def main():
train_set, test_set = getDataSets()
params = [[0.0001] * 3073] * 10
loss = np.array([])
for i in range(100):
print("epoch: {}".format(i + 1))
params, l = smModule.train(train_set, params, 100, 10, 10**(-9))
loss = np.append(loss, l)
loss = loss.flatten()
# print(loss)
# print(params)
score = smModule.score(test_set[0], test_set[1], params)
print("accuracy: {}".format(score))
plt.plot(loss)
plt.show()
def main():
train_set, test_set = getDataSets()
num_class = 10
params = [[0] * 785] * num_class
loss = np.array([])
for i in range(100):
print("epoch: {}".format(i + 1))
params, l = smModule.train(train_set, params, 1, num_class, 0.01)
loss = np.append(loss, l)
loss = loss.flatten()
score = smModule.score(test_set[0], test_set[1], params)
print("accuracy: {}".format(score))
plt.plot(loss)
plt.show()
def main():
fnameTrainIm = sys.argv[1]
fnameTrainLb = sys.argv[2]
fnameTestIm = sys.argv[3]
fnameTestLb = sys.argv[4]
# read training data and labels
trainData, trainLabel = read(fnameTrainIm, fnameTrainLb)
# initialize constants and parameters
inputSize = 28 * 28
numClasses = 10
lam = 1e-4
DEBUG = 0
if DEBUG == 1:
# compute difference between numerical gradient and computed grad on the subset
subData, subLabel, subTheta, subPatchsize = subsample(
trainData, trainLabel, rows, numClasses)
subCost, subGrad = softmax.softmaxCost(subTheta, numClasses,
subPatchsize, lam, subData,
subLabel)
numGrad, diff = numericalgrad(subTheta, numClasses, subPatchsize, lam,
subData, subLabel, subGrad)
print "The diff is", diff
# train regression code
thetaOpt = softmax.train(numClasses, inputSize, lam, trainData, trainLabel)
# predict labels for test data
testData, testLabel = read(fnameTestIm, fnameTestLb)
pred = softmax.predict(thetaOpt, testData, numClasses, inputSize)
# report accuracy of softmax regression
accuracy = 100 * np.sum(testLabel == pred) / len(testLabel)
print "Accuracy is {0:.2f}".format(accuracy)
jac=True,
options={'maxiter': 400})
sae2_opt_theta = result.x
print result
##======================================================================
'''
STEP 4: Train the softmax classifier
'''
# use features from the second hidden layer to train the softmax classifier
sae2_features = sparseAuto.autoencoder(sae2_opt_theta, hidden_size_L2,
hidden_size_L1, sae1_features)
# optimize parameters
softmax_theta = softmax.train(num_classes, hidden_size_L2, lambda_,
sae2_features, train_labels)
##======================================================================
'''
STEP 5: Finetune softmax model
'''
# Initialize the stack using the parameters learned
stack = [dict() for i in range(2)]
stack[0]['w'] = sae1_opt_theta[0:hidden_size_L1 * input_size].reshape(
hidden_size_L1, input_size)
stack[0]['b'] = sae1_opt_theta[2 * hidden_size_L1 *
input_size:2 * hidden_size_L1 * input_size +
hidden_size_L1]
stack[1]['w'] = sae2_opt_theta[0:hidden_size_L1 * hidden_size_L2].reshape(
hidden_size_L2, hidden_size_L1)
if __name__ == '__main__':
file_path = r"C:\Study\test\bone\2"
out_dir = "C:\\Study\\test\\softmax_norm_test"
# weights_file = "weights.npy"
# w0 = loadWeights(weights_file)
# w0 = np.load(weights_file)
# print(np.shape(w0))
# print(w0)
inputfile = "data.txt"
feature, label = loadData(inputfile)
feature = handleHistogram(feature)
# print(np.shape(feature), np.shape(label))
# print(feature)
k = 256
w0 = train(feature, label, k, 100000, 0.1)
fp = open("pickle_weight_test.dat", "wb")
pickle.dump(w0, fp)
fp.close()
handle(file_path, out_dir, (45,-45,45,-45), w0)
