Stat. 654 Quiz keras

Author

Your Name Here

Feed-Forward Neural Network for the Google Tensorflow Playground XOR Data

Clone the TFPlayground Github repository into your R Project folder.

To clone the repository you can use RStudio

File > New Project > Version Control > Git

and paste the URL of the repository into the Git Repository URL box. Then select a folder to clone the repository into.

Click the Green button and copy the ulr: https://github.com/hyounesy/TFPlaygroundPSA.git

Then paste the URL into the Git Repository URL box. Select a folder to clone the repository into. Click the Create Project button.

Use the data in ../data/tiny/xor_25/input.txt to create a feed-forward neural network to classify the data. Use the keras package to create the model.

Load the required libraries

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
✔ purrr     1.0.4     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(tidymodels)

── Attaching packages ────────────────────────────────────── tidymodels 1.3.0 ──
✔ broom        1.0.7          ✔ rsample      1.2.1.9000
✔ dials        1.4.0.9000     ✔ tune         1.3.0.9000
✔ infer        1.0.7          ✔ workflows    1.2.0.9000
✔ modeldata    1.4.0          ✔ workflowsets 1.1.0     
✔ parsnip      1.3.0.9000     ✔ yardstick    1.3.2     
✔ recipes      1.1.1.9000     
── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
✖ scales::discard() masks purrr::discard()
✖ dplyr::filter()   masks stats::filter()
✖ recipes::fixed()  masks stringr::fixed()
✖ dplyr::lag()      masks stats::lag()
✖ yardstick::spec() masks readr::spec()
✖ recipes::step()   masks stats::step()

library(readr)
library(janitor)


Attaching package: 'janitor'

The following objects are masked from 'package:stats':

    chisq.test, fisher.test

library(forcats)
library(keras)


Attaching package: 'keras'

The following object is masked from 'package:yardstick':

    get_weights

Load the data

input <- read_delim("data/tiny/xor_25/input.txt", 
     delim = "\t", escape_double = FALSE, 
     trim_ws = TRUE)

Rows: 200 Columns: 9
── Column specification ────────────────────────────────────────────────────────
Delimiter: "\t"
dbl (9): pid, X1, X2, X1Squared, X2Squared, X1X2, sinX1, sinX2, label

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

input <- input |> 
  clean_names() |> 
  mutate(label = if_else(label == -1, 0, 1) ) |>   # or use 0L, !L
  mutate(label = as.integer(label)) |>
  tibble()

head(input)

# A tibble: 6 × 9
    pid    x1     x2 x1squared x2squared  x1x2 sin_x1 sin_x2 label
  <dbl> <dbl>  <dbl>     <dbl>     <dbl> <dbl>  <dbl>  <dbl> <int>
1     0 -2.82  2.52       7.96     6.33  -7.10 -0.314  0.586     0
2     1  3.49  1.19      12.2      1.43   4.17 -0.342  0.930     1
3     2 -3.78 -2.68      14.3      7.20  10.1   0.592 -0.442     1
4     3  2.22  4.14       4.92    17.1    9.18  0.798 -0.841     1
5     4  3.64  0.970     13.2      0.941  3.53 -0.474  0.825     1
6     5  2.22  0.788      4.95     0.621  1.75  0.794  0.709     1

Split the data into training and testing sets

n <- nrow(input)

input_parts <- input |>
  initial_split(prop = 0.8)

train <- input_parts |>
  training()

test <- input_parts |>
  testing()

list(train, test) |>
  map_int(nrow)

[1] 160  40

Visualize the data

train |> 
  ggplot(aes(x = x1, y = x2, color = factor(label))) +
  geom_point()

test |> 
  ggplot(aes(x = x1, y = x2, color = factor(label))) +
  geom_point()

Using keras and tensorflow

Note that the functions in the keras package are expecting the data to be in a matrix object and not a tibble. So as.matrix is added at the end of each line.

Do not forget to remove the ID variable pid.

x_train <- train %>% select(-pid, -label) |> select(x1, x2) |> as.matrix()
y_train <- train %>% select(label) %>% as.matrix() %>% to_categorical() 

x_test <- test %>% select(-pid, -label) |> select(x1, x2) |> as.matrix()
y_test <- test %>% select(label) %>% as.matrix() %>% to_categorical() 

dim(x_train)

[1] 160   2

dim(x_test)

[1] 40  2

dim(y_train)

[1] 160   2

dim(y_test)

[1] 40  2

Set Architecture

With the data in place, we now set the architecture of our neural network.

keras activation

model <- keras_model_sequential()
model |>  
  layer_dense(units = 4, activation = 'relu', input_shape = 2) |> 
  layer_dense(units = 2, activation = 'softmax')
model |> summary()

Model: "sequential"
________________________________________________________________________________
 Layer (type)                       Output Shape                    Param #     
================================================================================
 dense_1 (Dense)                    (None, 4)                       12          
 dense (Dense)                      (None, 2)                       10          
================================================================================
Total params: 22
Trainable params: 22
Non-trainable params: 0
________________________________________________________________________________

Next, the architecture set in the model needs to be compiled.

model %>% compile(
  optimizer = "rmsprop",
  loss = "binary_crossentropy",
  metrics = "accuracy"
)

Train the Artificial Neural Network

Lastly we fit the model and save the training progress in the history object.

