用xDeepFM和DeepFM模型，结果几乎一样，甚至稍低

[ArtificialZeng]

Use tf.where in 2.0, which has the same broadcast rule as np.where Train on 6129770 samples, validate on 1532443 samples 2022-07-14 16:28:09.045936: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 Epoch 1/10 6129770/6129770 - 149s - loss: 0.1881 - binary_crossentropy: 0.1858 - val_loss: 0.1871 - val_binary_crossentropy: 0.1841 Epoch 2/10 6129770/6129770 - 157s - loss: 0.1860 - binary_crossentropy: 0.1828 - val_loss: 0.1863 - val_binary_crossentropy: 0.1832 Epoch 3/10 6129770/6129770 - 158s - loss: 0.1856 - binary_crossentropy: 0.1823 - val_loss: 0.1860 - val_binary_crossentropy: 0.1829 Epoch 4/10 6129770/6129770 - 160s - loss: 0.1854 - binary_crossentropy: 0.1821 - val_loss: 0.1858 - val_binary_crossentropy: 0.1825 Epoch 5/10 6129770/6129770 - 158s - loss: 0.1853 - binary_crossentropy: 0.1819 - val_loss: 0.1858 - val_binary_crossentropy: 0.1824 Epoch 6/10 6129770/6129770 - 158s - loss: 0.1852 - binary_crossentropy: 0.1817 - val_loss: 0.1856 - val_binary_crossentropy: 0.1822 Epoch 7/10 6129770/6129770 - 143s - loss: 0.1851 - binary_crossentropy: 0.1815 - val_loss: 0.1856 - val_binary_crossentropy: 0.1821 Epoch 8/10 6129770/6129770 - 161s - loss: 0.1849 - binary_crossentropy: 0.1814 - val_loss: 0.1855 - val_binary_crossentropy: 0.1820 Epoch 9/10 6129770/6129770 - 158s - loss: 0.1848 - binary_crossentropy: 0.1812 - val_loss: 0.1855 - val_binary_crossentropy: 0.1820 Epoch 10/10 6129770/6129770 - 149s - loss: 0.1848 - binary_crossentropy: 0.1811 - val_loss: 0.1854 - val_binary_crossentropy: 0.1820 test LogLoss 0.1821 test AUC 0.6954 训练完毕... deepFM训练耗时：1593.168582201004s

Process finished with exit code 0

Please refer to the FAQ in doc and search for the related issues before you ask the question.

Describe the question(问题描述) A clear and concise description of what the question is.

Additional context Add any other context about the problem here.

Operating environment(运行环境):

• python version [e.g. 3.6]
• tensorflow version [e.g. 1.4.0, 1.15.0, 2.5.0]
• deepctr version [e.g. 0.9.0,]

[zanshuxun]

有谁告诉你xDeepFM在任何数据上都一定比DeepFM效果好吗