NHZlX

name: "Flower463ResNet"

layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  data_param {
    source: "examples/flower463/flower463_train_lmdb"
    backend: LMDB

NHZlX

name: "ResNet-18"
layer {
    name: "data"
    type: "Data"
    top: "data"
    top: "label"
    include {
        phase: TRAIN
    }
    transform_param {

NHZlX

input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 224
  dim: 224
}
layer {
  bottom: "data"
  top: "conv1"

NHZlX

layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim:  dim:  dim:  dim:  } }
}

layer {
  name: "conv1"
  type: "Convolution"

NHZlX

#coding=utf-8
 
import os.path as osp
import sys
import copy
import os
from sys import path
import numpy as np
import google.protobuf as pb
 

NHZlX

input: "image"
input_dim: 1
input_dim: 3
input_dim: 540
input_dim: 960
layer {
  name: "conv1_1"
  type: "Convolution"
  bottom: "image"
  top: "conv1_1"

NHZlX

# edit-mode: -*- python -*-
import paddle.v2 as paddle


def conv_bn_layer(input, filter_size, num_filters,
                  stride, padding, channels=None, num_groups=1,
                  active_type=paddle.activation.Relu(),
                  layer_type=None):
    """
    A wrapper for conv layer with batch normalization layers.

NHZlX

name: "ENet"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 1
      dim: 3
      dim: 512

NHZlX

name: "MobileNet-SSD"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 300
  dim: 300
}
layer {
  name: "conv0"

NHZlX

name: "SIMPLIFIED_MOBILENET"
#  transform_param {
#    scale: 0.017
#    mirror: false
#    crop_size: 224
#    mean_value: [103.94,116.78,123.68]
#  }
input: "data"
input_shape { 
  dim: 1