if __name__ == "__main__":
# config
args = parse_args()
if args.model == 'ca':
config = load_json('./mnist-ca.json')
elif args.model == 'gc':
config = load_json('./mnist-gc.json')
else:
config = load_json('./mnist-gc.json')
gc = GCForest(config)
# gc.set_keep_model_in_mem(False)
gc.set_keep_model_in_mem(True)
# data
data_num_train = 60000 # The number of figures
data_num_test = 10000 # test num
fig_w = 45 # width of each figure
X_train = np.fromfile("./data/mnist_train/mnist_train_data",
dtype=np.uint8)
y_train = np.fromfile("./data/mnist_train/mnist_train_label",
dtype=np.uint8)
X_test = np.fromfile("./data/mnist_test/mnist_test_data", dtype=np.uint8)
y_test = np.fromfile("./data/mnist_test/mnist_test_label", dtype=np.uint8)
# reshape the matrix
X_train = X_train.reshape(data_num_train, 1, fig_w, fig_w)
})
config["cascade"] = ca_config
return config
if __name__ == "__main__":
args = parse_args()
if args.model is None:
config = get_toy_config()
else:
config = load_json(args.model)
gc = GCForest(config)
# If the model you use cost too much memory for you.
# You can use these methods to force gcforest not keeping model in memory
gc.set_keep_model_in_mem(False) # default is TRUE.
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# X_train, y_train = X_train[:2000], y_train[:2000]
X_train = X_train[:, np.newaxis, :, :]
X_test = X_test[:, np.newaxis, :, :]
X_train_enc = gc.fit_transform(X_train, y_train)
# X_enc is the concatenated predict_proba result of each estimators of the last layer of the GCForest model
# X_enc.shape =
# (n_datas, n_estimators * n_classes): If cascade is provided
# (n_datas, n_estimators * n_classes, dimX, dimY): If only finegrained part is provided
# You can also pass X_test, y_test to fit_transform method, then the accracy on test data will be logged when training.
# X_train_enc, X_test_enc = gc.fit_transform(X_train, y_train, X_test=X_test, y_test=y_test)
# WARNING: if you set gc.set_keep_model_in_mem(True), you would have to use
# gc.fit_transform(X_train, y_train, X_test=X_test, y_test=y_test) to evaluate your model.
config["cascade"] = ca_config
return config
if __name__ == "__main__":
args = parse_args()
if args.model is None:
config = get_toy_config()
else:
config = load_json(args.model)
gc = GCForest(config)
# If the model you use cost too much memory for you.
# You can use these methods to force gcforest not keeping model in memory
# gc.set_keep_model_in_mem(False), default is TRUE.
gc.set_keep_model_in_mem(False)
(X_train, y_train), (X_test, y_test) = load_defect_data()
print('X_train.shape', X_train.shape, 'X_test', X_test.shape, 'y_train', y_train.shape, 'y_test', y_test.shape)
# X_train, y_train = X_train[:2000], y_train[:2000]
X_train = X_train[:, np.newaxis, :, :]
X_test = X_test[:, np.newaxis, :, :]
X_train_enc = gc.fit_transform(X_train,y_train, X_test=X_test, y_test=y_test)
# X_enc is the concatenated predict_proba result of each estimators of the last layer of the GCForest model
# X_enc.shape =
# (n_datas, n_estimators * n_classes): If cascade is provided
# (n_datas, n_estimators * n_classes, dimX, dimY): If only finegrained part is provided
# You can also pass X_test, y_test to fit_transform method, then the accracy on test data will be logged when training.
# X_train_enc, X_test_enc = gc.fit_transform(X_train, y_train, X_test=X_test, y_test=y_test)