未验证 提交 e3663d26 编写于 作者: Z zhouzj 提交者: GitHub

To avoid out of memory, the batch size is down to 128. (#865)

上级 9058dc2c
......@@ -44,7 +44,7 @@ _logger = get_logger(__name__, level=logging.INFO)
parser = argparse.ArgumentParser(description=__doc__)
add_arg = functools.partial(add_arguments, argparser=parser)
# yapf: disable
add_arg('batch_size', int, 256, "Single Card Minibatch size.")
add_arg('batch_size', int, 128, "Single Card Minibatch size.")
add_arg('use_gpu', bool, True, "Whether to use GPU or not.")
add_arg('model', str, "mobilenet_v3", "The target model.")
add_arg('pretrained_model', str, "MobileNetV3_large_x1_0_ssld_pretrained", "Whether to use pretrained model.")
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册