# # 分割评估
# file_path = "C:\\Study\\test\\100-gt" # 标准分割图像目录路径
# out_dir = "C:\\Study\\test\\est_results" #结果保存目录
# print("softmax")
# file_path_2 = "C:\\Study\\test\\softmax_no_norm_no_limited" # 方法一得到分割图像路径
# res = batchProcess(file_path, file_path_2)
# printEst(res, "softmax")
# saveEst(res, "softmax", out_dir)
# rates and regularization strengths; if you are careful you should be able to
# get a classification accuracy of over 0.35 on the validation set.
results = {}
best_val = -1
best_softmax = None
learning_rates = [1e-7, 5e-7]
regularization_strengths = [2.5e4, 5e4]
for lr in learning_rates:
for rs in regularization_strengths:
softmax = liner_classifiers_total.Softmax()
loss_history = softmax.train(X_train,
Y_train,
lr,
rs,
num_iters=1500,
batch_size=100,
verbose=True)
Y_train_pred = softmax.predict(X_train)
train_accuracy = np.mean(Y_train == Y_train_pred)
Y_val_pred = softmax.predict(X_val)
val_accuracy = np.mean(Y_val == Y_val_pred)
if val_accuracy > best_val:
best_val = val_accuracy
best_softmax = softmax
results[(lr, rs)] = train_accuracy, val_accuracy
# print out result
def main():
"""
Step 0: Initialize parameter values for sparse autoencoder and softmax regression.
"""
row_size = 28
visible_size = row_size**2
num_labels = 5
hidden_size = 200
rho = 0.1
lambda_ = 3e-3
beta = 3
max_iter = 400
debug = 0
"""
Step 1: Load data from the MNIST database
Load the training set data and sort the training data into labeled and unlabeled sets.
"""
fIm = sys.argv[1]
fLb = sys.argv[2]
# read training data and labels
data, label = read(fIm, fLb)
# simulate a labeled and unlabeled set
# set the numbers that will be used for the unlabeled versus labeled sets
ixu = np.argwhere(label >= 5).flatten()
ixl = np.argwhere(label < 5).flatten()
# build a training and test set -> separate half the labeled set to use as test data
numTrain = round(ixl.shape[0] / 2) # half the examples in the set
train_val = ixl[0:numTrain]
test_val = ixl[numTrain:]
unlabeled_set = label[ixu]
unlabeled_data = data[:, ixu]
train_data = data[:, train_val]
train_set = label[train_val]
test_data = data[:, test_val]
test_set = label[test_val]
print data.shape
# output some statistics
print "# of examples in unlabeled set: {0:6d}".format(len(unlabeled_set))
print "# of examples in supervised training set: {0:6d}".format(
len(train_set))
print "# of examples in supervised test set: {0:6d}".format(len(test_set))
"""
Optional Step: Test Sparse Autoencoder
"""
if debug == 1:
subdata, sublabel, sub_visible, sub_hidden = sparseAuto.subsample(
train_data, train_set, row_size)
sub_theta = sparseAuto.initializeParameters(sub_hidden, sub_visible)
sub_grad, sub_cost = sparseAuto.costfun(sub_theta, sub_visible,
sub_hidden, lambda_, rho, beta,
subdata)
numGrad, diff = sparseAuto.numgrad(sub_theta, sub_grad, sub_visible,
sub_hidden, lambda_, rho, beta,
subdata)
print diff
"""
Step 2: Train Sparse Autoencoder
"""
print 'Step 2'
opt_theta = sparseAuto.train(visible_size, hidden_size, lambda_, rho, beta,
unlabeled_data)
"""
Step 3: Extract Features from the Supervised Data Set
"""
print 'Step 3'
train_features = sparseAuto.autoencoder(opt_theta, hidden_size,
visible_size, train_data)
test_features = sparseAuto.autoencoder(opt_theta, hidden_size,
visible_size, test_data)
"""
Step 4: Train the softmax classifier
"""
print 'Step 4'
lam = 1e-4
thetaOpt = softmax.train(num_labels, hidden_size, lam, train_features,
train_set)
"""
Step 5: Testing softmax classfier
"""
print 'Step 5'
pred = softmax.predict(thetaOpt, test_features, num_labels, hidden_size)
print pred[0:15]
print test_set[0:15]
# report accuracy of softmax regression
accuracy = 100 * np.sum(test_set == pred) / len(test_set)
print "Accuracy is {0:.2f}".format(accuracy)
def main():
"""
Step 0: Initialization
"""
# Initialize parameters for the exercise
image_dim = 64
image_channels = 3
patch_dim = 8
num_patches = 50000
visible_size = patch_dim * patch_dim * image_channels
output_size = visible_size
hidden_size = 400
epsilon = 0.1
pool_dim = 19
debug = 0
"""
Step 1: Train a sparse autoencoder (with a linear decoder)
"""
# load data from linear decoder exercise
opt_theta = np.load('opt_theta.npy')
zca_white = np.load('zca_white.npy')
mean_patch = np.load('mean_patch.npy')
# unpack W and b
W = opt_theta[0:hidden_size * visible_size].reshape(
hidden_size, visible_size)
b = opt_theta[2 * hidden_size *
visible_size:2 * hidden_size * visible_size + hidden_size]
"""
Step 2a: Implement convolution
"""
# read in train data from mat file
mat_contents = sio.loadmat('stlTrainSubset.mat')
train_images = mat_contents['trainImages']
train_labels = mat_contents['trainLabels']
num_train_images = mat_contents['numTrainImages'][0][0]
# read in test data from mat file
mat_contents = sio.loadmat('stlTestSubset.mat')
test_images = mat_contents['testImages']
test_labels = mat_contents['testLabels']
num_test_images = mat_contents['numTestImages'][0][0]
# use only the first 8 images for testing
conv_images = train_images[:, :, :, 0:8]
# use only the first 8 images to test
convolved_features = cnn.convolve(patch_dim, hidden_size, conv_images, W,
b, zca_white, mean_patch)
if debug == 1:
"""
Step 2b: Check your convolution
"""
for i in range(1000):
feature_num = np.random.randint(0, hidden_size)
image_num = np.random.randint(0, 8)
image_row = np.random.randint(0, image_dim - patch_dim + 1)
image_col = np.random.randint(0, image_dim - patch_dim + 1)
patch = conv_images[image_row:image_row + patch_dim,
image_col:image_col + patch_dim, :, image_num]
patch = np.concatenate(
(patch[:, :,
0].flatten(), patch[:, :,
1].flatten(), patch[:, :,
2].flatten()))
patch = np.reshape(patch, (patch.size, 1))
patch = patch - np.tile(mean_patch,
(patch.shape[1], 1)).transpose()
patch = zca_white.dot(patch)
features = sparseAuto.autoencoder(opt_theta, hidden_size,
visible_size, patch)
if abs(features[feature_num, 0] -
convolved_features[feature_num, image_num, image_row,
image_col]) > 1e-9:
print 'convolved feature does not activation from autoencoder'
print 'feature number:', feature_num
print 'image number:', image_num
print 'image row:', image_row
print 'image column:', image_col
print 'convolved feature:', convolved_features[feature_num,
image_num,
image_row,
image_col]
print 'sparse AE feature:', features[feature_num, 0]
sys.exit(
'convolved feature does not match activation from autoencoder'
)
print('congrats! convolution code passed the test')
"""
Step 2c: Implement Pooling
"""
# pooled_features = cnn.pooling(pool_dim, convolved_features)
"""
Step 2d: Checking your pooling
"""
test_matrix = np.arange(64).reshape(8, 8)
expected_matrix = np.array(
[[np.mean(test_matrix[0:4, 0:4]),
np.mean(test_matrix[0:4, 4:8])],
[np.mean(test_matrix[4:8, 0:4]),
np.mean(test_matrix[4:8, 4:8])]])
test_matrix = test_matrix.reshape(1, 1, 8, 8)
pooled_features = cnn.pooling(4, test_matrix)
if not (pooled_features == expected_matrix).all():
print 'pooling incorrect'
print 'expected:'
pprint.pprint(expected_matrix)
print 'got:'
pprint.pprint(pooled_features)
else:
print "congrats! pooling code passed the test"
"""
Step 3: Convolve and pool with the data set
"""
step_size = 50
assert hidden_size % step_size == 0
pooled_features_train = np.zeros(
(hidden_size, num_train_images,
int(np.floor((image_dim - patch_dim + 1) / pool_dim)),
int(np.floor((image_dim - patch_dim + 1) / pool_dim))))
pooled_features_test = np.zeros(
(hidden_size, num_test_images,
int(np.floor((image_dim - patch_dim + 1) / pool_dim)),
int(np.floor((image_dim - patch_dim + 1) / pool_dim))))
start_time = time.time()
for conv_part in range(hidden_size / step_size):
feature_start = conv_part * step_size
feature_end = (conv_part + 1) * step_size
print 'Step:', conv_part, 'Features', feature_start, 'to', feature_end
Wt = W[feature_start:feature_end, :]
bt = b[feature_start:feature_end]
print 'Convolving and pooling train images'
convolved_features_this = cnn.convolve(patch_dim, step_size,
train_images, Wt, bt, zca_white,
mean_patch)
pooled_features_this = cnn.pooling(pool_dim, convolved_features_this)
pooled_features_train[
feature_start:feature_end, :, :, :] = pooled_features_this
print 'Elapsed time is', str(
datetime.timedelta(seconds=time.time() - start_time))
print 'Convolving and pooling test images'
convolved_features_this = cnn.convolve(patch_dim, step_size,
test_images, Wt, bt, zca_white,
mean_patch)
pooled_features_this = cnn.pooling(pool_dim, convolved_features_this)
pooled_features_test[
feature_start:feature_end, :, :, :] = pooled_features_this
print 'Elapsed time is', str(
datetime.timedelta(seconds=time.time() - start_time))
np.save('pooled_features_train.npy', pooled_features_train)
np.save('pooled_features_test.npy', pooled_features_test)
print 'Elapsed time is', str(
datetime.timedelta(seconds=time.time() - start_time))
"""
Step 4: Use pooled features for classification
"""
# set up parameters for softmax
softmax_lambda = 1e-4
num_classes = 4
# reshape the pooled_features to form an input vector for softmax
softmax_x = np.transpose(pooled_features_train, [0, 2, 3, 1])
softmax_x = softmax_x.reshape(
(pooled_features_train.size / num_train_images, num_train_images))
softmax_y = train_labels.flatten() - 1
softmax_opt_theta = softmax.train(
num_classes, pooled_features_train.size / num_train_images,
softmax_lambda, softmax_x, softmax_y)
np.save('theta_opt_theta.npy', opt_theta)
"""
Step 5: Test Classifier
"""
softmax_x = np.transpose(pooled_features_test, [0, 2, 3, 1])
softmax_x = softmax_x.reshape(
(pooled_features_test.size / num_test_images, num_test_images))
softmax_y = test_labels.flatten() - 1
pred = softmax.predict(softmax_opt_theta, softmax_x, num_classes,
pooled_features_train.size / num_train_images)
accuracy = 100 * np.sum(softmax_y == pred) / len(softmax_y)
print "Accuracy is {0:.2f}".format(accuracy)
print 'Iter : %s Training error = %s' % (iter+1, trainError)
testError = evaluatePredictor(testExamples, lambda(x) : (1 if dotProduct(featureExtractor(x), weights) >= 0 else -1))
print "=" * 30
print "Result"
print 'Iter : %s Test error = %s' % (iter+1, testError)
return weights
def evaluatePredictor(examples, predictor):
'''
predictor: a function that takes an x and returns a predicted y.
Given a list of examples (x, y), makes predictions based on |predict| and returns the fraction
of misclassiied examples.
