我有一个受过MobileNetV2 using FasterRcnn in Tensorflow.培训的应用程序
我用MobileNetv1进行了训练，训练数据和过程相同，效果很好。
我将此page中的预训练模型用于both MobileNetV1 and MobileNetV2.
唯一的问题是，在从预训练模型的检查点训练MobileNetV2时，我无法初始化所有经过微调的变量。带有FasterRCNN的MobileNetV2训练模型需要这些变量。但是它们在预训练模型（all variables from checkpoint are here）中不可用
WARNING:root:Variable [MobilenetV2/expanded_conv_15/expand/biases] is not available in checkpoint
WARNING:root:Variable [MobilenetV2/expanded_conv_15/expand/weights] is not available in checkpoint
WARNING:root:Variable [MobilenetV2/expanded_conv_15/project/biases] is not available in checkpoint
WARNING:root:Variable [MobilenetV2/expanded_conv_16/depthwise/biases] is not available in checkpoint
WARNING:root:Variable [MobilenetV2/expanded_conv_16/expand/biases] is not available in checkpoint
我不能只初始化五个变量，但是为什么结果是如此糟糕。 可能还有其他问题吗？