我需要使用DeepLearning4j实现现有的Caffe模型。不过,我是DL4J的新手,所以不知道如何实施。通过搜索文档和示例搜索没有多大帮助,这两者的术语非常不同。 你会如何在dl4j中编写下面的caffe原型文件?将Caffe配置转换为DeepLearning4J配置
Layer1的:
layers {
name: "myLayer1"
type: CONVOLUTION
bottom: "data"
top: "myLayer1"
blobs_lr: 1
blobs_lr: 2
convolution_param {
num_output: 20
kernel_w: 2
kernel_h: 2
stride_w: 1
stride_h: 1
weight_filler {
type: "msra"
variance_norm: AVERAGE
}
bias_filler {
type: "constant"
}
}
}
二层
layers {
name: "myLayer1Relu"
type: RELU
relu_param {
negative_slope: 0.3
}
bottom: "myLayer1"
top: "myLayer1"
}
三层
layers {
name: "myLayer1_dropout"
type: DROPOUT
bottom: "myLayer1"
top: "myLayer1"
dropout_param {
dropout_ratio: 0.2
}
}
层4
layers {
name: "final_class"
type: INNER_PRODUCT
bottom: "myLayer4"
top: "final_class"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 10
weight_filler {
type: "xavier"
variance_norm: AVERAGE
}
bias_filler {
type: "constant"
value: 0
}
}
}
太好了,谢谢。这是一个很好的先发。 –