def main():
audio_path_label_pairs = load_audio_path_label_pairs()
print('loaded: ', len(audio_path_label_pairs))
classifier = Cifar10AudioClassifier(model_ctx=mxnet.gpu(0),
data_ctx=mxnet.gpu(0))
batch_size = 8
epochs = 100
history = classifier.fit(audio_path_label_pairs,
model_dir_path='./models',
batch_size=batch_size,
epochs=epochs,
checkpoint_interval=2)
def main():
audio_path_label_pairs = load_audio_path_label_pairs()
shuffle(audio_path_label_pairs)
print('loaded: ', len(audio_path_label_pairs))
classifier = Cifar10AudioClassifier()
classifier.load_model(model_dir_path='./models')
for i in range(0, 20):
audio_path, actual_label_id = audio_path_label_pairs[i]
predicted_label_id = classifier.predict_class(audio_path)
print(audio_path)
predicted_label = gtzan_labels[predicted_label_id]
actual_label = gtzan_labels[actual_label_id]
print('predicted: ', predicted_label, 'actual: ', actual_label)
def main():
sys.path.append(patch_path('..'))
audio_path_label_pairs = load_audio_path_label_pairs()
print('loaded: ', len(audio_path_label_pairs))
from mxnet_audio.library.cifar10 import Cifar10AudioClassifier
classifier = Cifar10AudioClassifier(model_ctx=mxnet.gpu(0),
data_ctx=mxnet.gpu(0))
batch_size = 8
epochs = 100
history = classifier.fit(audio_path_label_pairs,
model_dir_path=patch_path('models'),
batch_size=batch_size,
epochs=epochs,
checkpoint_interval=2)
def main():
sys.path.append(patch_path('..'))
audio_path_label_pairs = load_audio_path_label_pairs()
shuffle(audio_path_label_pairs)
print('loaded: ', len(audio_path_label_pairs))
from mxnet_audio.library.cifar10 import Cifar10AudioClassifier
classifier = Cifar10AudioClassifier()
classifier.load_model(model_dir_path=patch_path('models'))
for i in range(0, 20):
audio_path, actual_label_id = audio_path_label_pairs[i]
audio2vec = classifier.encode_audio(audio_path)
print(audio_path)
print('audio-to-vec: ', audio2vec)
def main():
sys.path.append(patch_path(".."))
audio_path_label_pairs = load_audio_path_label_pairs()
shuffle(audio_path_label_pairs)
print("loaded: ", len(audio_path_label_pairs))
from mxnet_audio.library.cifar10 import Cifar10AudioClassifier
from mxnet_audio.library.utility.gtzan_loader import gtzan_labels
classifier = Cifar10AudioClassifier()
classifier.load_model(model_dir_path=patch_path("models"))
for i in range(0, 20):
audio_path, actual_label_id = audio_path_label_pairs[i]
predicted_label_id = classifier.predict_class(audio_path)
print(audio_path)
predicted_label = gtzan_labels[predicted_label_id]
actual_label = gtzan_labels[actual_label_id]
print("predicted: ", predicted_label, "actual: ", actual_label)