def main():
images, labels = load_labeled_training(flatten=True)
images = standardize(images)
unl = load_unlabeled_training(flatten=True)
unl = standardize(unl)
test = load_public_test(flatten=True)
test = standardize(test)
shuffle_in_unison(images, labels)
#d = DictionaryLearning().fit(images)
d = MiniBatchDictionaryLearning(n_components=500, n_iter=500, verbose=True).fit(images)
s = SparseCoder(d.components_)
proj_test = s.transform(images)
pt = s.transform(test)
#kpca = KernelPCA(kernel="rbf")
#kpca.fit(unl)
#test_proj = kpca.transform(images)
#pt = kpca.transform(test)
#spca = SparsePCA().fit(unl)
#test_proj = spca.transform(images)
#pt = spca.transform(test)
svc = SVC()
scores = cross_validation.cross_val_score(svc, proj_test, labels, cv=10)
print scores
print np.mean(scores)
print np.var(scores)
svc.fit(proj_test, labels)
pred = svc.predict(pt)
write_results(pred, '../svm_res.csv')
def main():
K = 30 # Number of dimensions to PCA down to.
test_image, test_label = load_labeled_training(flatten=True)
train_image = load_unlabeled_training(flatten=True)
pca = PCA(n_components=K).fit(train_image)
proj_test = pca.transform(test_image)
#v, mean, projX = pcaimg(train_image.T, K)
#proj_test = np.dot(v.T, test_image.T).T
#assert proj_test.shape[0] == test_label.shape[0]
x_train, x_test, y_train, y_test = cross_validation.train_test_split(
proj_test, test_label)
nbrs = KNeighborsClassifier(n_neighbors=1)
scores = cross_validation.cross_val_score(nbrs, proj_test, test_label, cv=3)
print scores
def main():
K = 30 # Number of dimensions to PCA down to.
test_image, test_label = load_labeled_training(flatten=True)
train_image = load_unlabeled_training(flatten=True)
pca = PCA(n_components=K).fit(train_image)
proj_test = pca.transform(test_image)
#v, mean, projX = pcaimg(train_image.T, K)
#proj_test = np.dot(v.T, test_image.T).T
#assert proj_test.shape[0] == test_label.shape[0]
x_train, x_test, y_train, y_test = cross_validation.train_test_split(
proj_test, test_label)
nbrs = KNeighborsClassifier(n_neighbors=1)
scores = cross_validation.cross_val_score(nbrs,
proj_test,
test_label,
cv=3)
print scores
def get_dictionary_data(n_comp=20, zero_index=False):
unlabeled = util.load_unlabeled_training(flatten=False)
height, width = 32, 32
n_images = 10000
patch_size = (8, 8)
unlabeled = util.standardize(unlabeled)
np.random.shuffle(unlabeled)
print('Extracting reference patches...')
patches = np.empty((0, 64))
t0 = time()
for image in unlabeled[:n_images, :, :]:
data = np.array(extract_patches_2d(image, patch_size,
max_patches=0.01))
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
patches = np.concatenate([patches, data])
print('done in %.2fs.' % (time() - t0))
# whiten the patches
z = zca.ZCA()
z.fit(patches)
z.transform(patches)
print('Learning the dictionary...')
t0 = time()
dico = MiniBatchDictionaryLearning(n_components=n_comp, alpha=1)
V = dico.fit(patches).components_
dt = time() - t0
print('done in %.2fs.' % dt)
#plt.figure(figsize=(4.2, 4))
#for i, comp in enumerate(V[:100]):
# plt.subplot(10, 10, i + 1)
# plt.imshow(comp.reshape(patch_size), cmap=plt.cm.gray_r,
# interpolation='nearest')
# plt.xticks(())
# plt.yticks(())
#plt.subplots_adjust(0.08, 0.02, 0.92, 0.85, 0.08, 0.23)
#plt.show()
labeled_data, labels = util.load_labeled_training(flatten=False,
zero_index=True)
labeled_data = util.standardize(labeled_data)
test_data = util.load_all_test(flatten=False)
test_data = util.standardize(test_data)
#util.render_matrix(test_data, flattened=False)
print('Reconstructing the training images...')
