.dim.extend(arr.shape)
    blob.data.extend(arr.astype(float).flat)
    if diff is not None:
        blob.diff.extend(diff.astype(float).flat)
    return blob
Example #4
Source File: io.py    From TF2 with Apache License 2.0 5 votes vote down vote up 
def array_to_blobproto(arr, diff=None):
    """Converts a N-dimensional array to blob proto. If diff is given, also
    convert the diff. You need to make sure that arr and diff have the same
    shape, and this function does not do sanity check.
    """
    blob = caffe_pb2.BlobProto()
    blob.shape.dim.extend(arr.shape)
    blob.data.extend(arr.astype(float).flat)
    if diff is not None:
        blob.diff.extend(diff.astype(float).flat)
    return blob
Example #5
Source File: pickle_caffe_blobs.py    From NucleiDetectron with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #6
Source File: pickle_caffe_blobs.py    From CBNet with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #7
Source File: pickle_caffe_blobs.py    From Detectron-DA-Faster-RCNN with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #8
Source File: pickle_caffe_blobs.py    From Detectron with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #9
Source File: io.py    From Deep-Learning-Based-Structural-Damage-Detection with MIT License 5 votes vote down vote up 
def array_to_blobproto(arr, diff=None):
    """Converts a N-dimensional array to blob proto. If diff is given, also
    convert the diff. You need to make sure that arr and diff have the same
    shape, and this function does not do sanity check.
    """
    blob = caffe_pb2.BlobProto()
    blob.shape.dim.extend(arr.shape)
    blob.data.extend(arr.astype(float).flat)
    if diff is not None:
        blob.diff.extend(diff.astype(float).flat)
    return blob
Example #10
Source File: pickle_caffe_blobs.py    From Detectron-Cascade-RCNN with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #11
Source File: pickle_caffe_blobs.py    From KL-Loss with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #12
Source File: io.py    From mix-and-match with MIT License 5 votes vote down vote up 
def array_to_blobproto(arr, diff=None):
    """Converts a 4-dimensional array to blob proto. If diff is given, also
    convert the diff. You need to make sure that arr and diff have the same
    shape, and this function does not do sanity check.
    """
    if arr.ndim != 4:
        raise ValueError('Incorrect array shape.')
    blob = caffe_pb2.BlobProto()
    blob.num, blob.channels, blob.height, blob.width = arr.shape
    blob.data.extend(arr.astype(float).flat)
    if diff is not None:
        blob.diff.extend(diff.astype(float).flat)
    return blob
Example #13
Source File: pickle_caffe_blobs.py    From seg_every_thing with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #14
Source File: pickle_caffe_blobs.py    From Clustered-Object-Detection-in-Aerial-Image with Apache License 2.0 5 votes vote down vote up 
def add_missing_biases(caffenet_weights):
    for layer in caffenet_weights.layer:
        if layer.type == 'Convolution' and len(layer.blobs) == 1:
            num_filters = layer.blobs[0].shape.dim[0]
            bias_blob = caffe_pb2.BlobProto()
            bias_blob.data.extend(np.zeros(num_filters))
            bias_blob.num, bias_blob.channels, bias_blob.height = 1, 1, 1
            bias_blob.width = num_filters
            layer.blobs.extend([bias_blob])
Example #15
Source File: example.py    From hocrux with Apache License 2.0 4 votes vote down vote up 
def get_transformer(deploy_file, mean_file=None):
    """
    Returns an instance of caffe.io.Transformer

    Arguments:
    deploy_file -- path to a .prototxt file

    Keyword arguments:
    mean_file -- path to a .binaryproto file (optional)
    """
    network = caffe_pb2.NetParameter()
    with open(deploy_file) as infile:
        text_format.Merge(infile.read(), network)

    dims = network.input_dim

    t = caffe.io.Transformer(
            inputs = {'data': dims}
            )
    t.set_transpose('data', (2,0,1)) # transpose to (channels, height, width)

    # color images
    if dims[1] == 3:
        # channel swap
        t.set_channel_swap('data', (2,1,0))

    if mean_file:
        # set mean pixel
        with open(mean_file) as infile:
            blob = caffe_pb2.BlobProto()
            blob.MergeFromString(infile.read())
            if blob.HasField('shape'):
                blob_dims = blob.shape
                assert len(blob_dims) == 4, 'Shape should have 4 dimensions - shape is "%s"' % blob.shape
            elif blob.HasField('num') and blob.HasField('channels') and \
                    blob.HasField('height') and blob.HasField('width'):
                blob_dims = (blob.num, blob.channels, blob.height, blob.width)
            else:
                raise ValueError('blob does not provide shape or 4d dimensions')
            pixel = np.reshape(blob.data, blob_dims[1:]).mean(1).mean(1)
            t.set_mean('data', pixel)

    return t
Example #16
Source File: rasterize_jon_scratch.py    From hocrux with Apache License 2.0 4 votes vote down vote up 
def get_transformer(deploy_file, mean_file=None):
    """
    Returns an instance of caffe.io.Transformer

    Arguments:
    deploy_file -- path to a .prototxt file

    Keyword arguments:
    mean_file -- path to a .binaryproto file (optional)
    """
    network = caffe_pb2.NetParameter()
    with open(deploy_file) as infile:
        text_format.Merge(infile.read(), network)

    dims = network.input_dim

    t = caffe.io.Transformer(
            inputs = {'data': dims}
            )
    t.set_transpose('data', (2,0,1)) # transpose to (channels, height, width)

    # color images
    if dims[1] == 3:
        # channel swap
        t.set_channel_swap('data', (2,1,0))

    if mean_file:
        # set mean pixel
        with open(mean_file) as infile:
            blob = caffe_pb2.BlobProto()
            blob.MergeFromString(infile.read())
            if blob.HasField('shape'):
                blob_dims = blob.shape
                assert len(blob_dims) == 4, 'Shape should have 4 dimensions - shape is "%s"' % blob.shape
            elif blob.HasField('num') and blob.HasField('channels') and \
                    blob.HasField('height') and blob.HasField('width'):
                blob_dims = (blob.num, blob.channels, blob.height, blob.width)
            else:
                raise ValueError('blob does not provide shape or 4d dimensions')
            pixel = np.reshape(blob.data, blob_dims[1:]).mean(1).mean(1)
            t.set_mean('data', pixel)

    return t
Example #17
Source File: example.py    From hocrux with Apache License 2.0 4 votes vote down vote up 
def get_transformer(deploy_file, mean_file=None):
    """
    Returns an instance of caffe.io.Transformer

    Arguments:
    deploy_file -- path to a .prototxt file

    Keyword arguments:
    mean_file -- path to a .binaryproto file (optional)
    """
    network = caffe_pb2.NetParameter()
    with open(deploy_file) as infile:
        text_format.Merge(infile.read(), network)

    dims = network.input_dim

    t = caffe.io.Transformer(
            inputs = {'data': dims}
            )
    t.set_transpose('data', (2,0,1)) # transpose to (channels, height, width)

    # color images
    if dims[1] == 3:
        # channel swap
        t.set_channel_swap('data', (2,1,0))

    if mean_file:
        # set mean pixel
        with open(mean_file) as infile:
            blob = caffe_pb2.BlobProto()
            blob.MergeFromString(infile.read())
            if blob.HasField('shape'):
                blob_dims = blob.shape
                assert len(blob_dims) == 4, 'Shape should have 4 dimensions - shape is "%s"' % blob.shape
            elif blob.HasField('num') and blob.HasField('channels') and \
                    blob.HasField('height') and blob.HasField('width'):
                blob_dims = (blob.num, blob.channels, blob.height, blob.width)
            else:
                raise ValueError('blob does not provide shape or 4d dimensions')
            pixel = np.reshape(blob.data, blob_dims[1:]).mean(1).mean(1)
            t.set_mean('data', pixel)

    return t
Example #18
Source File: rasterize.py    From hocrux with Apache License 2.0 4 votes vote down vote up 
def get_transformer(deploy_file, mean_file=None):
    """
    Returns an instance of caffe.io.Transformer

    Arguments:
    deploy_file -- path to a .prototxt file

    Keyword arguments:
    mean_file -- path to a .binaryproto file (optional)
    """
    network = caffe_pb2.NetParameter()
    with open(deploy_file) as infile:
        text_format.Merge(infile.read(), network)

    dims = network.input_dim

    t = caffe.io.Transformer(
            inputs = {'data': dims}
            )
    t.set_transpose('data', (2,0,1)) # transpose to (channels, height, width)

    # color images
    if dims[1] == 3:
        # channel swap
        t.set_channel_swap('data', (2,1,0))

    if mean_file:
        # set mean pixel
        with open(mean_file) as infile:
            blob = caffe_pb2.BlobProto()
            blob.MergeFromString(infile.read())
            if blob.HasField('shape'):
                blob_dims = blob.shape
                assert len(blob_dims) == 4, 'Shape should have 4 dimensions - shape is "%s"' % blob.shape
            elif blob.HasField('num') and blob.HasField('channels') and \
                    blob.HasField('height') and blob.HasField('width'):
                blob_dims = (blob.num, blob.channels, blob.height, blob.width)
            else:
                raise ValueError('blob does not provide shape or 4d dimensions')
            pixel = np.reshape(blob.data, blob_dims[1:]).mean(1).mean(1)
            t.set_mean('data', pixel)

    return t
Example #19
Source File: rasterize_jon_scratch.py    From hocrux with Apache License 2.0 4 votes vote down vote up 
def get_transformer(deploy_file, mean_file=None):
    """
    Returns an instance of caffe.io.Transformer

    Arguments:
    deploy_file -- path to a .prototxt file

    Keyword arguments:
    mean_file -- path to a .binaryproto file (optional)
    """
    network = caffe_pb2.NetParameter()
    with open(deploy_file) as infile:
        text_format.Merge(infile.read(), network)

    dims = network.input_dim

    t = caffe.io.Transformer(
            inputs = {'data': dims}
            )
    t.set_transpose('data', (2,0,1)) # transpose to (channels, height, width)

    # color images
    if dims[1] == 3:
        # channel swap
        t.set_channel_swap('data', (2,1,0))

    if mean_file:
        # set mean pixel
        with open(mean_file) as infile:
            blob = caffe_pb2.BlobProto()
            blob.MergeFromString(infile.read())
            if blob.HasField('shape'):
                blob_dims = blob.shape
                assert len(blob_dims) == 4, 'Shape should have 4 dimensions - shape is "%s"' % blob.shape
            elif blob.HasField('num') and blob.HasField('channels') and \
                    blob.HasField('height') and blob.HasField('width'):
                blob_dims = (blob.num, blob.channels, blob.height, blob.width)
            else:
                raise ValueError('blob does not provide shape or 4d dimensions')
            pixel = np.reshape(blob.data, blob_dims[1:]).mean(1).mean(1)
            t.set_mean('data', pixel)

    return t
Example #20
Source File: example.py    From hocrux with Apache License 2.0 4 votes vote down vote up 
def get_transformer(deploy_file, mean_file=None):
    """
    Returns an instance of caffe.io.Transformer

    Arguments:
    deploy_file -- path to a .prototxt file

    Keyword arguments:
    mean_file -- path to a .binaryproto file (optional)
    """
    network = caffe_pb2.NetParameter()
    with open(deploy_file) as infile:
        text_format.Merge(infile.read(), network)

    dims = network.input_dim

    t = caffe.io.Transformer(
            inputs = {'data': dims}
            )
    t.set_transpose('data', (2,0,1)) # transpose to (channels, height, width)

    # color images
    if dims[1] == 3:
        # channel swap
        t.set_channel_swap('data', (2,1,0))

    if mean_file:
        # set mean pixel
        with open(mean_file) as infile:
            blob = caffe_pb2.BlobProto()
            blob.MergeFromString(infile.read())
            if blob.HasField('shape'):
                blob_dims = blob.shape
                assert len(blob_dims) == 4, 'Shape should have 4 dimensions - shape is "%s"' % blob.shape
            elif blob.HasField('num') and blob.HasField('channels') and \
                    blob.HasField('height') and blob.HasField('width'):
                blob_dims = (blob.num, blob.channels, blob.height, blob.width)
            else:
                raise ValueError('blob does not provide shape or 4d dimensions')
            pixel = np.reshape(blob.data, blob_dims[1:]).mean(1).mean(1)
            t.set_mean('data', pixel)

    return t