def main():
"""Entrypoint for test_converter"""
parser = argparse.ArgumentParser(description='Test Caffe converter')
parser.add_argument('--cpu', action='store_true', help='use cpu?')
parser.add_argument('--image_url', type=str,
default='https://github.com/dmlc/web-data/raw/master/mxnet/doc/'\
'tutorials/python/predict_image/cat.jpg',
help='input image to test inference, can be either file path or url')
args = parser.parse_args()
if args.cpu:
gpus = [-1]
default_batch_size = 32
else:
num_gpus = mx.context.num_gpus()
assert num_gpus, 'At least one GPU is needed to run test_converter in GPU mode'
default_batch_size = 32 * num_gpus
models = ['bvlc_googlenet', 'vgg-16', 'resnet-50']
val = download_data()
for m in models:
test_model_weights_and_outputs(m, args.image_url, gpus[0])
# Build/testing machines tend to be short on GPU memory
this_batch_size = default_batch_size / 4 if m == 'vgg-16' else default_batch_size
test_imagenet_model_performance(m, val, gpus, this_batch_size)
def main():
"""Entrypoint for test_converter"""
parser = argparse.ArgumentParser(description='Test Caffe converter')
parser.add_argument('--cpu', action='store_true', help='use cpu?')
parser.add_argument('--image_url', type=str,
default='https://github.com/dmlc/web-data/raw/master/mxnet/doc/'\
'tutorials/python/predict_image/cat.jpg',
help='input image to test inference, can be either file path or url')
args = parser.parse_args()
if args.cpu:
gpus = [-1]
default_batch_size = 32
else:
gpus = mx.test_utils.list_gpus()
assert gpus, 'At least one GPU is needed to run test_converter in GPU mode'
default_batch_size = 32 * len(gpus)
models = ['bvlc_googlenet', 'vgg-16', 'resnet-50']
val = download_data()
for m in models:
test_model_weights_and_outputs(m, args.image_url, gpus[0])
# Build/testing machines tend to be short on GPU memory
this_batch_size = default_batch_size / 4 if m == 'vgg-16' else default_batch_size
test_imagenet_model_performance(m, val, gpus, this_batch_size)
def main():
"""Entrypoint for test_converter"""
parser = argparse.ArgumentParser(description='Test Caffe converter')
parser.add_argument('--cpu', action='store_true', help='use cpu?')
parser.add_argument(
'--image_url',
type=str,
default=
'http://writm.com/wp-content/uploads/2016/08/Cat-hd-wallpapers.jpg',
help='input image to test inference, can be either file path or url')
args = parser.parse_args()
if args.cpu:
gpus = [-1]
batch_size = 32
else:
gpus = mx.test_utils.list_gpus()
assert gpus, 'At least one GPU is needed to run test_converter in GPU mode'
batch_size = 32 * len(gpus)
models = ['bvlc_googlenet']
val = download_data()
for m in models:
test_model_weights_and_outputs(m, args.image_url, gpus[0])
test_imagenet_model_performance(m, val, gpus, batch_size)
def main():
gpus = mx.test_utils.list_gpus()
assert len(gpus) > 0
batch_size = 32 * len(gpus)
models = ['bvlc_googlenet', 'vgg-16', 'resnet-50']
val = download_data()
for m in models:
test_imagenet_model(m, val, ','.join([str(i) for i in gpus]), batch_size)
def main():
"""Entrypoint for test_converter"""
parser = argparse.ArgumentParser(description='Test Caffe converter')
parser.add_argument('--cpu', action='store_true', help='use cpu?')
args = parser.parse_args()
if args.cpu:
gpus = ''
batch_size = 32
else:
gpus = mx.test_utils.list_gpus()
assert gpus, 'At least one GPU is needed to run test_converter in GPU mode'
batch_size = 32 * len(gpus)
models = ['bvlc_googlenet', 'vgg-16', 'resnet-50']
val = download_data()
for m in models:
test_imagenet_model(m, val, ','.join([str(i) for i in gpus]),
batch_size)
def main():
"""Entrypoint for test_converter"""
parser = argparse.ArgumentParser(description='Test Caffe converter')
parser.add_argument('--cpu', action='store_true', help='use cpu?')
parser.add_argument('--image_url', type=str,
default='http://writm.com/wp-content/uploads/2016/08/Cat-hd-wallpapers.jpg',
help='input image to test inference, can be either file path or url')
args = parser.parse_args()
if args.cpu:
gpus = [-1]
batch_size = 32
else:
gpus = mx.test_utils.list_gpus()
assert gpus, 'At least one GPU is needed to run test_converter in GPU mode'
batch_size = 32 * len(gpus)
models = ['bvlc_googlenet', 'vgg-16', 'resnet-50']
val = download_data()
for m in models:
test_model_weights_and_outputs(m, args.image_url, gpus[0])
test_imagenet_model_performance(m, val, gpus, batch_size)
mean_args = {'mean_img': mean}
else:
mean_args = {'rgb_mean': ','.join([str(i) for i in mean])}
(speed, ) = score(model=(sym, arg_params, aux_params),
data_val=val,
label_name='prob_label',
metrics=acc,
gpus=gpus,
batch_size=batch_size,
max_num_examples=500,
**mean_args)
logging.info('speed : %f image/sec', speed)
for a in acc:
logging.info(a.get())
assert acc[0].get()[1] > meta_info['top-1-acc'] - 0.3
assert acc[1].get()[1] > meta_info['top-5-acc'] - 0.3
if __name__ == '__main__':
gpus = mx.test_utils.list_gpus()
assert len(gpus) > 0
batch_size = 32 * len(gpus)
models = ['bvlc_googlenet', 'vgg-16', 'resnet-50']
val = download_data()
for m in models:
test_imagenet_model(m, val, ','.join([str(i) for i in gpus]),
batch_size)
acc = [mx.metric.create('acc'), mx.metric.create('top_k_accuracy', top_k = 5)]
if isinstance(mean, str):
mean_args = {'mean_img':mean}
else:
mean_args = {'rgb_mean':','.join([str(i) for i in mean])}
(speed,) = score(model=(sym, arg_params, aux_params),
data_val=val,
label_name = 'prob_label',
metrics=acc,
gpus=gpus,
batch_size=batch_size,
max_num_examples=500,
**mean_args)
logging.info('speed : %f image/sec', speed)
for a in acc:
logging.info(a.get())
assert acc[0].get()[1] > meta_info['top-1-acc'] - 0.3
assert acc[1].get()[1] > meta_info['top-5-acc'] - 0.3
if __name__ == '__main__':
gpus = mx.test_utils.list_gpus()
assert len(gpus) > 0
batch_size = 32 * len(gpus)
models = ['bvlc_googlenet', 'vgg-16', 'resnet-50']
val = download_data()
for m in models:
test_imagenet_model(m, val, ','.join([str(i) for i in gpus]), batch_size)