mnist updates

3 files changed, 140 insertions, 32 deletions

diff --git a/examples/convert_mnist_data.cpp b/examples/convert_mnist_data.cpp
new file mode 100644
index 00000000..32d9b9d9
--- /dev/null
+++ b/examples/convert_mnist_data.cpp
@@ -0,0 +1,106 @@
+// Copyright Yangqing Jia 2013
+//
+// This script converts the MNIST dataset to the leveldb format used
+// by caffe to perform classification.
+// Usage:
+//    convert_mnist_data input_image_file input_label_file output_db_file
+// The MNIST dataset could be downloaded at
+//    http://yann.lecun.com/exdb/mnist/
+
+#include <google/protobuf/text_format.h>
+#include <glog/logging.h>
+#include <leveldb/db.h>
+
+#include <stdint.h>
+#include <iostream>
+#include <fstream>
+
+#include "caffe/proto/caffe.pb.h"
+
+uint32_t swap_endian( uint32_t val )
+{
+    val = ((val << 8) & 0xFF00FF00 ) | ((val >> 8) & 0xFF00FF );
+    return (val << 16) | (val >> 16);
+}
+
+void convert_dataset(const char* image_filename, const char* label_filename,
+        const char* db_filename) {
+  // Open files
+  std::ifstream image_file(image_filename, std::ios::in | std::ios::binary);
+  std::ifstream label_file(label_filename, std::ios::in | std::ios::binary);
+  CHECK(image_file) << "Unable to open file " << image_filename;
+  CHECK(label_file) << "Unable to open file " << label_file;
+  // Read the magic and the meta data
+  uint32_t magic;
+  uint32_t num_items;
+  uint32_t num_labels;
+  uint32_t rows;
+  uint32_t cols;
+
+  image_file.read((char*)(&magic), 4);
+  magic = swap_endian(magic);
+  CHECK_EQ(magic, 2051) << "Incorrect image file magic.";
+  label_file.read((char*)(&magic), 4);
+  magic = swap_endian(magic);
+  CHECK_EQ(magic, 2049) << "Incorrect label file magic.";
+  image_file.read((char*)(&num_items), 4);
+  num_items = swap_endian(num_items);
+  label_file.read((char*)(&num_labels), 4);
+  num_labels = swap_endian(num_labels);
+  CHECK_EQ(num_items, num_labels);
+  image_file.read((char*)(&rows), 4);
+  rows = swap_endian(rows);
+  image_file.read((char*)(&cols), 4);
+  cols = swap_endian(cols);
+
+  // Open leveldb
+  leveldb::DB* db;
+  leveldb::Options options;
+  options.create_if_missing = true;
+  options.error_if_exists = true;
+  leveldb::Status status = leveldb::DB::Open(
+      options, db_filename, &db);
+  CHECK(status.ok()) << "Failed to open leveldb " << db_filename
+      << ". Is it already existing?";
+
+  char label;
+  char* pixels = new char[rows * cols];
+  char key[10];
+  std::string value;
+
+  caffe::Datum datum;
+  datum.set_channels(1);
+  datum.set_height(rows);
+  datum.set_width(cols);
+  LOG(INFO) << "A total of " << num_items << " items.";
+  LOG(INFO) << "Rows: " << rows << " Cols: " << cols;
+  for (int itemid = 0; itemid < num_items; ++itemid) {
+    image_file.read(pixels, rows * cols);
+    label_file.read(&label, 1);
+    datum.set_data(pixels, rows*cols);
+    datum.set_label(label);
+    datum.SerializeToString(&value);
+    sprintf(key, "%08d", itemid);
+    db->Put(leveldb::WriteOptions(), std::string(key), value);
+  }
+
+  delete db;
+  delete pixels;
+}
+
+int main (int argc, char** argv) {
+  if (argc != 4) {
+    printf("This script converts the MNIST dataset to the leveldb format used\n"
+           "by caffe to perform classification.\n"
+           "Usage:\n"
+           "    convert_mnist_data input_image_file input_label_file "
+           "output_db_file\n"
+           "The MNIST dataset could be downloaded at\n"
+           "    http://yann.lecun.com/exdb/mnist/\n"
+           "You should gunzip them after downloading.\n");
+  } else {
+    google::InitGoogleLogging(argv[0]);
+    convert_dataset(argv[1], argv[2], argv[3]);
+  }
+  return 0;
+}
diff --git a/examples/demo_mnist.cpp b/examples/demo_mnist.cpp
index c513a6aa..22c85c6f 100644
--- a/examples/demo_mnist.cpp
+++ b/examples/demo_mnist.cpp
@@ -1,10 +1,12 @@
 // Copyright 2013 Yangqing Jia
+// This example shows how to run a modified version of LeNet using Caffe.
 
