def run_summary(model_dir: str) -> None:
"""
Gets a summary of the dataset contained in a directory
:param model_dir: Path to the folder where the train.bin, test.bin and
validate.bin can be found
"""
assert (os.path.exists(model_dir))
train_bin = os.path.join(model_dir, "train.bin")
test_bin = os.path.join(model_dir, "test.bin")
validate_bin = os.path.join(model_dir, "validate.bin")
assert os.path.exists(train_bin), "Train dataset does not exists!"
assert os.path.exists(test_bin), "Test dataset does not exists!"
assert os.path.exists(validate_bin), "Validation dataset does not exists!"
train = BinaryDs(train_bin, read_only=True).open()
train_categories = count_categories(train)
openc = train.is_encoded()
features = train.get_features()
train.close()
val = BinaryDs(validate_bin, read_only=True).open()
val_categories = count_categories(val)
val.close()
test = BinaryDs(test_bin, read_only=True).open()
test_categories = count_categories(test)
test.close()
print(f"Features: {features}")
print(f"Number of classes: {len(train_categories)}")
if openc:
print("Type: opcode encoded")
else:
print("Type: raw values")
print("--------------------")
for i in range(0, len(train_categories)):
print(f"Training examples for class {i}: {train_categories[i]}")
for i in range(0, len(val_categories)):
print(f"Validation examples for class {i}: {val_categories[i]}")
for i in range(0, len(test_categories)):
print(f"Testing examples for class {i}: {test_categories[i]}")
def evaluate_incremental(bs: int, file: str, model_path: str,
test_bin) -> None:
"""
Evaluates the accuracy incrementally (first only 1 feature, then 3, then 5)
:param bs: batch size
:param file: file where to write the accuracy (.csv)
:param model_path: string pointing to the .h5 keras model of the network.
If empty will default to data_dir/model.h5
:param test_bin: path to the test dataset that will be used
"""
cut = 1
test = BinaryDs(test_bin, read_only=True).open()
model = load_model(model_path)
features = test.get_features()
with open(file, "w") as f:
f.write("features,accuracy\n")
while cut <= features:
print(f"Evaluating {cut}")
generator = DataGenerator(test, bs, fake_pad=True, pad_len=cut)
score = model.evaluate(generator)
with open(file, "a") as f:
f.write(f"{cut},{score[1]}\n")
if cut < 24:
cut = cut + 2
elif cut < 80:
cut = cut + 22
elif cut < 256:
cut = cut + 33
elif cut < 500:
cut = cut + 61
elif cut < features:
cut = cut + 129
cut = min(cut, features)
else:
break
test.close()
def test_open_wrong_features_readonly(self):
file = os.path.join(self.tmpdir, "open_wrong_features_readonly.bin")
dataset = BinaryDs(file, features=1024).open()
dataset.close()
with BinaryDs(file, features=2048, read_only=True) as dataset:
self.assertEqual(dataset.get_features(), 1024)