Estou tentando usar o fit para treinar uma CNN mas esta com mensagem de erro:
Error in py_call_impl(callable, dots$args, dots$keywords) :
ValueError: in user code:
File “C:\Users\Rubens\AppData\Local\r-miniconda\envs\r-reticulate\lib\site-packages\keras\engine\training.py”, line 878, in train_function *
return step_function(self, iterator)
File “C:\Users\Rubens\AppData\Local\r-miniconda\envs\r-reticulate\lib\site-packages\keras\engine\training.py”, line 867, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File “C:\Users\Rubens\AppData\Local\r-miniconda\envs\r-reticulate\lib\site-packages\keras\engine\training.py”, line 860, in run_step **
outputs = model.train_step(data)
File “C:\Users\Rubens\AppData\Local\r-miniconda\envs\r-reticulate\lib\site-packages\keras\engine\training.py”, line 810, in train_step
y, y_pred, sample_weight, regularization_losses=self.losses)
File “C:\Users\Rubens\AppData\Local\r-miniconda\envs\r-reticulate\lib\site-packages\keras\engine\compile_utils.py”, line 201, in call
loss_value = lo
a base utilizada é a de treino que esta no link:
Este é o modelo e as definições:
base de dados
path ← “C:/Users/Rubens/Desktop/Curso_r/deep_learning/projeto/Training/”
dataset ← image_dataset_from_directory(path, image_size = c(128,128), color_mode = “rgb”)
DEFININDO O MODELO
input ← layer_input(shape = c(128, 128, 3))
output ← input %>%
layer_conv_2d(kernel_size = c(3,3), filters = 32,
activation = “relu”, padding = “same”, use_bias = FALSE) %>%
layer_max_pooling_2d(pool_size = c(2,2)) %>%
layer_flatten() %>%
layer_dense(units = 250, activation = “relu”) %>%
layer_dense(units = 125, activation = “relu”) %>%
layer_dense(units = 62, activation = “relu”) %>%
layer_dense(units = 31, activation = “relu”) %>%
layer_dense(units = 15, activation = “relu”) %>%
layer_dense(units = 4, activation = “softmax”)
model ← keras_model(input, output)
summary(model)
model %>%
compile(
loss = “categorical_crossentropy”,
optimizer = optimizer_sgd(),
metrics = “acc”
)
Model fitting ------------------------------------------------
model %>%
fit(dataset)
Pelo que pesquisei é diferença do tamanho do dataset com o input do modelo, porém ambos estão do mesmo tamanho (128 x 128 e 3 canais)