import plotting
import numpy as np
from data_reader import load
from settings import DATA_DIR, DATA_SEED
trainx, trainy = load(DATA_DIR, subset='train')
rng_data = np.random.RandomState(DATA_SEED)
inds = rng_data.permutation(trainx.shape[0])
trainx = trainx[inds]
trainy = trainy[inds]
txs = []
for j in range(10):
txs.append(trainx[trainy == j][:10])
txs = np.concatenate(txs, axis=0)
img_bhwc = np.transpose(txs, (0, 2, 3, 1))
img_tile = plotting.img_tile(img_bhwc,
aspect_ratio=1.0,
border_color=1.0,
stretch=True)
img = plotting.plot_img(img_tile, title='CIFAR10 samples')
plotting.plt.savefig("cifar_sample.png")
from data_reader import load
from settings import DATA_DIR
import numpy as np
trainx, trainy = load(DATA_DIR, subset='train')
print('The training data is composed of: ' + str(np.shape(trainx)[0]) + ' examples.')
testx, testy = load(DATA_DIR, subset='test')
print('The testing data is composed of: ' + str(np.shape(testx)[0]) + ' examples.')
tx_resized = []
for n in range(batch_size):
tx_resized.append(
preprocess(np.transpose(train_temp[n], (1, 2, 0))))
tx_resized = np.concatenate(tx_resized, axis=0)
output_features.append(extract_features(tx_resized))
return np.concatenate(output_features, axis=0)
with open('inception_v3.pkl', 'rb') as f:
params = pickle.load(f)
net = build_network()
lasagne.layers.set_all_param_values(net['softmax'], params['param values'])
trainx, _ = load(DATA_DIR, subset='train')
testx, _ = load(DATA_DIR, subset='test')
minibatch_size = 10
feature_layer = net['pool3']
print("Extracting features from train data...")
train_features = extract(trainx, feature_layer, minibatch_size)
print("Extracting features from test data...")
test_features = extract(testx, feature_layer, minibatch_size)
print(train_features.shape)
print(test_features.shape)
np.savez_compressed('cifar_train_x', train_features)
np.savez_compressed('cifar_test_x', test_features)
import numpy as np
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
from data_reader import load, get_data
from settings import DATA_DIR, DATA_SEED
samples_per_class = 500
data_type = 'train' # 'test' or 'train'
data_name = 'cifar_train_triplet_100_x.npz'
datax = get_data(data_name)
_, datay = load(DATA_DIR, subset=data_type)
pca = PCA(n_components=2)
X_new = pca.fit_transform(datax)
print(datax.shape)
rng_data = np.random.RandomState(DATA_SEED)
inds = rng_data.permutation(X_new.shape[0])
X_new = X_new[inds]
datay = datay[inds]
plt.rcParams["figure.figsize"] = (15, 12)
for j in range(10):
txs = X_new[datay == j][:samples_per_class]
plt.scatter(txs[:, 0], txs[:, 1])
plt.title('PCA 2D transform on ' + data_name, fontsize=20)
plt.xlabel('PC1', fontsize=18)
plt.ylabel('PC2', fontsize=18)
plt.savefig('pca_' + data_name + '.png')