如果标签以数值形式给出，模型推理结果以概率形式给出，则model.compile()函数中metrics参数应选择哪一项？
A: ‘sparse_categorical_crossentropy’
B: ‘accuracy’
C: ‘categorical_accuracy’
D: ‘sparse_ categorical_accuracy’
A: ‘sparse_categorical_crossentropy’
B: ‘accuracy’
C: ‘categorical_accuracy’
D: ‘sparse_ categorical_accuracy’
举一反三
- 中国大学MOOC: 如果标签以数值形式给出，模型推理结果以概率形式给出，则model.compile()函数中metrics参数应选择哪一项？
- 编译模型时用了以下代码：model.compile（optimizer=’Adam，loss=’categorical.crossentropy’，metrics=[tf.keras.metrics.accuracy]），在使用evaluate方法评估模型时，会输出以下哪些指标？（） A: accuracy B: categorical_1oss C: loss D: categoricalaccuracy
- What are the three parts a categorical syllogismconsists of:
- The best type of chart for comparing two sets of categorical data is:
- Nominal (categorical) data may be treated as ordinal or numerical (quantitative).