Try changing the validation_split from 0 to 0.2 to see the validation_loss.

history <- model %>% fit(
  x = x_train, y = y_train,
  epochs = 400,
  batch_size = 20,
  validation_split = 0.2
)

Epoch 1/400
7/7 - 1s - loss: 0.9043 - accuracy: 0.5156 - val_loss: 0.9107 - val_accuracy: 0.5312 - 1s/epoch - 159ms/step
Epoch 2/400
7/7 - 0s - loss: 0.8834 - accuracy: 0.5312 - val_loss: 0.8975 - val_accuracy: 0.5312 - 60ms/epoch - 9ms/step
Epoch 3/400
7/7 - 0s - loss: 0.8669 - accuracy: 0.5156 - val_loss: 0.8875 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 4/400
7/7 - 0s - loss: 0.8530 - accuracy: 0.5234 - val_loss: 0.8768 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 5/400
7/7 - 0s - loss: 0.8396 - accuracy: 0.5312 - val_loss: 0.8679 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 6/400
7/7 - 0s - loss: 0.8274 - accuracy: 0.5234 - val_loss: 0.8589 - val_accuracy: 0.5000 - 52ms/epoch - 7ms/step
Epoch 7/400
7/7 - 0s - loss: 0.8153 - accuracy: 0.5312 - val_loss: 0.8504 - val_accuracy: 0.5000 - 41ms/epoch - 6ms/step
Epoch 8/400
7/7 - 0s - loss: 0.8042 - accuracy: 0.5156 - val_loss: 0.8417 - val_accuracy: 0.5000 - 38ms/epoch - 5ms/step
Epoch 9/400
7/7 - 0s - loss: 0.7927 - accuracy: 0.5078 - val_loss: 0.8349 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 10/400
7/7 - 0s - loss: 0.7823 - accuracy: 0.5156 - val_loss: 0.8277 - val_accuracy: 0.4375 - 34ms/epoch - 5ms/step
Epoch 11/400
7/7 - 0s - loss: 0.7716 - accuracy: 0.5078 - val_loss: 0.8193 - val_accuracy: 0.4375 - 33ms/epoch - 5ms/step
Epoch 12/400
7/7 - 0s - loss: 0.7606 - accuracy: 0.5156 - val_loss: 0.8117 - val_accuracy: 0.4688 - 33ms/epoch - 5ms/step
Epoch 13/400
7/7 - 0s - loss: 0.7507 - accuracy: 0.5156 - val_loss: 0.8050 - val_accuracy: 0.4688 - 33ms/epoch - 5ms/step
Epoch 14/400
7/7 - 0s - loss: 0.7413 - accuracy: 0.5312 - val_loss: 0.7979 - val_accuracy: 0.5000 - 85ms/epoch - 12ms/step
Epoch 15/400
7/7 - 0s - loss: 0.7315 - accuracy: 0.5391 - val_loss: 0.7913 - val_accuracy: 0.4688 - 33ms/epoch - 5ms/step
Epoch 16/400
7/7 - 0s - loss: 0.7227 - accuracy: 0.5469 - val_loss: 0.7849 - val_accuracy: 0.5000 - 36ms/epoch - 5ms/step
Epoch 17/400
7/7 - 0s - loss: 0.7145 - accuracy: 0.5469 - val_loss: 0.7785 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 18/400
7/7 - 0s - loss: 0.7056 - accuracy: 0.5469 - val_loss: 0.7720 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 19/400
7/7 - 0s - loss: 0.6973 - accuracy: 0.5391 - val_loss: 0.7669 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 20/400
7/7 - 0s - loss: 0.6901 - accuracy: 0.5391 - val_loss: 0.7615 - val_accuracy: 0.4688 - 34ms/epoch - 5ms/step
Epoch 21/400
7/7 - 0s - loss: 0.6826 - accuracy: 0.5234 - val_loss: 0.7564 - val_accuracy: 0.4062 - 33ms/epoch - 5ms/step
Epoch 22/400
7/7 - 0s - loss: 0.6757 - accuracy: 0.5000 - val_loss: 0.7520 - val_accuracy: 0.4062 - 32ms/epoch - 5ms/step
Epoch 23/400
7/7 - 0s - loss: 0.6690 - accuracy: 0.5000 - val_loss: 0.7462 - val_accuracy: 0.3750 - 33ms/epoch - 5ms/step
Epoch 24/400
7/7 - 0s - loss: 0.6622 - accuracy: 0.5078 - val_loss: 0.7411 - val_accuracy: 0.4062 - 34ms/epoch - 5ms/step
Epoch 25/400
7/7 - 0s - loss: 0.6555 - accuracy: 0.5156 - val_loss: 0.7361 - val_accuracy: 0.3750 - 34ms/epoch - 5ms/step
Epoch 26/400
7/7 - 0s - loss: 0.6494 - accuracy: 0.5156 - val_loss: 0.7329 - val_accuracy: 0.3750 - 34ms/epoch - 5ms/step
Epoch 27/400
7/7 - 0s - loss: 0.6442 - accuracy: 0.5312 - val_loss: 0.7289 - val_accuracy: 0.3750 - 34ms/epoch - 5ms/step
Epoch 28/400
7/7 - 0s - loss: 0.6383 - accuracy: 0.5312 - val_loss: 0.7243 - val_accuracy: 0.4062 - 33ms/epoch - 5ms/step
Epoch 29/400
7/7 - 0s - loss: 0.6328 - accuracy: 0.5312 - val_loss: 0.7198 - val_accuracy: 0.4062 - 34ms/epoch - 5ms/step
Epoch 30/400
7/7 - 0s - loss: 0.6274 - accuracy: 0.5391 - val_loss: 0.7156 - val_accuracy: 0.4062 - 33ms/epoch - 5ms/step
Epoch 31/400
7/7 - 0s - loss: 0.6221 - accuracy: 0.5469 - val_loss: 0.7120 - val_accuracy: 0.4062 - 33ms/epoch - 5ms/step
Epoch 32/400
7/7 - 0s - loss: 0.6170 - accuracy: 0.5547 - val_loss: 0.7083 - val_accuracy: 0.4062 - 36ms/epoch - 5ms/step
Epoch 33/400
7/7 - 0s - loss: 0.6123 - accuracy: 0.5781 - val_loss: 0.7041 - val_accuracy: 0.4375 - 40ms/epoch - 6ms/step
Epoch 34/400
7/7 - 0s - loss: 0.6070 - accuracy: 0.5938 - val_loss: 0.7002 - val_accuracy: 0.4375 - 42ms/epoch - 6ms/step
Epoch 35/400
7/7 - 0s - loss: 0.6021 - accuracy: 0.6328 - val_loss: 0.6959 - val_accuracy: 0.4688 - 38ms/epoch - 5ms/step
Epoch 36/400
7/7 - 0s - loss: 0.5974 - accuracy: 0.6562 - val_loss: 0.6915 - val_accuracy: 0.4688 - 46ms/epoch - 7ms/step
