knsong

from itertools import product
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch import autograd
from torch.autograd.function import once_differentiable

class my_func(autograd.Function):
    @staticmethod
    def forward(ctx, x, scale=2.0):

knsong

'''ResNet in PyTorch.

For Pre-activation ResNet, see 'preact_resnet.py'.

Reference:
[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
    Deep Residual Learning for Image Recognition. arXiv:1512.03385
'''
import torch
import torch.nn as nn

knsong

'''ResNet in PyTorch.

For Pre-activation ResNet, see 'preact_resnet.py'.

Reference:
[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
    Deep Residual Learning for Image Recognition. arXiv:1512.03385
'''
import torch
import torch.nn as nn

knsong

import math
import os
import nvidia.dali.ops as ops
import nvidia.dali.types as types
import nvidia.dali.tfrecord as tfrec
from nvidia.dali.backend import oss
from nvidia.dali.pipeline import Pipeline
from nvidia.dali.plugin.pytorch import DALIGenericIterator, DALIClassificationIterator
from nvidia.dali.types import DALIDataType

knsong

Sample::Sample(){
    LOG(INFO) << "Initializing model";
    struct timeval begint, endt;
    gettimeofday(&begint, NULL);                     
    TF_Buffer* graph_def = read_file("./models.pb");                      
    tf_graph_ = TF_NewGraph();
    // Import graph_def into graph                                                          
    TF_Status* status = TF_NewStatus();                                                     
    TF_ImportGraphDefOptions* opts = TF_NewImportGraphDefOptions();                         
    TF_GraphImportGraphDef(tf_graph_, graph_def, opts, status);

knsong

name: "CaffeNet"

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

knsong

#include <algorithm>
#include <vector>

#include "caffe/layers/relu_layer.hpp"

namespace caffe {

template <typename Dtype>
__global__ void ReLUForward(const int n, const Dtype* in, Dtype* out,
    Dtype negative_slope, Dtype threshold) {

knsong

#include "caffe/layers/regression_accuracy_layer.hpp"

namespace caffe{
  template <typename Dtype>
  void RegressionAccuracyLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top){
    vector<int> top_shape(0);  // Accuracy is a scalar; 0 axes.
    top[0]->Reshape(top_shape);
  }
  template <typename Dtype>