'text.fontsize': 10,
'legend.fontsize': 10,
'xtick.labelsize': 10,
'ytick.labelsize': 10,
'text.usetex': False,
'figure.figsize': [4.5, 4.5]})
import pscgen
def num_ops(N, M):
return N * (2 * M - 1)
args = json.loads(sys.argv[1])
storage = pscgen.name_to_storage(args['storage'])
comp_scheme = pscgen.name_to_comp_scheme('pca')
X, Y, X_flat = util.wav_to_np(args['tr_folder_path'], window_size=50)
assert False
num_folds = 5
acc = 0.0
max_atoms = 1000
sss = StratifiedShuffleSplit(Y, num_folds, test_size=0.7, random_state=0)
alphas = [1, 2, 3, 4, 5, 5, 5, 5, 5, 10, 10, 10, 15, 20, 20, 20, 20, 25]
betas = [1, 1, 1, 1, 1, 2, 3, 4, 5, 5, 7, 10, 10, 10, 12, 15, 20, 20]
Ns = [1, 2, 3, 4, 5, 10, 15, 20, 25, 50, 70, 100, 150, 200, 240, 300, 400, 500]
alphas = [1, 2, 3, 4, 5, 5, 5, 5, 5, 10, 10, 10, 15, 20, 20]
betas = [1, 1, 1, 1, 1, 2, 3, 4, 5, 5, 7, 10, 10, 10, 12]
Ns = [1, 2, 3, 4, 5, 10, 15, 20, 25, 50, 70, 100, 150, 200, 240]
accs = {}
for s in sets:
result = result.intersection(s)
return result
N = 25
M = 10000
KMeans_tr_size = 200000
D_atoms = 500
zoom_dim = 20
data_folder = sys.argv[1]
output_folder = sys.argv[2]
if output_folder[-1] != '/':
output_folder += '/'
X, Y = util.wav_to_np(data_folder)
X = [util.sliding_window(x, 40, 20) for x in X]
X = np.vstack(X)
X = X[np.random.permutation(len(X))]
X_Kmeans = X[:KMeans_tr_size]
D = KMeans(n_clusters=D_atoms, init_size=D_atoms*3)
D.fit(X_Kmeans)
D = D.cluster_centers_
D = util.normalize(D)
X = util.normalize(X)
D_mean = np.mean(D, axis=0)
D = D - D_mean
X = X - D_mean
U, S_D, V = np.linalg.svd(D)
predictions = np.array(predictions)
return self.class_labels[np.argmax(np.sum(predictions, axis=0), axis=1)]
linewidth = 2
fig_name = 'boosted_dim'
KMeans_tr_size = 200000
D_atoms = 500
ws = 50
subsample_pcts = [1., 1., 1., 0.5]
X_flat, Y = util.wav_to_np('/home/brad/data/robot/')
X = []
num_folds = 10
sss = StratifiedShuffleSplit(Y, num_folds, test_size=0.7, random_state=0)
for x in X_flat:
X.append(util.sliding_window(x, ws, 5))
plt_dict = {}
features = [2, 5, 10, 20]
nodes = [1, 2, 5, 10, 15, 20]
for f in features:
plt_dict[f] = []
for n in nodes:
