Python 基于不同数据维的评价模型
我有形状Python 基于不同数据维的评价模型,python,tensorflow,keras,Python,Tensorflow,Keras,我有形状(37520,32,9)的数据,有五类形状(37520,5),我正在使用Conv1D训练模型,到目前为止我能够训练数据。但问题是,我需要在不同的维度上对其求值-(37520,32,4)(类是相同的),我得到以下错误: Traceback (most recent call last): File "data_maker_cnn_multiuser_folds_correct.py", line 870, in <module> f = run_cnn(a) F
(37520,32,9)
的数据,有五类形状(37520,5)
,我正在使用Conv1D训练模型,到目前为止我能够训练数据。但问题是,我需要在不同的维度上对其求值-(37520,32,4)
(类是相同的),我得到以下错误:
Traceback (most recent call last):
File "data_maker_cnn_multiuser_folds_correct.py", line 870, in <module>
f = run_cnn(a)
File "data_maker_cnn_multiuser_folds_correct.py", line 155, in run_cnn
_, accuracy = model.evaluate(x_test, y_test, batch_size=batch_size, verbose=verbose)
File "/Users/akshayrajgollahalli/miniconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 930, in evaluate
use_multiprocessing=use_multiprocessing)
File "/Users/akshayrajgollahalli/miniconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 490, in evaluate
use_multiprocessing=use_multiprocessing, **kwargs)
File "/Users/akshayrajgollahalli/miniconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 426, in _model_iteration
use_multiprocessing=use_multiprocessing)
File "/Users/akshayrajgollahalli/miniconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 646, in _process_inputs
x, y, sample_weight=sample_weights)
File "/Users/akshayrajgollahalli/miniconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 2383, in _standardize_user_data
batch_size=batch_size)
File "/Users/akshayrajgollahalli/miniconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 2410, in _standardize_tensors
exception_prefix='input')
File "/Users/akshayrajgollahalli/miniconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_utils.py", line 582, in standardize_input_data
str(data_shape))
ValueError: Error when checking input: expected conv1d_input to have shape (32, 9) but got array with shape (32, 4)
甚至有可能做到这一点吗?我也尝试过使用预测,但仍然有一个错误。模型需要有以下参数才能固定,以便对其进行训练、评估和预测
- 模型中所有图层的名称和类型
- 输出每个层的形状
- 每层的权重参数数
- 每层接收的输入
- 模型的可训练和不可训练参数的总数
(32,9)
截断为(32,4)
,然后重新训练。然而,信息将会丢失。培训后,您的评估和预测将使用(32,4)
数据。但同样,如果您试图使用原始输入大小进行评估或预测,则它将不起作用
希望这能回答你的问题。愉快的学习。我认为这是不可能的。你可以用零来填充它,但你可能不会有好的表现。我尝试过,但效果很差。请提供完整的可复制代码。@Akshay-希望我们已经回答了您的问题。如果你对答案感到满意,请接受并投票。