使用paddle进行酒店评论的情感分类9——运行结果

(paddle) D:\study_software\vscode\Microsoft VS Code\paddle\homework_sentiment_analysis>python __main__.py
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\ADMINI~1\AppData\Local\Temp\jieba.cache
Loading model cost 0.334 seconds.
Prefix dict has been built successfully.
there are totoally 17285 different words in the corpus
word [oov], its id 0, its word freq 10000000000
word [pad], its id 1, its word freq 10000000000
word 的, its id 2, its word freq 14421
word 了, its id 3, its word freq 5428
word 酒店, its id 4, its word freq 4566
word 是, its id 5, its word freq 4131
word 我, its id 6, its word freq 3541
word 房间, its id 7, its word freq 3158
word 很, its id 8, its word freq 2843
word 也, its id 9, its word freq 2288
word 在, its id 10, its word freq 2207
word 有, its id 11, its word freq 1780
word 不, its id 12, its word freq 1732
word 都, its id 13, its word freq 1725
word 还, its id 14, its word freq 1654
word 没有, its id 15, its word freq 1548
word 服务, its id 16, its word freq 1516
word 住, its id 17, its word freq 1512
word 就, its id 18, its word freq 1498
word 我们, its id 19, its word freq 1371
(array([[[   36],
        [   21],
        [    2],
        [  211],
        [   17],
        [    2],
        [    5],
        [  209],
        [  566],
        [  406],
        [  271],
        [   18],
        [   27],
        [  989],
        [ 1321],
        [   22],
        [  315],
        [ 1248],
        [ 7099],
        [    9],
        [   17],
        [   55],
        [  267],
        [  789],
        [  105],
        [    3],
        [  533],
        [ 1015],
        [  138],
        [  387],
        [   17],
        [    1],
        [    1],
        [    1],
        [    1],
        [    1],
        [    1],
        [    1],
        [    1],
        [    1]],

       [[  325],
        [  447],
        [   30],
        [   20],
        [  161],
        [  672],
        [   28],
        [  179],
        [    6],
        [   10],
        [   23],
        [    2],
        [  202],
        [   58],
        [ 1331],
        [  776],
        [ 4423],
        [   24],
        [ 1985],
        [  840],
        [  175],
        [    4],
        [    2],
        [ 3170],
        [  849],
        [   25],
        [  226],
        [  328],
        [    2],
        [ 1150],
        [   28],
        [  580],
        [11374],
        [  840],
        [  444],
        [  267],
        [  135],
        [  238],
        [   11],
        [ 3775]],

       [[  356],
        [    6],
        [  258],
        [  296],
        [   43],
        [  132],
        [   48],
        [    5],
        [    6],
        [  137],
        [ 7984],
        [    2],
        [  282],
        [   37],
        [  263],
        [    2],
        [    4],
        [   10],
        [  776],
        [  159],
        [ 1011],
        [  840],
        [    2],
        [ 2150],
        [  133],
        [   12],
        [  255],
        [  135],
        [   53],
        [   35],
        [    4],
        [    2],
        [  661],
        [  762],
        [ 3330],
        [  661],
        [  239],
        [ 3937],
        [    6],
        [   12]]], dtype=int64), array([[1],
       [1],
       [0]], dtype=int64))
W0803 11:52:42.684672 11268 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.9, Driver API Version: 12.2, Runtime API Version: 11.7
W0803 11:52:43.023296 11268 gpu_resources.cc:149] device: 0, cuDNN Version: 8.4.
I0803 11:52:45.736480 11268 eager_method.cc:140] Warning:: 0D Tensor cannot be used as 'Tensor.numpy()[0]' . In order to avoid this problem, 0D Tensor will be changed to 1D numpy currently, but it's not correct and will be removed in release 2.6. For Tensor contain only one element, Please modify  'Tensor.numpy()[0]' to 'float(Tensor)' as soon as possible, otherwise 'Tensor.numpy()[0]' will raise error in release 2.6.
I0803 11:52:45.741479 11268 eager_method.cc:140] Warning:: 0D Tensor cannot be used as 'Tensor.numpy()[0]' . In order to avoid this problem, 0D Tensor will be changed to 1D numpy currently, but it's not correct and will be removed in release 2.6. For Tensor contain only one element, Please modify  'Tensor.numpy()[0]' to 'float(Tensor)' as soon as possible, otherwise 'Tensor.numpy()[0]' will raise error in release 2.6.
step 0, loss 0.692
I0803 11:52:48.154095 11268 eager_method.cc:140] Warning:: 0D Tensor cannot be used as 'Tensor.numpy()[0]' . In order to avoid this problem, 0D Tensor will be changed to 1D numpy currently, but it's not correct and will be removed in release 2.6. For Tensor contain only one element, Please modify  'Tensor.numpy()[0]' to 'float(Tensor)' as soon as possible, otherwise 'Tensor.numpy()[0]' will raise error in release 2.6.
I0803 11:52:48.159094 11268 eager_method.cc:140] Warning:: 0D Tensor cannot be used as 'Tensor.numpy()[0]' . In order to avoid this problem, 0D Tensor will be changed to 1D numpy currently, but it's not correct and will be removed in release 2.6. For Tensor contain only one element, Please modify  'Tensor.numpy()[0]' to 'float(Tensor)' as soon as possible, otherwise 'Tensor.numpy()[0]' will raise error in release 2.6.
step 100, loss 0.681
TP: 226
FP: 196
TN: 64
FN: 26

Accuracy: 0.5664

准确率挺低，远低于预期，要么是网络参数问题要么是数据集问题，准备先筛一遍数据集，再调网络参数