 #include <cuda_runtime.h>
 #include <fcntl.h>
 #include <google/protobuf/text_format.h>
 
 #include <cstring>
+#include <iostream>
 
 #include "caffe/blob.hpp"
 #include "caffe/common.hpp"
@@ -17,12 +19,26 @@
 using namespace caffe;
 
 int main(int argc, char** argv) {
-  cudaSetDevice(1);
-  Caffe::set_mode(Caffe::GPU);
+  if (argc < 3) {
+    std::cout << "Usage:" << std::endl;
+    std::cout << "demo_mnist.bin train_file test_file [CPU/GPU]" << std::endl;
+    return 0;
+  }
+  google::InitGoogleLogging(argv[0]);
+
+  if (argc == 4) {
+    if (strcmp(argv[3], "GPU") == 0) {
+      Caffe::set_mode(Caffe::GPU);
+    } else {
+      Caffe::set_mode(Caffe::CPU);
+    }
+  }
+
+  // Start training
   Caffe::set_phase(Caffe::TRAIN);
 
   NetParameter net_param;
-  ReadProtoFromTextFile("data/lenet.prototxt",
+  ReadProtoFromTextFile(argv[1],
       &net_param);
   vector<Blob<float>*> bottom_vec;
   Net<float> caffe_net(net_param, bottom_vec);
@@ -34,9 +50,11 @@ int main(int argc, char** argv) {
   LOG(ERROR) << "Initial loss: " << caffe_net.Backward();
 
   SolverParameter solver_param;
+  // Solver Parameters are hard-coded in this case, but you can write a
+  // SolverParameter protocol buffer to specify all these values.
   solver_param.set_base_lr(0.01);
   solver_param.set_display(100);
-  solver_param.set_max_iter(6000);
+  solver_param.set_max_iter(5000);
   solver_param.set_lr_policy("inv");
   solver_param.set_gamma(0.0001);
   solver_param.set_power(0.75);
@@ -48,43 +66,23 @@ int main(int argc, char** argv) {
   solver.Solve(&caffe_net);
   LOG(ERROR) << "Optimization Done.";
 
-  // Run the network after training.
-  LOG(ERROR) << "Performing Forward";
-  caffe_net.Forward(bottom_vec);
-  LOG(ERROR) << "Performing Backward";
-  float loss = caffe_net.Backward();
-  LOG(ERROR) << "Final loss: " << loss;
-
+  // Write the trained network to a NetParameter protobuf. If you are training
+  // the model and saving it for later, this is what you want to serialize and
+  // store.
   NetParameter trained_net_param;
   caffe_net.ToProto(&trained_net_param);
 
-  NetParameter traintest_net_param;
-  ReadProtoFromTextFile("data/lenet_traintest.prototxt",
-      &traintest_net_param);
-  Net<float> caffe_traintest_net(traintest_net_param, bottom_vec);
-  caffe_traintest_net.CopyTrainedLayersFrom(trained_net_param);
-
+  // Now, let's starting doing testing.
   Caffe::set_phase(Caffe::TEST);
 
-  // Test run
-  double train_accuracy = 0;
-  int batch_size = traintest_net_param.layers(0).layer().batchsize();
-  for (int i = 0; i < 60000 / batch_size; ++i) {
-    const vector<Blob<float>*>& result =
-        caffe_traintest_net.Forward(bottom_vec);
-    train_accuracy += result[0]->cpu_data()[0];
-  }
-  train_accuracy /= 60000 / batch_size;
-  LOG(ERROR) << "Train accuracy:" << train_accuracy;
-
+  // Using the testing data to test the accuracy.
   NetParameter test_net_param;
-  ReadProtoFromTextFile("data/lenet_test.prototxt", &test_net_param);
+  ReadProtoFromTextFile(argv[2], &test_net_param);
   Net<float> caffe_test_net(test_net_param, bottom_vec);
   caffe_test_net.CopyTrainedLayersFrom(trained_net_param);
 
-  // Test run
   double test_accuracy = 0;
-  batch_size = test_net_param.layers(0).layer().batchsize();
+  int batch_size = test_net_param.layers(0).layer().batchsize();
   for (int i = 0; i < 10000 / batch_size; ++i) {
     const vector<Blob<float>*>& result =
         caffe_test_net.Forward(bottom_vec);
diff --git a/src/caffe/pyutil/convert.py b/src/caffe/pyutil/convert.py
index 483e4ea7..7db31645 100644
--- a/src/caffe/pyutil/convert.py
+++ b/src/caffe/pyutil/convert.py
@@ -4,6 +4,7 @@
 from caffe.proto import caffe_pb2
 import numpy as np
 
+
 def blobproto_to_array(blob, return_diff=False):
   """Convert a blob proto to an array. In default, we will just return the data,
   unless return_diff is True, in which case we will return the diff.
@@ -15,6 +16,7 @@ def blobproto_to_array(blob, return_diff=False):
     return np.array(blob.data).reshape(
         blob.num, blob.channels, blob.height, blob.width)
 
+
 def array_to_blobproto(arr, diff=None):
   """Converts a 4-dimensional array to blob proto. If diff is given, also
   convert the diff. You need to make sure that arr and diff have the same
@@ -29,6 +31,7 @@ def array_to_blobproto(arr, diff=None):
     blob.diff.extend(diff.astype(float).flat)
   return blob
 
+
 def array_to_datum(arr, label=0):
   """Converts a 3-dimensional array to datum. If the array has dtype uint8,
   the output data will be encoded as a string. Otherwise, the output data
@@ -45,6 +48,7 @@ def array_to_datum(arr, label=0):
   datum.label = label
   return datum
 
+
 def datum_to_array(datum):
   """Converts a datum to an array. Note that the label is not returned,
   as one can easily get it by calling datum.label.
@@ -54,4 +58,4 @@ def datum_to_array(datum):
         datum.channels, datum.height, datum.width)
   else:
     return np.array(datum.float_data).astype(float).reshape(
-        datum.channels, datum.height, datum.width)
\ No newline at end of file
+        datum.channels, datum.height, datum.width)