Mxnet/Training and Inference

Linear Regression

원문
전체 소스

import mxnet as mx
import numpy as np

#Training data
train_data = np.random.uniform(0, 1, [100, 2])
train_label = np.array([train_data[i][0] + 2 * train_data[i][1] for i in range(100)])
batch_size = 1

#Evaluation Data
eval_data = np.array([[7,2],[6,10],[12,2]])
eval_label = np.array([11,26,16])

train_iter = mx.io.NDArrayIter(train_data,train_label, batch_size, shuffle=True,label_name='lin_reg_label')           #(1)
eval_iter = mx.io.NDArrayIter(eval_data, eval_label, batch_size, shuffle=False)

X = mx.sym.Variable('data')
Y = mx.symbol.Variable('lin_reg_label')         #(2)
fully_connected_layer  = mx.sym.FullyConnected(data=X, name='fc1', num_hidden = 1)
lro = mx.sym.LinearRegressionOutput(data=fully_connected_layer, label=Y, name="lro")             #(3)

model = mx.mod.Module(
    symbol = lro ,
    data_names=['data'],
    label_names = ['lin_reg_label']# network structure      (4)
)

mx.viz.plot_network(symbol=lro)
# (5)
model.fit(train_iter, eval_iter,
            optimizer_params={'learning_rate':0.005, 'momentum': 0.9},
            num_epoch=1000,
            batch_end_callback = mx.callback.Speedometer(batch_size, 2))

model.predict(eval_iter).asnumpy()

metric = mx.metric.MSE()
model.score(eval_iter, metric)

eval_data = np.array([[7,2],[6,10],[12,2]])
eval_label = np.array([11.1,26.1,16.1]) #Adding 0.1 to each of the values
eval_iter = mx.io.NDArrayIter(eval_data, eval_label, batch_size, shuffle=False)
model.score(eval_iter, metric)

(3) mx.sym.LinearRegressionOutput은 l2 loss계산함.
(1),(2)에서 lin_reg_label이라고 준 것과 NDArrayIter에서 이름이 일치해야 한다. train_iter = mx.io.NDArrayIter(..., label_name='lin_reg_label' ) 다시말해, 입력단의 이름이 일치해야 한다는 얘기. 결국 (4)에 나오는 이름까지 일치해야 해서 같은 이름이 세번 나온다

(5)의 model.fit에서 batch_end_callback으로 mx.callback.Speedometer줄 수 있다.

• Speedometer(batch_size, frequent=50, auto_reset=True) : 배치 50번마다 로깅하고, 로깅 후 reset할것. 아래를 미리 해줘야 stdout에 보인다.

import logging
logging.getLogger().setLevel(logging.DEBUG)

실행해보면,

>>> # Print training speed and evaluation metrics every ten batches. Batch size is one.
>>> module.fit(iterator, num_epoch=n_epoch,
... batch_end_callback=mx.callback.Speedometer(1, 10))
Epoch[0] Batch [10] Speed: 1910.41 samples/sec  Train-accuracy=0.200000
Epoch[0] Batch [20] Speed: 1764.83 samples/sec  Train-accuracy=0.400000
Epoch[0] Batch [30] Speed: 1740.59 samples/sec  Train-accuracy=0.500000

Handwritten Digit Recognition

원문

full src

import mxnet as mx
mnist = mx.test_utils.get_mnist()

batch_size = 100
train_iter = mx.io.NDArrayIter(mnist['train_data'], mnist['train_label'], batch_size, shuffle=True)
val_iter = mx.io.NDArrayIter(mnist['test_data'], mnist['test_label'], batch_size)

data = mx.sym.var('data')
# Flatten the data from 4-D shape into 2-D (batch_size, num_channel*width*height)
data = mx.sym.flatten(data=data)

# The first fully-connected layer and the corresponding activation function
fc1  = mx.sym.FullyConnected(data=data, num_hidden=128)
act1 = mx.sym.Activation(data=fc1, act_type="relu")

# The second fully-connected layer and the corresponding activation function
fc2  = mx.sym.FullyConnected(data=act1, num_hidden = 64)
act2 = mx.sym.Activation(data=fc2, act_type="relu")

# MNIST has 10 classes
fc3  = mx.sym.FullyConnected(data=act2, num_hidden=10)
# Softmax with cross entropy loss
mlp  = mx.sym.SoftmaxOutput(data=fc3, name='softmax')

import logging
logging.getLogger().setLevel(logging.DEBUG)  # logging to stdout
# create a trainable module on CPU
mlp_model = mx.mod.Module(symbol=mlp, context=mx.cpu())
mlp_model.fit(train_iter,  # train data
              eval_data=val_iter,  # validation data
              optimizer='sgd',  # use SGD to train
              optimizer_params={'learning_rate':0.1},  # use fixed learning rate
              eval_metric='acc',  # report accuracy during training
              batch_end_callback = mx.callback.Speedometer(batch_size, 100), # output progress for each 100 data batches
              num_epoch=10)  # train for at most 10 dataset passes

test_iter = mx.io.NDArrayIter(mnist['test_data'], None, batch_size)
prob = mlp_model.predict(test_iter)
assert prob.shape == (10000, 10)

test_iter = mx.io.NDArrayIter(mnist['test_data'], mnist['test_label'], batch_size)
# predict accuracy of mlp
acc = mx.metric.Accuracy()
mlp_model.score(test_iter, acc)
print(acc)
assert acc.get()[1] > 0.96

data = mx.sym.var('data')
# first conv layer
conv1 = mx.sym.Convolution(data=data, kernel=(5,5), num_filter=20)
tanh1 = mx.sym.Activation(data=conv1, act_type="tanh")
pool1 = mx.sym.Pooling(data=tanh1, pool_type="max", kernel=(2,2), stride=(2,2))
# second conv layer
conv2 = mx.sym.Convolution(data=pool1, kernel=(5,5), num_filter=50)
tanh2 = mx.sym.Activation(data=conv2, act_type="tanh")
pool2 = mx.sym.Pooling(data=tanh2, pool_type="max", kernel=(2,2), stride=(2,2))
# first fullc layer
flatten = mx.sym.flatten(data=pool2)
fc1 = mx.symbol.FullyConnected(data=flatten, num_hidden=500)
tanh3 = mx.sym.Activation(data=fc1, act_type="tanh")
# second fullc
fc2 = mx.sym.FullyConnected(data=tanh3, num_hidden=10)
# softmax loss
lenet = mx.sym.SoftmaxOutput(data=fc2, name='softmax')

# create a trainable module on GPU 0
lenet_model = mx.mod.Module(symbol=lenet, context=mx.cpu())
# train with the same
lenet_model.fit(train_iter,
                eval_data=val_iter,
                optimizer='sgd',
                optimizer_params={'learning_rate':0.1},
                eval_metric='acc',
                batch_end_callback = mx.callback.Speedometer(batch_size, 100),
                num_epoch=10)

test_iter = mx.io.NDArrayIter(mnist['test_data'], None, batch_size)
prob = lenet_model.predict(test_iter)
test_iter = mx.io.NDArrayIter(mnist['test_data'], mnist['test_label'], batch_size)
# predict accuracy for lenet
acc = mx.metric.Accuracy()
lenet_model.score(test_iter, acc)
print(acc)
assert acc.get()[1] > 0.98

Loading data

mx.test_utils.get_mnist()

이 뒤로는 trivial.