当前位置: 首页>>代码示例>>Python>>正文


Python tensorpack.InputDesc方法代码示例

本文整理汇总了Python中tensorpack.InputDesc方法的典型用法代码示例。如果您正苦于以下问题:Python tensorpack.InputDesc方法的具体用法?Python tensorpack.InputDesc怎么用?Python tensorpack.InputDesc使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在tensorpack的用法示例。


在下文中一共展示了tensorpack.InputDesc方法的4个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: _get_inputs

# 需要导入模块: import tensorpack [as 别名]
# 或者: from tensorpack import InputDesc [as 别名]
def _get_inputs(self):
        return [InputDesc(self.image_dtype, [None, self.image_shape, self.image_shape, 3], 'input'),
                InputDesc(tf.int32, [None], 'label')] 
开发者ID:qinenergy,项目名称:webvision-2.0-benchmarks,代码行数:5,代码来源:imagenet_utils.py

示例2: _get_inputs

# 需要导入模块: import tensorpack [as 别名]
# 或者: from tensorpack import InputDesc [as 别名]
def _get_inputs(self):
        return [InputDesc(tf.float32, (BATCH_SIZE, IMAGE_WIDTH, IMAGE_HEIGHT, 3), 'input_a'),
                InputDesc(tf.float32, (BATCH_SIZE,), 'score_a'),
                InputDesc(tf.float32, (BATCH_SIZE, IMAGE_WIDTH, IMAGE_HEIGHT, 3), 'input_p'),
                InputDesc(tf.float32, (BATCH_SIZE,), 'score_p'),
                InputDesc(tf.float32, (BATCH_SIZE, IMAGE_WIDTH, IMAGE_HEIGHT, 3), 'input_n'),
                InputDesc(tf.float32, (BATCH_SIZE,), 'score_n')] 
开发者ID:cgtuebingen,项目名称:will-people-like-your-image,代码行数:9,代码来源:resnet50_for_embedding.py

示例3: inputs

# 需要导入模块: import tensorpack [as 别名]
# 或者: from tensorpack import InputDesc [as 别名]
def inputs(self):
        # Use a combined state for efficiency.
        # The first h channels are the current state, and the last h channels are the next state.
        return [InputDesc(tf.uint8,
                          (None,) + self.image_shape + (self.channel + 1,),
                          'comb_state'),
                InputDesc(tf.int64, (None,), 'action'),
                InputDesc(tf.float32, (None,), 'reward'),
                InputDesc(tf.bool, (None,), 'isOver')] 
开发者ID:amiralansary,项目名称:rl-medical,代码行数:11,代码来源:DQNModel.py

示例4: _get_inputs

# 需要导入模块: import tensorpack [as 别名]
# 或者: from tensorpack import InputDesc [as 别名]
def _get_inputs(self):
        # Use a combined state for efficiency.
        # The first h channels are the current state, and the last h channels are the next state.
        return [InputDesc(tf.uint8,
                          (None,) + (self.agents,)+self.image_shape + (self.channel + 1,),
                          'comb_state'),
                InputDesc(tf.int64, (None,self.agents), 'action'),
                InputDesc(tf.float32, (None,self.agents), 'reward'),
                InputDesc(tf.bool, (None,self.agents), 'isOver'),
                ] 
开发者ID:thanosvlo,项目名称:MARL-for-Anatomical-Landmark-Detection,代码行数:12,代码来源:DQNModel.py


注:本文中的tensorpack.InputDesc方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。