将DeepLab转换为TensorFlow Lite
我正在尝试将在Cityscapes数据集上训练的DeepLab从这里转换为TFLite。在Netron中查看冻结图时，输入和输出张量均为uint8类型。我能够使用为TFLite GPU委托提供的默认DeepLab模型，该模型具有float32输入和输出张量。我认为模型不应该被量化，所以当尝试以下没有注释行的代码时，我得到了这个错误：将DeepLab转换为TensorFlow Lite,tensorflow,tensorflow-lite,Tensorflow,Tensorflow Lite,我正在尝试将在Cityscapes数据集上训练的DeepLab从这里转换为TFLite。在Netron中查看冻结图时，输入和输出张量均为uint8类型。我能够使用为TFLite GPU委托提供的默认DeepLab模型，该模型具有float32输入和输出张量。我认为模型不应该被量化，所以当尝试以下没有注释行的代码时，我得到了这个错误： F tensorflow/lite/toco/tooling_util.cc:2241] Check failed: array.data_type == arra
F tensorflow/lite/toco/tooling_util.cc:2241] Check failed: array.data_type == array.final_data_type Array "ImageTensor" has mis-matching actual and final data types (data_type=uint8, final_data_type=float).
F ./tensorflow/lite/toco/toco_tooling.h:38] Check failed: s.ok() Unimplemented: this graph contains anoperator of type Cast for which the quantized form is not yet implemented. Sorry, and patches welcome (that's a relatively fun patch to write, mostly providing the actual quantized arithmetic code for this op).