I tried to use the same code with some modification here for digit recognitions using a trained model for mnist based on Caffe. My modified source code and network is as follows. I also included the error message at the end. The image is used in the code is a sample image from mnist. The line of code that it cannot go through is
net.forward();
And I'm pretty sure it is because of the dimension of input.
Any ideas how to run the code for LeNet?
caffe_mnist.cpp
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <time.h>
#include <math.h>
using namespace cv;
using namespace cv::dnn;
#include <fstream>
#include <iostream>
#include <cstdlib>
using namespace std;
clock_t t;
/* Find best class for the blob (i. e. class with maximal probability) */
void getMaxClass(dnn::Blob &probBlob, int *classId, double *classProb)
{
Mat probMat = probBlob.matRefConst().reshape(1, 1); //reshape the blob to 1x1000 matrix
Point classNumber;
minMaxLoc(probMat, NULL, classProb, NULL, &classNumber);
*classId = classNumber.x;
}
std::vector<String> readClassNames(const char *filename = "./caffe_model/mnist/label.txt")
{
std::vector<String> classNames;
std::ifstream fp(filename);
if (!fp.is_open())
{
std::cerr << "File with classes labels not found: " << filename << std::endl;
exit(-1);
}
std::string name;
while (!fp.eof())
{
std::getline(fp, name);
if (name.length())
classNames.push_back( name.substr(name.find(' ')+1) );
}
fp.close();
return classNames;
}
int main(int argc, char **argv)
{
String modelTxt = "./caffe_model/mnist/mnist.prototxt";
String modelBin = "./caffe_model/mnist/mnist.caffemodel";
String imageFile = (argc > 1) ? argv[1] : "./caffe_model/mnist/0.png";
Ptr<dnn::Importer> importer;
try //Try to import Caffe GoogleNet model
{
importer = dnn::createCaffeImporter(modelTxt, modelBin);
}
catch (const cv::Exception &err) //Importer can throw errors, we will catch them
{
std::cerr << err.msg << std::endl;
}
if (!importer)
{
std::cerr << "Can't load network by using the following files: " << std::endl;
std::cerr << "prototxt: " << modelTxt << std::endl;
std::cerr << "caffemodel: " << modelBin << std::endl;
exit(-1);
}
dnn::Net net;
importer->populateNet(net);
std::cout << "done: importer->populateNet(net) " << std::endl;
importer.release(); //We don't need importer anymore
Mat img = imread(imageFile);
if (img.empty())
{
std::cerr << "Can't read image from the file: " << imageFile << std::endl;
exit(-1);
}
resize(img, img, Size(28, 28)); //LeNet accepts 224x224 RGB-images
std::cout << "done: resize(img, img, Size(28, 28)); " << std::endl;
dnn::Blob inputBlob = dnn::Blob(img); //Convert Mat to dnn::Blob image batch
net.setBlob(".data", inputBlob); //set the network input
std::cout << "done: net.setBlob(.data, inputBlob); " << std::endl;
t = clock();
net.forward();
std::cout << "done: net.forward(); " << std::endl;
//compute output
dnn::Blob prob = net.getBlob("prob"); //gather output of "prob" layer
int classId;
double classProb;
getMaxClass(prob, &classId, &classProb);//find the best class
std::vector<String> classNames = readClassNames();
std::cout << "Best class: #" << classId << " '" << classNames.at(classId) << "'" << std::endl;
std::cout << "Probability: " << classProb * 100 << "%" << std::endl;
t = clock() - t;
std::cout << "Time Spent: " << ((float)t)/CLOCKS_PER_SEC << std::endl;
return 0;
} //main
mnist.prototxt
name: "LeNet"
input: "data"
input_dim: 1
input_dim: 1
input_dim: 28
input_dim: 28
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 20
kernel_size: 5
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
}
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 50
kernel_size: 5
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
}
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "ip1"
type: "InnerProduct"
bottom: "pool2"
top: "ip1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 500
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "ip1"
top: "ip1"
}
layer {
name: "ip2"
type: "InnerProduct"
bottom: "ip1"
top: "ip2"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 10
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
}
}
}
layer {
name: "prob"
type: "Softmax"
bottom: "ip2"
top: "prob"
}
Error:
done: importer->populateNet(net)
done: resize(img, img, Size(28, 28));
done: net.setBlob(.data, inputBlob);
OpenCV Error: Assertion failed (blobs[0].num() == outCn && blobs[0].channels() == inpCn / group) in allocate, file /home/ubuntu/opencv_contrib/modules/dnn/src/layers/convolution_layer.cpp, line 87
terminate called after throwing an instance of 'cv::Exception'
what(): /home/ubuntu/opencv_contrib/modules/dnn/src/layers/convolution_layer.cpp:87: error: (-215) blobs[0].num() == outCn && blobs[0].channels() == inpCn / group in function allocate
Aborted (core dumped)