random.seed(3141)
np.random.seed(59265)
weights = np.random.randn(dimVectors, 5)
print "Training for reg=%f" % regularization
# We will do batch optimization
weights = sgd(lambda weights: softmax_wrapper(trainFeatures, trainLabels,
weights, regularization),
weights,
3.0,
10000,
PRINT_EVERY=100)
# Test on train set
_, _, pred = softmaxRegression(trainFeatures, trainLabels, weights)
trainAccuracy = accuracy(trainLabels, pred)
print "Train accuracy (%%): %f" % trainAccuracy
# Test on dev set
_, _, pred = softmaxRegression(devFeatures, devLabels, weights)
devAccuracy = accuracy(devLabels, pred)
print "Dev accuracy (%%): %f" % devAccuracy
# Save the results and weights
results.append({
"reg": regularization,
"weights": weights,
"train": trainAccuracy,
"dev": devAccuracy
})
dimensions[1] + 1) * dimensions[2], )
tr_N = trainLabels.shape[0]
tr_labels = np.zeros((tr_N, dimensions[2]))
for i in xrange(tr_N):
tr_labels[i, trainLabels[i]] = 1
dv_N = devLabels.shape[0]
dv_labels = np.zeros((dv_N, dimensions[2]))
for i in xrange(dv_N):
dv_labels[i, devLabels[i]] = 1
weights = sgd(lambda weights: neural_wrapper(trainFeatures, tr_labels, weights, dimensions),
weights, 3.0, ITER, PRINT_EVERY=100)
_, _, pred = forward_backward_prop(trainFeatures, tr_labels, weights, dimensions)
trainAccuracy = accuracy(trainLabels, pred)
print "Train accuracy (%%): %f" % trainAccuracy
_, _, pred = forward_backward_prop(devFeatures, dv_labels, weights, dimensions)
devAccuracy = accuracy(devLabels, pred)
print "Dev accuracy (%%): %f" % devAccuracy
###########################################
# Save the results and weights
results.append({
"reg" : regularization,
"weights" : weights,
"train" : trainAccuracy,
"dev" : devAccuracy})
random.seed(3141)
np.random.seed(59265)
weights = np.random.randn(dimVectors, 5) # 0,1,2,3,4 总共５类
print("Training for reg=%f" % regularization)
# We will do batch optimization
# 使用sgd来训练参数，并不重新训练词向量
weights = sgd(lambda weights: softmax_wrapper(trainFeatures, trainLabels,
weights, regularization),
weights,
3.0,
10000,
PRINT_EVERY=100)
# Test on train set
_, _, pred = softmaxRegression(trainFeatures, trainLabels, weights)
trainAccuracy = accuracy(trainLabels, pred) # 13.7289325843
print("Train accuracy (%%): %f" % trainAccuracy)
# Test on dev set
_, _, pred = softmaxRegression(devFeatures, devLabels, weights)
devAccuracy = accuracy(devLabels, pred)
print("Dev accuracy (%%): %f" % devAccuracy)
# Save the results and weights
results.append({
"reg": regularization,
"weights": weights,
"train": trainAccuracy,
"dev": devAccuracy
})
# Try our regularization parameters
results = []
for regularization in REGULARIZATION:
random.seed(3141)
np.random.seed(59265)
weights = np.random.randn(dimVectors, 5)
print "Training for reg=%f" % regularization
# We will do batch optimization
weights = sgd(lambda weights: softmax_wrapper(trainFeatures, trainLabels,
weights, regularization), weights, 3.0, 10000, PRINT_EVERY=100)
# Test on train set
_, _, pred = softmaxRegression(trainFeatures, trainLabels, weights)
trainAccuracy = accuracy(trainLabels, pred)
print "Train accuracy (%%): %f" % trainAccuracy
# Test on dev set
_, _, pred = softmaxRegression(devFeatures, devLabels, weights)
devAccuracy = accuracy(devLabels, pred)
print "Dev accuracy (%%): %f" % devAccuracy
# Save the results and weights
results.append({
"reg" : regularization,
"weights" : weights,
"train" : trainAccuracy,
"dev" : devAccuracy})
# Print the accuracies
random.seed(3141)
np.random.seed(59265)
weights = np.random.randn(dimVectors, 5)
print "Training for reg=%f" % regularization
# We will do batch optimization
weights = sgd(lambda weights: softmax_wrapper(trainFeatures, trainLabels,
weights, regularization),
weights,
3.0,
10000,
PRINT_EVERY=100)
# Test on train set
_, _, pred = softmaxRegression(trainFeatures, trainLabels, weights)
trainAccuracy = accuracy(trainLabels, pred)
print "Training accuracy (%%): %f" % trainAccuracy
# Test on dev set
_, _, pred = softmaxRegression(devFeatures, devLabels, weights)
devAccuracy = accuracy(devLabels, pred)
print "The dev accuracy (%%): %f" % devAccuracy
# Save the results and weights
results.append({
"reg": regularization,
"weights": weights,
"train": trainAccuracy,
"dev": devAccuracy
})