Epoch 37/400
7/7 - 0s - loss: 0.5925 - accuracy: 0.6562 - val_loss: 0.6877 - val_accuracy: 0.4688 - 47ms/epoch - 7ms/step
Epoch 38/400
7/7 - 0s - loss: 0.5879 - accuracy: 0.6641 - val_loss: 0.6830 - val_accuracy: 0.4688 - 38ms/epoch - 5ms/step
Epoch 39/400
7/7 - 0s - loss: 0.5834 - accuracy: 0.6797 - val_loss: 0.6807 - val_accuracy: 0.4688 - 39ms/epoch - 6ms/step
Epoch 40/400
7/7 - 0s - loss: 0.5794 - accuracy: 0.6797 - val_loss: 0.6766 - val_accuracy: 0.4688 - 42ms/epoch - 6ms/step
Epoch 41/400
7/7 - 0s - loss: 0.5753 - accuracy: 0.6797 - val_loss: 0.6733 - val_accuracy: 0.4688 - 49ms/epoch - 7ms/step
Epoch 42/400
7/7 - 0s - loss: 0.5714 - accuracy: 0.6797 - val_loss: 0.6698 - val_accuracy: 0.4688 - 42ms/epoch - 6ms/step
Epoch 43/400
7/7 - 0s - loss: 0.5676 - accuracy: 0.6797 - val_loss: 0.6668 - val_accuracy: 0.4688 - 45ms/epoch - 6ms/step
Epoch 44/400
7/7 - 0s - loss: 0.5638 - accuracy: 0.6875 - val_loss: 0.6635 - val_accuracy: 0.4688 - 35ms/epoch - 5ms/step
Epoch 45/400
7/7 - 0s - loss: 0.5602 - accuracy: 0.6875 - val_loss: 0.6602 - val_accuracy: 0.4688 - 40ms/epoch - 6ms/step
Epoch 46/400
7/7 - 0s - loss: 0.5571 - accuracy: 0.6875 - val_loss: 0.6565 - val_accuracy: 0.4688 - 43ms/epoch - 6ms/step
Epoch 47/400
7/7 - 0s - loss: 0.5538 - accuracy: 0.6953 - val_loss: 0.6530 - val_accuracy: 0.4688 - 34ms/epoch - 5ms/step
Epoch 48/400
7/7 - 0s - loss: 0.5506 - accuracy: 0.6953 - val_loss: 0.6506 - val_accuracy: 0.4688 - 35ms/epoch - 5ms/step
Epoch 49/400
7/7 - 0s - loss: 0.5477 - accuracy: 0.6953 - val_loss: 0.6485 - val_accuracy: 0.4688 - 33ms/epoch - 5ms/step
Epoch 50/400
7/7 - 0s - loss: 0.5449 - accuracy: 0.7031 - val_loss: 0.6451 - val_accuracy: 0.4688 - 32ms/epoch - 5ms/step
Epoch 51/400
7/7 - 0s - loss: 0.5420 - accuracy: 0.7031 - val_loss: 0.6432 - val_accuracy: 0.5000 - 36ms/epoch - 5ms/step
Epoch 52/400
7/7 - 0s - loss: 0.5393 - accuracy: 0.7031 - val_loss: 0.6397 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 53/400
7/7 - 0s - loss: 0.5367 - accuracy: 0.7031 - val_loss: 0.6373 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 54/400
7/7 - 0s - loss: 0.5338 - accuracy: 0.7031 - val_loss: 0.6344 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 55/400
7/7 - 0s - loss: 0.5312 - accuracy: 0.7031 - val_loss: 0.6325 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 56/400
7/7 - 0s - loss: 0.5291 - accuracy: 0.7031 - val_loss: 0.6295 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 57/400
7/7 - 0s - loss: 0.5266 - accuracy: 0.7031 - val_loss: 0.6278 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 58/400
7/7 - 0s - loss: 0.5245 - accuracy: 0.7031 - val_loss: 0.6261 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 59/400
7/7 - 0s - loss: 0.5225 - accuracy: 0.7031 - val_loss: 0.6238 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 60/400
7/7 - 0s - loss: 0.5205 - accuracy: 0.7031 - val_loss: 0.6216 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 61/400
7/7 - 0s - loss: 0.5185 - accuracy: 0.7031 - val_loss: 0.6196 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 62/400
7/7 - 0s - loss: 0.5166 - accuracy: 0.7031 - val_loss: 0.6167 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 63/400
7/7 - 0s - loss: 0.5146 - accuracy: 0.7031 - val_loss: 0.6149 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 64/400
7/7 - 0s - loss: 0.5129 - accuracy: 0.7031 - val_loss: 0.6137 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 65/400
7/7 - 0s - loss: 0.5110 - accuracy: 0.7031 - val_loss: 0.6112 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 66/400
7/7 - 0s - loss: 0.5090 - accuracy: 0.7031 - val_loss: 0.6098 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 67/400
7/7 - 0s - loss: 0.5072 - accuracy: 0.7031 - val_loss: 0.6083 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 68/400
7/7 - 0s - loss: 0.5056 - accuracy: 0.7031 - val_loss: 0.6065 - val_accuracy: 0.5000 - 40ms/epoch - 6ms/step
Epoch 69/400
7/7 - 0s - loss: 0.5037 - accuracy: 0.7031 - val_loss: 0.6053 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 70/400
7/7 - 0s - loss: 0.5019 - accuracy: 0.7031 - val_loss: 0.6030 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 71/400
7/7 - 0s - loss: 0.4999 - accuracy: 0.7031 - val_loss: 0.6013 - val_accuracy: 0.5000 - 35ms/epoch - 5ms/step
Epoch 72/400
7/7 - 0s - loss: 0.4986 - accuracy: 0.7031 - val_loss: 0.5996 - val_accuracy: 0.5000 - 36ms/epoch - 5ms/step
Epoch 73/400
7/7 - 0s - loss: 0.4965 - accuracy: 0.7031 - val_loss: 0.5977 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 74/400
7/7 - 0s - loss: 0.4948 - accuracy: 0.7031 - val_loss: 0.5955 - val_accuracy: 0.5000 - 34ms/epoch - 5ms/step
Epoch 75/400
7/7 - 0s - loss: 0.4931 - accuracy: 0.7031 - val_loss: 0.5929 - val_accuracy: 0.5000 - 42ms/epoch - 6ms/step
Epoch 76/400
7/7 - 0s - loss: 0.4914 - accuracy: 0.7031 - val_loss: 0.5919 - val_accuracy: 0.5000 - 47ms/epoch - 7ms/step
Epoch 77/400
7/7 - 0s - loss: 0.4897 - accuracy: 0.7031 - val_loss: 0.5902 - val_accuracy: 0.5312 - 40ms/epoch - 6ms/step
Epoch 78/400
7/7 - 0s - loss: 0.4882 - accuracy: 0.7031 - val_loss: 0.5881 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 79/400
7/7 - 0s - loss: 0.4866 - accuracy: 0.7031 - val_loss: 0.5872 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 80/400
7/7 - 0s - loss: 0.4851 - accuracy: 0.7031 - val_loss: 0.5854 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 81/400
7/7 - 0s - loss: 0.4834 - accuracy: 0.7031 - val_loss: 0.5839 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 82/400
7/7 - 0s - loss: 0.4820 - accuracy: 0.7031 - val_loss: 0.5830 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 83/400
7/7 - 0s - loss: 0.4805 - accuracy: 0.7031 - val_loss: 0.5814 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 84/400
7/7 - 0s - loss: 0.4791 - accuracy: 0.7031 - val_loss: 0.5804 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 85/400
7/7 - 0s - loss: 0.4778 - accuracy: 0.7031 - val_loss: 0.5795 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 86/400
7/7 - 0s - loss: 0.4762 - accuracy: 0.7031 - val_loss: 0.5780 - val_accuracy: 0.5312 - 40ms/epoch - 6ms/step
Epoch 87/400
7/7 - 0s - loss: 0.4750 - accuracy: 0.7031 - val_loss: 0.5765 - val_accuracy: 0.5312 - 38ms/epoch - 5ms/step
Epoch 88/400
7/7 - 0s - loss: 0.4736 - accuracy: 0.7031 - val_loss: 0.5763 - val_accuracy: 0.5312 - 39ms/epoch - 6ms/step
Epoch 89/400
7/7 - 0s - loss: 0.4723 - accuracy: 0.7031 - val_loss: 0.5752 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 90/400
7/7 - 0s - loss: 0.4712 - accuracy: 0.7031 - val_loss: 0.5744 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 91/400
7/7 - 0s - loss: 0.4698 - accuracy: 0.7031 - val_loss: 0.5729 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 92/400
7/7 - 0s - loss: 0.4688 - accuracy: 0.7109 - val_loss: 0.5723 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 93/400
7/7 - 0s - loss: 0.4674 - accuracy: 0.7109 - val_loss: 0.5718 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 94/400
7/7 - 0s - loss: 0.4666 - accuracy: 0.7109 - val_loss: 0.5704 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 95/400
7/7 - 0s - loss: 0.4654 - accuracy: 0.7109 - val_loss: 0.5687 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 96/400
7/7 - 0s - loss: 0.4644 - accuracy: 0.7109 - val_loss: 0.5683 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 97/400
7/7 - 0s - loss: 0.4637 - accuracy: 0.7109 - val_loss: 0.5674 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 98/400
7/7 - 0s - loss: 0.4628 - accuracy: 0.7109 - val_loss: 0.5673 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 99/400
7/7 - 0s - loss: 0.4620 - accuracy: 0.7109 - val_loss: 0.5657 - val_accuracy: 0.5312 - 38ms/epoch - 5ms/step
Epoch 100/400
7/7 - 0s - loss: 0.4610 - accuracy: 0.7109 - val_loss: 0.5645 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 101/400
7/7 - 0s - loss: 0.4601 - accuracy: 0.7109 - val_loss: 0.5631 - val_accuracy: 0.5312 - 40ms/epoch - 6ms/step
Epoch 102/400
7/7 - 0s - loss: 0.4592 - accuracy: 0.7109 - val_loss: 0.5622 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 103/400
7/7 - 0s - loss: 0.4584 - accuracy: 0.7109 - val_loss: 0.5622 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 104/400
7/7 - 0s - loss: 0.4575 - accuracy: 0.7109 - val_loss: 0.5618 - val_accuracy: 0.5312 - 51ms/epoch - 7ms/step
Epoch 105/400
7/7 - 0s - loss: 0.4568 - accuracy: 0.7109 - val_loss: 0.5608 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 106/400
7/7 - 0s - loss: 0.4559 - accuracy: 0.7109 - val_loss: 0.5606 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 107/400
7/7 - 0s - loss: 0.4551 - accuracy: 0.7109 - val_loss: 0.5601 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 108/400
7/7 - 0s - loss: 0.4544 - accuracy: 0.7109 - val_loss: 0.5592 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 109/400
7/7 - 0s - loss: 0.4539 - accuracy: 0.7109 - val_loss: 0.5593 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 110/400
7/7 - 0s - loss: 0.4529 - accuracy: 0.7109 - val_loss: 0.5585 - val_accuracy: 0.5312 - 52ms/epoch - 7ms/step
Epoch 111/400
7/7 - 0s - loss: 0.4522 - accuracy: 0.7109 - val_loss: 0.5572 - val_accuracy: 0.5312 - 52ms/epoch - 7ms/step
Epoch 112/400
7/7 - 0s - loss: 0.4515 - accuracy: 0.7109 - val_loss: 0.5563 - val_accuracy: 0.5312 - 54ms/epoch - 8ms/step
Epoch 113/400
7/7 - 0s - loss: 0.4510 - accuracy: 0.7109 - val_loss: 0.5558 - val_accuracy: 0.5312 - 54ms/epoch - 8ms/step
Epoch 114/400
7/7 - 0s - loss: 0.4502 - accuracy: 0.7109 - val_loss: 0.5560 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 115/400
7/7 - 0s - loss: 0.4495 - accuracy: 0.7109 - val_loss: 0.5554 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 116/400
7/7 - 0s - loss: 0.4488 - accuracy: 0.7109 - val_loss: 0.5539 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 117/400
7/7 - 0s - loss: 0.4481 - accuracy: 0.7109 - val_loss: 0.5538 - val_accuracy: 0.5312 - 39ms/epoch - 6ms/step
Epoch 118/400
7/7 - 0s - loss: 0.4474 - accuracy: 0.7109 - val_loss: 0.5534 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 119/400
7/7 - 0s - loss: 0.4469 - accuracy: 0.7109 - val_loss: 0.5521 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 120/400
7/7 - 0s - loss: 0.4462 - accuracy: 0.7109 - val_loss: 0.5522 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 121/400
7/7 - 0s - loss: 0.4455 - accuracy: 0.7109 - val_loss: 0.5522 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 122/400
7/7 - 0s - loss: 0.4450 - accuracy: 0.7109 - val_loss: 0.5523 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 123/400
7/7 - 0s - loss: 0.4444 - accuracy: 0.7109 - val_loss: 0.5517 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 124/400
7/7 - 0s - loss: 0.4436 - accuracy: 0.7188 - val_loss: 0.5500 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 125/400
7/7 - 0s - loss: 0.4429 - accuracy: 0.7266 - val_loss: 0.5498 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 126/400
7/7 - 0s - loss: 0.4426 - accuracy: 0.7266 - val_loss: 0.5495 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 127/400
7/7 - 0s - loss: 0.4419 - accuracy: 0.7266 - val_loss: 0.5487 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 128/400
7/7 - 0s - loss: 0.4412 - accuracy: 0.7266 - val_loss: 0.5483 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 129/400
7/7 - 0s - loss: 0.4405 - accuracy: 0.7344 - val_loss: 0.5481 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 130/400
7/7 - 0s - loss: 0.4400 - accuracy: 0.7344 - val_loss: 0.5482 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 131/400
7/7 - 0s - loss: 0.4393 - accuracy: 0.7344 - val_loss: 0.5475 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 132/400
7/7 - 0s - loss: 0.4388 - accuracy: 0.7344 - val_loss: 0.5471 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 133/400
7/7 - 0s - loss: 0.4382 - accuracy: 0.7344 - val_loss: 0.5469 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 134/400
7/7 - 0s - loss: 0.4376 - accuracy: 0.7344 - val_loss: 0.5457 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 135/400
7/7 - 0s - loss: 0.4369 - accuracy: 0.7344 - val_loss: 0.5450 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 136/400
7/7 - 0s - loss: 0.4364 - accuracy: 0.7344 - val_loss: 0.5441 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 137/400
7/7 - 0s - loss: 0.4357 - accuracy: 0.7344 - val_loss: 0.5430 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 138/400
7/7 - 0s - loss: 0.4353 - accuracy: 0.7344 - val_loss: 0.5431 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 139/400
7/7 - 0s - loss: 0.4346 - accuracy: 0.7344 - val_loss: 0.5425 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 140/400
7/7 - 0s - loss: 0.4341 - accuracy: 0.7344 - val_loss: 0.5412 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 141/400
7/7 - 0s - loss: 0.4338 - accuracy: 0.7344 - val_loss: 0.5411 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 142/400
7/7 - 0s - loss: 0.4332 - accuracy: 0.7344 - val_loss: 0.5407 - val_accuracy: 0.5312 - 50ms/epoch - 7ms/step
Epoch 143/400
7/7 - 0s - loss: 0.4326 - accuracy: 0.7344 - val_loss: 0.5399 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 144/400
7/7 - 0s - loss: 0.4322 - accuracy: 0.7344 - val_loss: 0.5389 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 145/400
7/7 - 0s - loss: 0.4318 - accuracy: 0.7344 - val_loss: 0.5381 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 146/400
7/7 - 0s - loss: 0.4312 - accuracy: 0.7344 - val_loss: 0.5381 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 147/400
7/7 - 0s - loss: 0.4310 - accuracy: 0.7344 - val_loss: 0.5385 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 148/400
7/7 - 0s - loss: 0.4306 - accuracy: 0.7344 - val_loss: 0.5381 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 149/400
7/7 - 0s - loss: 0.4303 - accuracy: 0.7344 - val_loss: 0.5383 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 150/400
7/7 - 0s - loss: 0.4300 - accuracy: 0.7344 - val_loss: 0.5376 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 151/400
7/7 - 0s - loss: 0.4295 - accuracy: 0.7344 - val_loss: 0.5366 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 152/400
7/7 - 0s - loss: 0.4289 - accuracy: 0.7344 - val_loss: 0.5360 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 153/400
7/7 - 0s - loss: 0.4287 - accuracy: 0.7344 - val_loss: 0.5349 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 154/400
7/7 - 0s - loss: 0.4280 - accuracy: 0.7344 - val_loss: 0.5350 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 155/400
7/7 - 0s - loss: 0.4278 - accuracy: 0.7344 - val_loss: 0.5343 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 156/400
7/7 - 0s - loss: 0.4275 - accuracy: 0.7344 - val_loss: 0.5345 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 157/400
7/7 - 0s - loss: 0.4271 - accuracy: 0.7344 - val_loss: 0.5348 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 158/400
7/7 - 0s - loss: 0.4271 - accuracy: 0.7344 - val_loss: 0.5347 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 159/400
7/7 - 0s - loss: 0.4265 - accuracy: 0.7344 - val_loss: 0.5342 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 160/400
7/7 - 0s - loss: 0.4263 - accuracy: 0.7344 - val_loss: 0.5328 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 161/400
7/7 - 0s - loss: 0.4259 - accuracy: 0.7344 - val_loss: 0.5322 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 162/400
7/7 - 0s - loss: 0.4256 - accuracy: 0.7344 - val_loss: 0.5323 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 163/400
7/7 - 0s - loss: 0.4253 - accuracy: 0.7344 - val_loss: 0.5326 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 164/400
7/7 - 0s - loss: 0.4250 - accuracy: 0.7344 - val_loss: 0.5327 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 165/400
7/7 - 0s - loss: 0.4246 - accuracy: 0.7344 - val_loss: 0.5329 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 166/400
7/7 - 0s - loss: 0.4244 - accuracy: 0.7344 - val_loss: 0.5326 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 167/400
7/7 - 0s - loss: 0.4241 - accuracy: 0.7344 - val_loss: 0.5325 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 168/400
7/7 - 0s - loss: 0.4239 - accuracy: 0.7344 - val_loss: 0.5322 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 169/400
7/7 - 0s - loss: 0.4233 - accuracy: 0.7344 - val_loss: 0.5323 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 170/400
7/7 - 0s - loss: 0.4231 - accuracy: 0.7344 - val_loss: 0.5319 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 171/400
7/7 - 0s - loss: 0.4227 - accuracy: 0.7344 - val_loss: 0.5312 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 172/400
7/7 - 0s - loss: 0.4223 - accuracy: 0.7344 - val_loss: 0.5316 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 173/400
7/7 - 0s - loss: 0.4222 - accuracy: 0.7344 - val_loss: 0.5317 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 174/400
7/7 - 0s - loss: 0.4216 - accuracy: 0.7344 - val_loss: 0.5314 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 175/400
7/7 - 0s - loss: 0.4215 - accuracy: 0.7344 - val_loss: 0.5310 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 176/400
7/7 - 0s - loss: 0.4213 - accuracy: 0.7344 - val_loss: 0.5309 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 177/400
7/7 - 0s - loss: 0.4209 - accuracy: 0.7344 - val_loss: 0.5293 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 178/400
7/7 - 0s - loss: 0.4205 - accuracy: 0.7344 - val_loss: 0.5293 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 179/400
7/7 - 0s - loss: 0.4203 - accuracy: 0.7344 - val_loss: 0.5279 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 180/400
7/7 - 0s - loss: 0.4200 - accuracy: 0.7344 - val_loss: 0.5273 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 181/400
7/7 - 0s - loss: 0.4198 - accuracy: 0.7344 - val_loss: 0.5260 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 182/400
7/7 - 0s - loss: 0.4195 - accuracy: 0.7344 - val_loss: 0.5260 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 183/400
7/7 - 0s - loss: 0.4192 - accuracy: 0.7344 - val_loss: 0.5259 - val_accuracy: 0.5312 - 40ms/epoch - 6ms/step
