candidate_samples[i * n_test + j][4:516] = cnn_prediction
candidate_samples[np.isfinite(candidate_samples) == False] = 0
candidate_samples[np.isnan(candidate_samples) == True] = 0
pred = sg.predict(candidate_samples)
pred_labels = np.zeros(pred.shape[0])
for i in range(0, pred.shape[0]):
if pred[i, 0] > pred[i, 1]:
pred_labels[i] = pred[i, 0]
else:
pred_labels[i] = pred[i, 1]
def save_data_as_hdf5_results(hdf5_data_filename, data, predict_labels):
'''
HDF5 is one of the data formats Caffe accepts
'''
with h5py.File(hdf5_data_filename, 'w') as f:
f['data'] = data.astype(np.float32)
f['label'] = predict_labels.astype(np.float32)
save_data_as_hdf5_results('test_data_full_with_prediction_.hdf5',
isolated_test_data_img[:, 0:3, ...], pred_labels)
# test accuracy
pred = sg.predict(train_samples[n_train:])
pred_classes = [np.argmax(p) for p in pred]
#
_ = sg.evaluate(labels[n_train:], pred_classes)
shuffle_idx = np.random.permutation(y.size)
X = X[shuffle_idx]
y = y[shuffle_idx]
# hold out 20 percent of data for testing accuracy
train_prct = 0.8
n_train = int(round(X.shape[0]*train_prct))
# define base models
base_models = [RandomForestClassifier(n_estimators=100, n_jobs=-1, criterion='gini'),
RandomForestClassifier(n_estimators=100, n_jobs=-1, criterion='entropy'),
ExtraTreesClassifier(n_estimators=100, n_jobs=-1, criterion='gini')]
# define blending model
blending_model = LogisticRegression()
# initialize multi-stage model
sg = StackedGeneralizer(base_models, blending_model,
n_folds=N_FOLDS, verbose=VERBOSE)
# fit model
sg.fit(X[:n_train],y[:n_train])
# test accuracy
pred = sg.predict(X[n_train:])
pred_classes = [np.argmax(p) for p in pred]
_ = sg.evaluate(y[n_train:], pred_classes)
shuffle_idx = np.random.permutation(y.shape[0])
X = train_sample[shuffle_idx]
y = y[shuffle_idx]
# hold out 20 percent of data for testing accuracy
train_prct = 0.8
n_train = int(round(X.shape[0]*train_prct))
# define base models
base_models = [GradientBoostingClassifier(n_estimators=100),
GradientBoostingClassifier(n_estimators=100),
GradientBoostingClassifier(n_estimators=100)]
# define blending model
blending_model = LogisticRegression()
# initialize multi-stage model
sg = StackedGeneralizer(base_models, blending_model,
n_folds=N_FOLDS, verbose=VERBOSE)
# fit model
sg.fit(X[:n_train],y[:n_train])
# test accuracy
pred = sg.predict(X[n_train:])
pred_classes = [np.argmax(p) for p in pred]
_ = sg.evaluate(y[n_train:], pred_classes)
# define blending model
blending_model = LogisticRegression()
# initialize multi-stage model
sg = StackedGeneralizer(base_models,
blending_model,
n_folds=N_FOLDS,
verbose=VERBOSE)
# fit model
sg.fit(train_samples, labels)
pred = sg.predict(train_samples)
pred_classes = [np.argmax(p) for p in pred]
#
_ = sg.evaluate(labels, pred_classes)
# Generate Test Data
print 'Finish the fitting phase'
overlap_threshold = 0.8
def overlap_area(test_box, restrict_box):
result = 0
w = min(test_box[2] + test_box[0], restrict_box[2] +
restrict_box[0]) - max(test_box[0], restrict_box[0]) + 1
h = min(test_box[3] + test_box[1], restrict_box[3] +
restrict_box[1]) - max(test_box[1], restrict_box[1]) + 1
if w > 0 and h > 0:
