有可能使用tf吗。contrib。量化。用Keras模型创建训练图?

有可能使用 tf.contrib.quantize.create_training_graph 用已经训练过的Keras模型进行模型量化?

据我所知,我可以进口 tf.Graph 来自Keras模型,但我可以在使用 tf。contrib。量化。创建_培训_图表 ?

我能打电话 tf.contrib.quantize.create_training_graph(input_graph=K.get_session().graph, quant_delay=int(0)) 在模型定义和模型加载之后,但得到:

2019-02-22 14:56:24.216742: W tensorflow/c/c_api.cc:686] Operation '{name:'global_average_pooling2d_1_1/Mean' id:3777 op device:{} def:{global_average_pooling2d_1_1/Mean = Mean[T=DT_FLOAT, Tidx=DT_INT32, keep_dims=false](conv2d_15_1/act_quant/FakeQuantWithMinMaxVars:0, global_average_pooling2d_1_1/Mean/reduction_indices)}}' was changed by updating input tensor after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.

至少在转换为keras时,我能够使用uint8权重保存模型->tensorflow->tflite,据我所知,模型和推理的输入仍然是fp32。

converter = tf.contrib.lite.TFLiteConverter.from_frozen_graph(
        graph_def_file='tf_model.pb',
        input_arrays=input_node_names,
        output_arrays=output_node_names)

converter.post_training_quantize = True

tflite_model = converter.convert()

https://github.com/keras-team/keras/issues/11105