Epoch 184/400
7/7 - 0s - loss: 0.4192 - accuracy: 0.7344 - val_loss: 0.5249 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 185/400
7/7 - 0s - loss: 0.4187 - accuracy: 0.7344 - val_loss: 0.5253 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 186/400
7/7 - 0s - loss: 0.4185 - accuracy: 0.7344 - val_loss: 0.5237 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 187/400
7/7 - 0s - loss: 0.4182 - accuracy: 0.7344 - val_loss: 0.5235 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 188/400
7/7 - 0s - loss: 0.4180 - accuracy: 0.7344 - val_loss: 0.5233 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 189/400
7/7 - 0s - loss: 0.4179 - accuracy: 0.7344 - val_loss: 0.5234 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 190/400
7/7 - 0s - loss: 0.4174 - accuracy: 0.7344 - val_loss: 0.5225 - val_accuracy: 0.5312 - 52ms/epoch - 7ms/step
Epoch 191/400
7/7 - 0s - loss: 0.4172 - accuracy: 0.7344 - val_loss: 0.5227 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 192/400
7/7 - 0s - loss: 0.4169 - accuracy: 0.7344 - val_loss: 0.5225 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 193/400
7/7 - 0s - loss: 0.4167 - accuracy: 0.7344 - val_loss: 0.5222 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 194/400
7/7 - 0s - loss: 0.4164 - accuracy: 0.7344 - val_loss: 0.5216 - val_accuracy: 0.5312 - 52ms/epoch - 7ms/step
Epoch 195/400
7/7 - 0s - loss: 0.4162 - accuracy: 0.7344 - val_loss: 0.5216 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 196/400
7/7 - 0s - loss: 0.4161 - accuracy: 0.7344 - val_loss: 0.5212 - val_accuracy: 0.5312 - 40ms/epoch - 6ms/step
Epoch 197/400
7/7 - 0s - loss: 0.4157 - accuracy: 0.7344 - val_loss: 0.5212 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 198/400
7/7 - 0s - loss: 0.4155 - accuracy: 0.7344 - val_loss: 0.5208 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 199/400
7/7 - 0s - loss: 0.4152 - accuracy: 0.7344 - val_loss: 0.5199 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 200/400
7/7 - 0s - loss: 0.4150 - accuracy: 0.7344 - val_loss: 0.5205 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 201/400
7/7 - 0s - loss: 0.4147 - accuracy: 0.7344 - val_loss: 0.5193 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 202/400
7/7 - 0s - loss: 0.4146 - accuracy: 0.7344 - val_loss: 0.5200 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 203/400
7/7 - 0s - loss: 0.4143 - accuracy: 0.7344 - val_loss: 0.5196 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 204/400
7/7 - 0s - loss: 0.4142 - accuracy: 0.7344 - val_loss: 0.5191 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 205/400
7/7 - 0s - loss: 0.4140 - accuracy: 0.7344 - val_loss: 0.5195 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 206/400
7/7 - 0s - loss: 0.4138 - accuracy: 0.7344 - val_loss: 0.5198 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 207/400
7/7 - 0s - loss: 0.4136 - accuracy: 0.7344 - val_loss: 0.5190 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 208/400
7/7 - 0s - loss: 0.4132 - accuracy: 0.7344 - val_loss: 0.5195 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 209/400
7/7 - 0s - loss: 0.4131 - accuracy: 0.7344 - val_loss: 0.5190 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 210/400
7/7 - 0s - loss: 0.4130 - accuracy: 0.7344 - val_loss: 0.5181 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 211/400
7/7 - 0s - loss: 0.4127 - accuracy: 0.7344 - val_loss: 0.5174 - val_accuracy: 0.5312 - 40ms/epoch - 6ms/step
Epoch 212/400
7/7 - 0s - loss: 0.4126 - accuracy: 0.7344 - val_loss: 0.5175 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 213/400
7/7 - 0s - loss: 0.4123 - accuracy: 0.7344 - val_loss: 0.5164 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 214/400
7/7 - 0s - loss: 0.4122 - accuracy: 0.7344 - val_loss: 0.5160 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 215/400
7/7 - 0s - loss: 0.4119 - accuracy: 0.7344 - val_loss: 0.5163 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 216/400
7/7 - 0s - loss: 0.4117 - accuracy: 0.7344 - val_loss: 0.5150 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 217/400
7/7 - 0s - loss: 0.4115 - accuracy: 0.7344 - val_loss: 0.5150 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 218/400
7/7 - 0s - loss: 0.4114 - accuracy: 0.7344 - val_loss: 0.5139 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 219/400
7/7 - 0s - loss: 0.4113 - accuracy: 0.7344 - val_loss: 0.5141 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 220/400