'''
error = 0
for x, y in examples:
if predictor(x) != y:
error += 1
return 1.0 * error / len(examples)
if __name__ == '__main__':
# Load training data
trainingData = loadTrainingData()
testData = loadTestData()
trainExamples = [(data, 1 if data['stars'] > 3 else -1) for data in trainingData]
testExamples = [(data, 1 if data['stars'] > 3 else -1) for data in testData]
perceptron(trainExamples, testExamples, extractWordAndIdFeatures)
trainExamples = [(data, data['stars']) for data in trainingData]
testExamples = [(data, data['stars']) for data in testData]
softmax.train(trainExamples, testExamples, extractWordFeatures)
rel_error = abs(grad_numerical - grad_analytic) / (
abs(grad_numerical) + abs(grad_analytic))
print('numerical: %f analytic: %f, relative error: %e' %
(grad_numerical, grad_analytic, rel_error))
#现在我们对加入了正则项的梯度进行检验
loss, grad = softmax.softmax_loss_vectorized(w, x_dev, y_dev, 0.0)
f = lambda w: softmax.softmax_loss_vectorized(w, x_dev, y_dev, 0.0)[0]
grad_numerical = grad_check_sparse(f, w, grad)
softmax = Softmax() #创建对象，此时W为空
tic = time.time()
loss_hist = softmax.train(x_train,
y_train,
learning_rate=1e-7,
reg=2.5e4,
num_iters=1500,
verbose=True) #此时svm对象中有W
toc = time.time()
print('that took %fs' % (toc - tic))
plt.plot(loss_hist)
plt.xlabel('iteration number')
plt.ylabel('loss value')
plt.show()
#训练完成之后，将参数保存，使用参数进行预测，计算准确率
y_train_pred = softmax.predict(x_train)
print('training accuracy: %f' % (np.mean(y_train == y_train_pred))) #返回条件成立的占比
y_val_pred = softmax.predict(x_val)
print('validation accuracy: %f' % (np.mean(y_val == y_val_pred)))
#在拿到一组数据时一般分为训练集，开发集（验证集），测试集。训练和测试集都知道是干吗的，验证集在除了做验证训练结果外
regularization_strengths = [7.5e3, 1e4, 2.5e4, 5e4, 7.5e4, 1e5]
################################################################################
# TODO: #
# Use the validation set to set the learning rate and regularization strength. #
# This should be identical to the validation that you did for the SVM; save #
# the best trained softmax classifer in best_softmax. #
################################################################################
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
for learning_rate in learning_rates:
for regularization_strength in regularization_strengths:
softmax = linear_classifier.Softmax()
softmax.train(X_train,
y_train,
learning_rate=learning_rate,
reg=regularization_strength,
num_iters=1500)
y_train_pred = softmax.predict(X_train)
y_val_pred = softmax.predict(X_val)
train_acc = np.mean(y_train == y_train_pred)
val_acc = np.mean(y_val == y_val_pred)
results[learning_rate, regularization_strength] = train_acc, val_acc
if best_val < val_acc:
best_val = val_acc
best_softmax = softmax
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
print "Result"
print 'Iter : %s Test error = %s' % (iter + 1, testError)
return weights
def evaluatePredictor(examples, predictor):
'''
predictor: a function that takes an x and returns a predicted y.
Given a list of examples (x, y), makes predictions based on |predict| and returns the fraction
of misclassiied examples.
'''
error = 0
for x, y in examples:
if predictor(x) != y:
error += 1
return 1.0 * error / len(examples)
if __name__ == '__main__':
# Load training data
trainingData = loadTrainingData()
testData = loadTestData()
trainExamples = [(data, 1 if data['stars'] > 3 else -1)
for data in trainingData]
testExamples = [(data, 1 if data['stars'] > 3 else -1)
for data in testData]
perceptron(trainExamples, testExamples, extractWordAndIdFeatures)
trainExamples = [(data, data['stars']) for data in trainingData]
testExamples = [(data, data['stars']) for data in testData]
softmax.train(trainExamples, testExamples, extractWordFeatures)
