我试图从一个非常简单的CAffe模型中获取权重,并将其解释为全功能的Keras模型。

这是caffe中模型的原始定义,我们称之为 simple.prototxt :

input: "im_data"
input_shape {
  dim: 1
  dim: 3
  dim: 1280
  dim: 1280
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "im_data"
  top: "conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 11
    pad: 5
    stride: 4
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    pad: 0
    stride: 2
  }
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  top: "conv2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 5
    pad: 2
    group: 2
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}

caffe中的层定义可能看起来很复杂,但它只是一个维度的图像。 1280x1280x3 将其传递到卷积层,然后max将其聚集并传递到最终的卷积层。

这是它在 克拉斯 更简单的是:

from keras.models import Model
from keras.layers import Input, BatchNormalization, 
from keras.activations import relu, softmax

im_data = Input(shape=(1280, 1280, 3),
                   dtype='float32',
                   name='im_data')
conv1 = Conv2D(filters=96,
               kernel_size=11,
               strides=(4, 4),
               activation=relu,
               padding='same',
               name='conv1')(im_data)

pooling1 = MaxPooling2D(pool_size=(3, 3),
                        strides=(2, 2),
                        padding='same',
                        name='pooling1')(conv1)
normalized1 = BatchNormalization()(pooling1)  # https://stats.stackexchange.com/questions/145768/importance-of-local-response-normalization-in-cnn

conv2 = Conv2D(filters=256,
               kernel_size=5,
               activation=relu,
               padding='same',
               name='conv2')(normalized1)
model = Model(inputs=[im_data], outputs=conv2)  

问题:

尽管两个模型在每一层中似乎都有相似的参数,但问题是 它们的重量形状不相等 . 我知道CAFFE的形状顺序与KERAS不同,但这里不关心订购问题。

问题是,与CAFFE中的最后一个卷积层相比,KERS中的最后一个卷积层在三维上具有不同的值。见下文。

重量形状 卡费 :

>>> net = caffe.net('simple.prototxt', 'premade_weights.caffemodel', caffe.TEST)
>>> for i in range(len(net.layers)):
...     if len(net.layers[i].blobs) != 0:  # if layer has no weights
...         print(("name", net._layer_names[i]))
...         print("weight_shapes", [v.data.shape for v in net.layers[i].blobs])
('name', 'conv1')
('weight_shapes', [(96, 3, 11, 11), (96,)])
('name', 'conv2')
('weight_shapes', [(256, 48, 5, 5), (256,)])

重量形状 克拉斯 :

>>> for layer in model.layers:
...     if len(layer.get_weights()) != 0:
...         print(("name", layer.name))
...         print(("weight_shapes", [w.shape for w in layer.get_weights()]))  
('name', 'conv1')
('weight_shapes', [(11, 11, 3, 96), (96,)])
('name', 'conv2')
('weight_shapes', [(5, 5, 96, 256), (256,)])

这似乎是一种奇怪的行为。如你所见, conv1 caffe和keras的形状相等(忽略顺序)。但在Caffe conv2 形状是 [(256, 48, 5, 5), (256,)]) 而在角膜“conv2”形状是 [(5, 5, 96, 256), (256,)] , 通知 ,那 48*2=96 .

也, 通知 那个 二维卷积 层直接位于最大池层之后,因此KERS中的最大池层可能有问题。

问题:

我是否正确地解释了从CAffe到Keras的模型定义?尤其是最大池层及其参数?

非常感谢你!