if __name__ == "__main__":
if len(sys.argv) < 6:
print(
"Error, Syntax: {0} [version] [prototype selection] [classwise/independent] [prototype number] [fold]"
.format(sys.argv[0]))
exit()
version = sys.argv[1]
selection = sys.argv[2]
classwise = sys.argv[3]
proto_number = int(sys.argv[4])
fold = int(sys.argv[5])
print("Starting: {}".format(version))
# load settings
ns.load_settings_raw(version, "1d", 50, 2, fold)
full_data_file = os.path.join("data", version + "-re-data.txt")
full_label_file = os.path.join("data", version + "-re-labels.txt")
# load data
data_sets = input_data.read_data_sets(full_data_file,
full_label_file,
ns.IMAGE_SHAPE,
test_ratio=0.1,
validation_ratio=0.0,
pickle=False,
boring=False,
fold=fold)
no_classes = ns.NUM_CLASSES
# print(proto_number)
def main(argv):
if len(argv) < 5:
print(
"Error, Syntax: {0} [train/test] [dataset] [conv dim] [conv width] [fold]"
.format(argv[0]))
exit()
global conv_shape
conv_shape = int(argv[4])
dataset = argv[2]
conv_dim = argv[3]
test = argv[1]
fold = int(argv[5])
ns.load_settings_raw(dataset, conv_dim, 50, 2, fold)
run_name = "raw-fc1024-lr{0}-adam-{1}conv-{2}-fold{3}".format(
ns.LEARNING_RATE, conv_shape, dataset, fold) # +"-"+nowtime
print(run_name)
data_sets = input_data.read_data_sets(ns.TRAINING_FILE,
ns.TRAINING_LABEL,
ns.IMAGE_SHAPE,
test_file=ns.TEST_FILE,
test_label=ns.TEST_LABEL,
validation_ratio=0.0,
pickle=False,
boring=False)
train_data = data_sets.train.images # Returns np.array
train_labels = np.asarray(data_sets.train.labels, dtype=np.int32)
eval_data = data_sets.test.images # Returns np.array
eval_labels = np.asarray(data_sets.test.labels, dtype=np.int32)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.4
# Create the Estimator
if conv_dim == "1d":
classifier = tf.estimator.Estimator(
model_fn=cnn_model_1D,
model_dir="models/" + run_name,
config=tf.estimator.RunConfig(session_config=config))
else:
classifier = tf.estimator.Estimator(
model_fn=cnn_model_2D,
model_dir="models/" + run_name,
config=tf.estimator.RunConfig(session_config=config))
if test == "train":
# train
# Set up logging for predictions
# Log the values in the "Softmax" tensor with label "probabilities"
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log,
every_n_iter=100)
# Train the model
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": train_data},
y=train_labels,
batch_size=ns.BATCH_SIZE,
num_epochs=None,
shuffle=True)
classifier.train(input_fn=train_input_fn,
steps=ns.NUM_ITER,
hooks=[logging_hook])
# Evaluate the model and print results
eval_input_fn = tf.estimator.inputs.numpy_input_fn(x={"x": eval_data},
y=eval_labels,
num_epochs=1,
shuffle=False)
eval_results = classifier.evaluate(input_fn=eval_input_fn)
print(run_name)
print(eval_results)
else:
# test
# Evaluate the model and print results
eval_input_fn = tf.estimator.inputs.numpy_input_fn(x={"x": eval_data},
y=eval_labels,
num_epochs=1,
shuffle=False)
# eval_results = classifier.evaluate(input_fn=eval_input_fn)
labels = eval_labels
predictions = list(classifier.predict(input_fn=eval_input_fn))
predicted_classes = [p["classes"] for p in predictions]
from sklearn.metrics import confusion_matrix, classification_report
print(run_name)
print(confusion_matrix(labels, predicted_classes))
print(classification_report(labels, predicted_classes))
output, cost, DTW, path = dtw.dtw(local_proto,
local_sample,
extended=True)
for f in range(50):
features[f, prototype] = cost[path[0][f]][path[1][f]]
return features
if __name__ == "__main__":
for version in ["1a", "1b", "1c"]:
print("Starting: {}".format(version))
# load settings
ns.load_settings_raw(version, "1d")
full_data_file = os.path.join("data", version + "-re-data.txt")
full_label_file = os.path.join("data", version + "-re-labels.txt")
# load data
data_sets = input_data.read_data_sets(full_data_file,
full_label_file,
ns.IMAGE_SHAPE,
test_ratio=0.1,
validation_ratio=0.0,
pickle=False,
boring=False)
# proto_factor is number of same class prototypes
proto_factor = 5 if version == "1a" else 2
no_classes = ns.NUM_CLASSES
