I am having a problem when running a Convolutional Neural Network using Quanteda Classifiers. I try to replicate the analysis from the vignette, and I get the following result after running pred <- predict(tmod, newdata = newdata):
Error: AttributeError: 'Sequential' object has no attribute 'predict_classes'
In addition: Warning message:
In predict_classes(object$clefitted, x = data$matrix) :
predict_classes() is deprecated and and was removed from tensorflow in version 2.6.
Please update your code:
If your model does multi-class classification:
(e.g. if it uses a softmax last-layer activation). model %>% predict(x) %>% k_argmax()
if your model does binary classification
(e.g. if it uses a sigmoid last-layer activation). model %>% predict(x) %>% >(0.5) %>% k_cast("int32")
However, when I try to use model %>% predict(x) %>% k_argmax() or model %>% predict(x) %>% >(0.5) %>% k_cast("int32") I get the same result.
I know this is related to the version of TensorFlow, but I don't know how to fix it to get the code running.
I am having a problem when running a Convolutional Neural Network using Quanteda Classifiers. I try to replicate the analysis from the vignette, and I get the following result after running
pred <- predict(tmod, newdata = newdata)
:However, when I try to use model %>% predict(x) %>% k_argmax() or model %>% predict(x) %>%
>
(0.5) %>% k_cast("int32") I get the same result.I know this is related to the version of TensorFlow, but I don't know how to fix it to get the code running.