t0 = time()
reconstructed_images = np.empty((0, 32, 32))
for i, image in enumerate(labeled_data):
data = extract_patches_2d(image, patch_size)
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
code = dico.transform(data)
patches = np.dot(code, V)
z.transform(patches)
patches = patches.reshape(len(data), *patch_size)
data = reconstruct_from_patches_2d(patches, (width, height))
data = data.reshape(1, 32, 32)
reconstructed_images = np.concatenate([reconstructed_images, data])
print('done in %.2fs.' % (time() - t0))
# flatten
n, x, y = reconstructed_images.shape
training_images = reconstructed_images.reshape(
reconstructed_images.shape[0],
reconstructed_images.shape[1] * reconstructed_images.shape[2])
assert training_images.shape == (n, x * y)
print('Reconstructing the test images...')
t0 = time()
reconstructed_test_images = np.empty((0, 32, 32))
for image in test_data:
data = extract_patches_2d(image, patch_size)
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
code = dico.transform(data)
patches = np.dot(code, V)
z.transform(patches)
patches = patches.reshape(len(data), *patch_size)
data = reconstruct_from_patches_2d(patches, (width, height))
data = data.reshape(1, 32, 32)
reconstructed_test_images = np.concatenate(
[reconstructed_test_images, data])
print('done in %.2fs.' % (time() - t0))
# flatten
n, x, y = reconstructed_test_images.shape
test_images = reconstructed_test_images.reshape(
reconstructed_test_images.shape[0],
reconstructed_test_images.shape[1] *
reconstructed_test_images.shape[2])
assert test_images.shape == (n, x * y)
return (training_images, labels, test_images)
def get_dictionary_data(n_comp=20, zero_index=True):
unlabeled = util.load_unlabeled_training(flatten=False)
height, width = 32, 32
n_images = 10000
patch_size = (8, 8)
unlabeled = util.standardize(unlabeled)
np.random.shuffle(unlabeled)
print('Extracting reference patches...')
patches = np.empty((0, 64))
t0 = time()
for image in unlabeled[:n_images, :, :]:
data = np.array(extract_patches_2d(image, patch_size, max_patches=0.10))
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
patches = np.concatenate([patches, data])
print('done in %.2fs.' % (time() - t0))
# whiten the patches
z = zca.ZCA()
z.fit(patches)
z.transform(patches)
print('Learning the dictionary...')
t0 = time()
dico = MiniBatchDictionaryLearning(n_components=n_comp, alpha=1)
V = dico.fit(patches).components_
dt = time() - t0
print('done in %.2fs.' % dt)
#plt.figure(figsize=(4.2, 4))
#for i, comp in enumerate(V[:100]):
# plt.subplot(10, 10, i + 1)
# plt.imshow(comp.reshape(patch_size), cmap=plt.cm.gray_r,
# interpolation='nearest')
# plt.xticks(())
# plt.yticks(())
#plt.subplots_adjust(0.08, 0.02, 0.92, 0.85, 0.08, 0.23)
#plt.show()
labeled_data, labels = util.load_labeled_training(flatten=False, zero_index=True)
labeled_data = util.standardize(labeled_data)
test_data = util.load_all_test(flatten=False)
test_data = util.standardize(test_data)
#util.render_matrix(test_data, flattened=False)
print('Training SVM with the training images...')
t0 = time()
reconstructed_images = np.empty((0, 64))
multiplied_labels = np.empty((0))
for i in range(len(labeled_data)):
image = labeled_data[i, :, :]
label = labels[i]
data = extract_patches_2d(image, patch_size, max_patches=0.50)
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
code = dico.transform(data)
patches = np.dot(code, V)
z.transform(patches)
reconstructed_images = np.concatenate([reconstructed_images, patches])
extended_labels = np.asarray([label] * len(patches))
multiplied_labels = np.concatenate([multiplied_labels, extended_labels])
print(reconstructed_images.shape, multiplied_labels.shape)
svc = SVC()
#print('Getting cross-val scores...')
#scores = cross_validation.cross_val_score(svc, reconstructed_images, multiplied_labels, cv=10)
#print('cross-val scores:', scores)
#print('cross-val mean:', np.mean(scores))
#print('cross-val variance:', np.var(scores))
print('done in %.2fs.' % (time() - t0))
svc.fit(reconstructed_images, multiplied_labels)
print('Reconstructing the test images...')
t0 = time()
predictions = []
for i, image in enumerate(test_data):
data = extract_patches_2d(image, patch_size, max_patches=0.25)
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
code = dico.transform(data)
patches = np.dot(code, V)
z.transform(patches)
pred = svc.predict(patches)
print('Variance in the predictions:', np.var(pred))
predictions.append(mode(pred))
print('done in %.2fs.' % (time() - t0))
predictions += 1
util.write_results(predictions, 'svm_patches_25_percent_20_comp.csv')
def get_dictionary_data(n_comp=20, zero_index=False):
unlabeled = util.load_unlabeled_training(flatten=False)
height, width = 32, 32
n_images = 10000
patch_size = (8, 8)
unlabeled = util.standardize(unlabeled)
np.random.shuffle(unlabeled)
print('Extracting reference patches...')
patches = np.empty((0, 64))
t0 = time()
for image in unlabeled[:n_images, :, :]:
data = np.array(extract_patches_2d(image, patch_size, max_patches=0.01))
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
patches = np.concatenate([patches, data])
print('done in %.2fs.' % (time() - t0))
# whiten the patches
z = zca.ZCA()
z.fit(patches)
z.transform(patches)
print('Learning the dictionary...')
t0 = time()
dico = MiniBatchDictionaryLearning(n_components=n_comp, alpha=1)
V = dico.fit(patches).components_
dt = time() - t0
print('done in %.2fs.' % dt)
#plt.figure(figsize=(4.2, 4))
#for i, comp in enumerate(V[:100]):
# plt.subplot(10, 10, i + 1)
# plt.imshow(comp.reshape(patch_size), cmap=plt.cm.gray_r,
# interpolation='nearest')
# plt.xticks(())
# plt.yticks(())
#plt.subplots_adjust(0.08, 0.02, 0.92, 0.85, 0.08, 0.23)
#plt.show()
labeled_data, labels = util.load_labeled_training(flatten=False, zero_index=True)
labeled_data = util.standardize(labeled_data)
test_data = util.load_all_test(flatten=False)
test_data = util.standardize(test_data)
#util.render_matrix(test_data, flattened=False)
print('Reconstructing the training images...')
t0 = time()
reconstructed_images = np.empty((0, 32, 32))
for i, image in enumerate(labeled_data):
data = extract_patches_2d(image, patch_size)
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
code = dico.transform(data)
patches = np.dot(code, V)
z.transform(patches)
patches = patches.reshape(len(data), *patch_size)
data = reconstruct_from_patches_2d(patches, (width, height))
data = data.reshape(1, 32, 32)
reconstructed_images = np.concatenate([reconstructed_images, data])
print('done in %.2fs.' % (time() - t0))
# flatten
n, x, y = reconstructed_images.shape
training_images = reconstructed_images.reshape(reconstructed_images.shape[0], reconstructed_images.shape[1]*reconstructed_images.shape[2])
assert training_images.shape == (n, x*y)
print('Reconstructing the test images...')
t0 = time()
reconstructed_test_images = np.empty((0, 32, 32))
for image in test_data:
data = extract_patches_2d(image, patch_size)
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0) + 1e-20
code = dico.transform(data)
patches = np.dot(code, V)
z.transform(patches)
patches = patches.reshape(len(data), *patch_size)
data = reconstruct_from_patches_2d(patches, (width, height))
data = data.reshape(1, 32, 32)
reconstructed_test_images = np.concatenate([reconstructed_test_images, data])
print('done in %.2fs.' % (time() - t0))
# flatten
n, x, y = reconstructed_test_images.shape
test_images = reconstructed_test_images.reshape(reconstructed_test_images.shape[0], reconstructed_test_images.shape[1]*reconstructed_test_images.shape[2])
assert test_images.shape == (n, x*y)
return (training_images, labels, test_images)
