Question

构建模型后出现以下错误（完全按照教程进行，但将其应用于我自己的数据集。

这里有模型和我遇到的错误。（重新应用代码时遇到第二个错误）。

我有5个类别变量，我想尝试训练一些文本数据以将自身分类为5个类别中的1个。

代码和错误：

> maxlen
[1] 1000
> embedding_dim
[1] 300
> max_words
[1] 15000

> embedding_dim <- 300
> 
> model <- keras_model_sequential() %>% 
+   layer_embedding(input_dim = max_words, output_dim = embedding_dim, 
+                   input_length = maxlen) %>% 
+   layer_flatten() %>% 
+   layer_dense(units = 8, activation = "relu") %>% 
+   layer_dropout(0.4) %>%
+   layer_dense(units = 5, activation = "softmax")
> 
> model %>% compile(
+   optimizer = "rmsprop",
+   loss = "categorical_crossentropy",
+   metrics = c("accuracy")
+ )
> 
> history <- model %>% fit(
+   x_train, to_categorical(y_train),
+   epochs = 20,
+   batch_size = 32,
+   validation_data = list(x_val, to_categorical(y_val))
+ )
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
WARNING: Logging before flag parsing goes to stderr.
W0730 19:41:13.310763 140518437951872 lazy_loader.py:50] 
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
  * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
  * https://github.com/tensorflow/addons
  * https://github.com/tensorflow/io (for I/O related ops)
If you depend on functionality not listed there, please file an issue.

Error in py_call_impl(callable, dots$args, dots$keywords) : 
  ValueError: cannot convert float NaN to integer

Detailed traceback: 
  File "/data/users/USER/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/keras/utils/np_utils.py", line 40, in to_categorical
    y = np.array(y, dtype='int')

当我重新运行模型时

> model <- keras_model_sequential() %>% 
+   layer_embedding(input_dim = max_words, output_dim = embedding_dim, 
+                   input_length = maxlen) %>% 
+   layer_flatten() %>% 
+   layer_dense(units = 8, activation = "relu") %>% 
+   layer_dropout(0.4) %>%
+   layer_dense(units = 5, activation = "softmax")
> model %>% compile(
+   optimizer = "rmsprop",
+   loss = "categorical_crossentropy",
+   metrics = c("accuracy")
+ )
> history <- model %>% fit(
+   x_train, to_categorical(y_train),
+   epochs = 20,
+   batch_size = 32,
+   validation_data = list(x_val, to_categorical(y_val))
+ )
Error in py_call_impl(callable, dots$args, dots$keywords) : 
  ValueError: cannot convert float NaN to integer

Detailed traceback: 
  File "/data/users/msmith/.virtualenvs/r-reticulate/lib64/python3.6/site-packages/tensorflow/python/keras/utils/np_utils.py", line 40, in to_categorical
    y = np.array(y, dtype='int')

Answer 1

当y包含任何NA值时，我也会遇到相同的错误。您需要确保y和y_train不包含任何NA值。

keras::to_categorical(c(1, NA))
#> Error in py_call_impl(callable, dots$args, dots$keywords): ValueError: cannot convert float NaN to integer
#> 
#> Detailed traceback: 
#>   File "/Users/dfalbel/.virtualenvs/r-reticulate/lib/python2.7/site-packages/tensorflow/python/keras/utils/np_utils.py", line 40, in to_categorical
#>     y = np.array(y, dtype='int')

^{由reprex package（v0.3.0）于2019-07-31创建}

keras错误py_call_impl（可调用，点$ args，点$关键字）

1 个答案: