add a lenet example of specifying train/test net directly in solver;

multiple test nets

diff --git a/examples/mnist/lenet_consolidated_solver.prototxt b/examples/mnist/lenet_consolidated_solver.prototxt
new file mode 100644 (file)
index 0000000..14a048a
--- /dev/null
+++ b/examples/mnist/lenet_consolidated_solver.prototxt
@@ -0,0 +1,396 @@
+# lenet_consolidated_solver.prototxt consolidates the lenet_solver, lenet_train,
+# and lenet_test prototxts into a single file.  It also adds an additional test
+# net which runs on the training set, e.g., for the purpose of comparing
+# train/test accuracy (accuracy is computed only on the test set in the included
+# LeNet example.  This is mainly included as an example of using these features
+# (specify NetParameters directly in the solver, specify multiple test nets)
+# if desired.
+# 
+# test_iter specifies how many forward passes the test should carry out.
+# In the case of MNIST, we have test batch size 100 and 100 test iterations,
+# covering the full 10,000 testing images.
+test_iter: 100
+# Carry out testing every 500 training iterations.
+test_interval: 500
+# The base learning rate, momentum and the weight decay of the network.
+base_lr: 0.01
+momentum: 0.9
+weight_decay: 0.0005
+# The learning rate policy
+lr_policy: "inv"
+gamma: 0.0001
+power: 0.75
+# Display every 100 iterations
+display: 100
+# The maximum number of iterations
+max_iter: 10000
+# snapshot intermediate results
+snapshot: 5000
+snapshot_prefix: "lenet"
+# Set a random_seed for repeatable results.
+# (For results that vary due to random initialization, comment out the below
+# line, or set to a negative integer -- e.g. "random_seed: -1")
+random_seed: 1701
+# solver mode: CPU or GPU
+solver_mode: GPU
+# The training protocol buffer definition
+train_net_param {
+  name: "LeNet"
+  layers {
+    name: "mnist"
+    type: DATA
+    top: "data"
+    top: "label"
+    data_param {
+      source: "mnist-train-leveldb"
+      scale: 0.00390625
+      batch_size: 64
+    }
+  }
+  layers {
+    name: "conv1"
+    type: CONVOLUTION
+    bottom: "data"
+    top: "conv1"
+    blobs_lr: 1
+    blobs_lr: 2
+    convolution_param {
+      num_output: 20
+      kernel_size: 5
+      stride: 1
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "pool1"
+    type: POOLING
+    bottom: "conv1"
+    top: "pool1"
+    pooling_param {
+      pool: MAX
+      kernel_size: 2
+      stride: 2
+    }
+  }
+  layers {
+    name: "conv2"
+    type: CONVOLUTION
+    bottom: "pool1"
+    top: "conv2"
+    blobs_lr: 1
+    blobs_lr: 2
+    convolution_param {
+      num_output: 50
+      kernel_size: 5
+      stride: 1
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "pool2"
+    type: POOLING
+    bottom: "conv2"
+    top: "pool2"
+    pooling_param {
+      pool: MAX
+      kernel_size: 2
+      stride: 2
+    }
+  }
+  layers {
+    name: "ip1"
+    type: INNER_PRODUCT
+    bottom: "pool2"
+    top: "ip1"
+    blobs_lr: 1
+    blobs_lr: 2
+    inner_product_param {
+      num_output: 500
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "relu1"
+    type: RELU
+    bottom: "ip1"
+    top: "ip1"
+  }
+  layers {
+    name: "ip2"
+    type: INNER_PRODUCT
+    bottom: "ip1"
+    top: "ip2"
+    blobs_lr: 1
+    blobs_lr: 2
+    inner_product_param {
+      num_output: 10
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "loss"
+    type: SOFTMAX_LOSS
+    bottom: "ip2"
+    bottom: "label"
+  }
+}
+# The testing protocol buffer definition
+test_net_param {
+  name: "LeNet-test"
+  layers {
+    name: "mnist"
+    type: DATA
+    top: "data"
+    top: "label"
+    data_param {
+      source: "mnist-test-leveldb"
+      scale: 0.00390625
+      batch_size: 100
+    }
+  }
+  layers {
+    name: "conv1"
+    type: CONVOLUTION
+    bottom: "data"
+    top: "conv1"
+    convolution_param {
+      num_output: 20
+      kernel_size: 5
+      stride: 1
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "pool1"
+    type: POOLING
+    bottom: "conv1"
+    top: "pool1"
+    pooling_param {
+      pool: MAX
+      kernel_size: 2
+      stride: 2
+    }
+  }
+  layers {
+    name: "conv2"
+    type: CONVOLUTION
+    bottom: "pool1"
+    top: "conv2"
+    convolution_param {
+      num_output: 50
+      kernel_size: 5
+      stride: 1
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "pool2"
+    type: POOLING
+    bottom: "conv2"
+    top: "pool2"
+    pooling_param {
+      pool: MAX
+      kernel_size: 2
+      stride: 2
+    }
+  }
+  layers {
+    name: "ip1"
+    type: INNER_PRODUCT
+    bottom: "pool2"
+    top: "ip1"
+    inner_product_param {
+      num_output: 500
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "relu1"
+    type: RELU
+    bottom: "ip1"
+    top: "ip1"
+  }
+  layers {
+    name: "ip2"
+    type: INNER_PRODUCT
+    bottom: "ip1"
+    top: "ip2"
+    inner_product_param {
+      num_output: 10
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "prob"
+    type: SOFTMAX
+    bottom: "ip2"
+    top: "prob"
+  }
+  layers {
+    name: "accuracy"
+    type: ACCURACY
+    bottom: "prob"
+    bottom: "label"
+    top: "accuracy"
+  }
+}
+# The protocol buffer definition to test on the train set
+test_net_param {
+  name: "LeNet-test-on-train"
+  layers {
+    name: "mnist"
+    type: DATA
+    top: "data"
+    top: "label"
+    data_param {
+      source: "mnist-train-leveldb"
+      scale: 0.00390625
+      batch_size: 100
+    }
+  }
+  layers {
+    name: "conv1"
+    type: CONVOLUTION
+    bottom: "data"
+    top: "conv1"
+    convolution_param {
+      num_output: 20
+      kernel_size: 5
+      stride: 1
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "pool1"
+    type: POOLING
+    bottom: "conv1"
+    top: "pool1"
+    pooling_param {
+      pool: MAX
+      kernel_size: 2
+      stride: 2
+    }
+  }
+  layers {
+    name: "conv2"
+    type: CONVOLUTION
+    bottom: "pool1"
+    top: "conv2"
+    convolution_param {
+      num_output: 50
+      kernel_size: 5
+      stride: 1
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "pool2"
+    type: POOLING
+    bottom: "conv2"
+    top: "pool2"
+    pooling_param {
+      pool: MAX
+      kernel_size: 2
+      stride: 2
+    }
+  }
+  layers {
+    name: "ip1"
+    type: INNER_PRODUCT
+    bottom: "pool2"
+    top: "ip1"
+    inner_product_param {
+      num_output: 500
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "relu1"
+    type: RELU
+    bottom: "ip1"
+    top: "ip1"
+  }
+  layers {
+    name: "ip2"
+    type: INNER_PRODUCT
+    bottom: "ip1"
+    top: "ip2"
+    inner_product_param {
+      num_output: 10
+      weight_filler {
+        type: "xavier"
+      }
+      bias_filler {
+        type: "constant"
+      }
+    }
+  }
+  layers {
+    name: "prob"
+    type: SOFTMAX
+    bottom: "ip2"
+    top: "prob"
+  }
+  layers {
+    name: "accuracy"
+    type: ACCURACY
+    bottom: "prob"
+    bottom: "label"
+    top: "accuracy"
+  }
+}