尝试应用非函数错误，keras_predict

如何解决尝试应用非函数错误，keras_predict

我正在关注 Emil Hvitfeldt 和 Julia Silge 编写的用于 R 中文本的出色 SML 教程。

此处的数据：https://www.kaggle.com/oscarvilla/kickstarter-nlp

此处的代码：https://smltar.com/dllstm.html#compare-to-a-recurrent-neural-network

正在研究第 9.2 章和第 9.3 章，但在比较模型时我一直遇到以下错误：

bilstm_res <- keras_predict(bilstm_mod,kick_assess,state_assess)
Error in modules$np$int32(x) : attempt to apply non-function

之前和之后的一切都运行良好，但这种比较在任一部分（9.2 或 9.3）中都不起作用。

会话信息：

R version 4.0.4 (2021-02-15)
Platform: x86_64-apple-darwin17.0 (64-bit)
Running under: macOS Big Sur 10.16

Matrix products: default
LAPACK: /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRlapack.dylib

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] stats     graphics  Grdevices utils     datasets  methods   base     

other attached packages:
 [1] reticulate_1.18   kerasR_0.6.1      keras_2.3.0.0     textrecipes_0.4.0 yardstick_0.0.7  
 [6] workflows_0.2.1   tune_0.1.2        rsample_0.0.9     recipes_0.1.15    parsnip_0.1.5    
[11] modeldata_0.1.0   infer_0.5.4       dials_0.0.9       scales_1.1.1      broom_0.7.5      
[16] tidymodels_0.1.2  forcats_0.5.1     stringr_1.4.0     dplyr_1.0.4       purrr_0.3.4      
[21] readr_1.4.0       tidyr_1.1.2       tibble_3.0.6      ggplot2_3.3.3     tidyverse_1.3.0  

loaded via a namespace (and not attached):
 [1] nlme_3.1-152       fs_1.5.0           lubridate_1.7.9.2  DiceDesign_1.9     httr_1.4.2        
 [6] snowballC_0.7.0    tools_4.0.4        backports_1.2.1    utf8_1.1.4         R6_2.5.0          
[11] rpart_4.1-15       DBI_1.1.1          mgcv_1.8-34        colorspace_2.0-0   nnet_7.3-15       
[16] withr_2.4.1        tidyselect_1.1.0   compiler_4.0.4     cli_2.3.0          rvest_0.3.6       
[21] xml2_1.3.2         labeling_0.4.2     tfruns_1.4         digest_0.6.27      base64enc_0.1-3   
[26] pkgconfig_2.0.3    parallelly_1.23.0  lhs_1.1.1          dbplyr_2.1.0       rlang_0.4.10      
[31] readxl_1.3.1       rstudioapi_0.13    farver_2.0.3       generics_0.1.0     jsonlite_1.7.2    
[36] tensorflow_2.2.0   tokenizers_0.2.1   magrittr_2.0.1     Matrix_1.3-2       GPfit_1.0-8       
[41] Rcpp_1.0.6         munsell_0.5.0      fansi_0.4.2        lifecycle_1.0.0    furrr_0.2.2       
[46] pROC_1.17.0.1      stringi_1.5.3      whisker_0.4        MASS_7.3-53.1      plyr_1.8.6        
[51] grid_4.0.4         parallel_4.0.4     listenv_0.8.0      Crayon_1.4.1       lattice_0.20-41   
[56] haven_2.3.1        splines_4.0.4      hms_1.0.0          zeallot_0.1.0      pillar_1.5.0      
[61] codetools_0.2-18   reprex_1.0.0       glue_1.4.2         modelr_0.1.8       foreach_1.5.1     
[66] vctrs_0.3.6        cellranger_1.1.0   gtable_0.3.0       future_1.21.0      assertthat_0.2.1  
[71] gower_0.2.2        prodlim_2019.11.13 class_7.3-18       survival_3.2-7     timeDate_3043.102 
[76] iterators_1.0.13   lava_1.6.8.1       globals_0.14.0     ellipsis_0.3.1     ipred_0.9-9

谁能告诉我我可能做错了什么？