使用训练好的tensorflow模型,转换成caffemodel的时候,需要对tensorflow中接口设置和caffe中接口设置都非常了解,才能对其参数进行对应设置,举个简单的例子:在我们使用slim库的时候,只需要按照如下方式进行书写:
net = slim.conv2d(inputs, 16, 3, stride=1, padding='VALID', scope='Conv1')
但是如果我们搭建prototxt的结构是按照下面搭建
cnn = caffe.layers.Convolution(inputs, num_output=16, kernel_size=3,
stride=1, pad=0, name='Conv1')
即使上述两段代码设置完全一样,我们经过inference之后就是得不到正确的结构,这是为什么呢?
我们打开tensorflow slim中的conv2d的函数定义:
def convolution2d(inputs,
num_outputs,
kernel_size,
stride=1,
padding='SAME',
data_format=None,
rate=1,
activation_fn=nn.relu, ###注意这行!!!
normalizer_fn=None,
normalizer_params=None,
weights_initializer=initializers.xavier_initializer(),
weights_regularizer=None,
biases_initializer=init_ops.zeros_initializer(),
biases_regularizer=None,
reuse=None,
variables_collections=None,
outputs_collections=None,
trainable=True,
scope=None):
我们再看下caffe对应conv2d的定义:
message ConvolutionParameter {
optional uint32 num_output = 1; // The number of outputs for the layer
optional bool bias_term = 2 [default = true]; // whether to have bias terms
// Pad, kernel size, and stride are all given as a single value for equal
// dimensions in all spatial dimensions, or once per spatial dimension.
repeated uint32 pad = 3; // The padding size; defaults to 0
repeated uint32 kernel_size = 4; // The kernel size
repeated uint32 stride = 6; // The stride; defaults to 1
// Factor used to dilate the kernel, (implicitly) zero-filling the resulting
// holes. (Kernel dilation is sometimes referred to by its use in the
// algorithme à trous from Holschneider et al. 1987.)
repeated uint32 dilation = 18; // The dilation; defaults to 1
// For 2D convolution only, the *_h and *_w versions may also be used to
// specify both spatial dimensions.
optional uint32 pad_h = 9 [default = 0]; // The padding height (2D only)
optional uint32 pad_w = 10 [default = 0]; // The padding width (2D only)
optional uint32 kernel_h = 11; // The kernel height (2D only)
optional uint32 kernel_w = 12; // The kernel width (2D only)
optional uint32 stride_h = 13; // The stride height (2D only)
optional uint32 stride_w = 14; // The stride width (2D only)
optional uint32 group = 5 [default = 1]; // The group size for group conv
optional FillerParameter weight_filler = 7; // The filler for the weight
optional FillerParameter bias_filler = 8; // The filler for the bias
enum Engine {
DEFAULT = 0;
CAFFE = 1;
CUDNN = 2;
}
optional Engine engine = 15 [default = DEFAULT];
// The axis to interpret as "channels" when performing convolution.
// Preceding dimensions are treated as independent inputs;
// succeeding dimensions are treated as "spatial".
// With (N, C, H, W) inputs, and axis == 1 (the default), we perform
// N independent 2D convolutions, sliding C-channel (or (C/g)-channels, for
// groups g>1) filters across the spatial axes (H, W) of the input.
// With (N, C, D, H, W) inputs, and axis == 1, we perform
// N independent 3D convolutions, sliding (C/g)-channels
// filters across the spatial axes (D, H, W) of the input.
optional int32 axis = 16 [default = 1];
// Whether to force use of the general ND convolution, even if a specific
// implementation for blobs of the appropriate number of spatial dimensions
// is available. (Currently, there is only a 2D-specific convolution
// implementation; for input blobs with num_axes != 2, this option is
// ignored and the ND implementation will be used.)
optional bool force_nd_im2col = 17 [default = false];
}
当然这个太详细了,我们可以发现slim中默认是卷积后进行relu激活的,在caffe中并没有这一个操作,一个经过relu激活,一个没有这个操作,你转换后的模型肯定不会和转换前一样得到正确的结果,所以要想将tensorflow模型正确的转成caffemodel,那就老老实实的了解每个接口后面的参数设置,并对应的写到你的caffe模型中。
慢工出细活,有些事儿吧,你急不来。。。