7/7 - 0s - loss: 0.4110 - accuracy: 0.7344 - val_loss: 0.5139 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 221/400
7/7 - 0s - loss: 0.4110 - accuracy: 0.7344 - val_loss: 0.5143 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 222/400
7/7 - 0s - loss: 0.4109 - accuracy: 0.7344 - val_loss: 0.5139 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 223/400
7/7 - 0s - loss: 0.4106 - accuracy: 0.7344 - val_loss: 0.5133 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 224/400
7/7 - 0s - loss: 0.4105 - accuracy: 0.7344 - val_loss: 0.5138 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 225/400
7/7 - 0s - loss: 0.4104 - accuracy: 0.7344 - val_loss: 0.5140 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 226/400
7/7 - 0s - loss: 0.4100 - accuracy: 0.7344 - val_loss: 0.5145 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 227/400
7/7 - 0s - loss: 0.4099 - accuracy: 0.7344 - val_loss: 0.5138 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 228/400
7/7 - 0s - loss: 0.4096 - accuracy: 0.7344 - val_loss: 0.5135 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 229/400
7/7 - 0s - loss: 0.4096 - accuracy: 0.7344 - val_loss: 0.5142 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 230/400
7/7 - 0s - loss: 0.4093 - accuracy: 0.7344 - val_loss: 0.5151 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 231/400
7/7 - 0s - loss: 0.4092 - accuracy: 0.7344 - val_loss: 0.5133 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 232/400
7/7 - 0s - loss: 0.4088 - accuracy: 0.7344 - val_loss: 0.5132 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 233/400
7/7 - 0s - loss: 0.4088 - accuracy: 0.7344 - val_loss: 0.5135 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 234/400
7/7 - 0s - loss: 0.4086 - accuracy: 0.7344 - val_loss: 0.5134 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 235/400
7/7 - 0s - loss: 0.4085 - accuracy: 0.7344 - val_loss: 0.5130 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 236/400
7/7 - 0s - loss: 0.4083 - accuracy: 0.7344 - val_loss: 0.5116 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 237/400
7/7 - 0s - loss: 0.4080 - accuracy: 0.7344 - val_loss: 0.5103 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 238/400
7/7 - 0s - loss: 0.4079 - accuracy: 0.7344 - val_loss: 0.5113 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 239/400
7/7 - 0s - loss: 0.4078 - accuracy: 0.7344 - val_loss: 0.5109 - val_accuracy: 0.5312 - 51ms/epoch - 7ms/step
Epoch 240/400
7/7 - 0s - loss: 0.4076 - accuracy: 0.7344 - val_loss: 0.5117 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 241/400
7/7 - 0s - loss: 0.4074 - accuracy: 0.7344 - val_loss: 0.5114 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 242/400
7/7 - 0s - loss: 0.4073 - accuracy: 0.7344 - val_loss: 0.5117 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 243/400
7/7 - 0s - loss: 0.4071 - accuracy: 0.7344 - val_loss: 0.5114 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 244/400
7/7 - 0s - loss: 0.4071 - accuracy: 0.7344 - val_loss: 0.5103 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 245/400
7/7 - 0s - loss: 0.4068 - accuracy: 0.7344 - val_loss: 0.5106 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 246/400
7/7 - 0s - loss: 0.4068 - accuracy: 0.7344 - val_loss: 0.5114 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 247/400
7/7 - 0s - loss: 0.4065 - accuracy: 0.7344 - val_loss: 0.5110 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 248/400
7/7 - 0s - loss: 0.4064 - accuracy: 0.7344 - val_loss: 0.5104 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 249/400
7/7 - 0s - loss: 0.4063 - accuracy: 0.7344 - val_loss: 0.5096 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 250/400
7/7 - 0s - loss: 0.4061 - accuracy: 0.7344 - val_loss: 0.5085 - val_accuracy: 0.5312 - 39ms/epoch - 6ms/step
Epoch 251/400
7/7 - 0s - loss: 0.4059 - accuracy: 0.7344 - val_loss: 0.5087 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 252/400
7/7 - 0s - loss: 0.4057 - accuracy: 0.7344 - val_loss: 0.5080 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 253/400
7/7 - 0s - loss: 0.4056 - accuracy: 0.7344 - val_loss: 0.5079 - val_accuracy: 0.5312 - 38ms/epoch - 5ms/step
Epoch 254/400
7/7 - 0s - loss: 0.4053 - accuracy: 0.7344 - val_loss: 0.5075 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 255/400
7/7 - 0s - loss: 0.4052 - accuracy: 0.7344 - val_loss: 0.5080 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 256/400
7/7 - 0s - loss: 0.4052 - accuracy: 0.7344 - val_loss: 0.5078 - val_accuracy: 0.5312 - 38ms/epoch - 5ms/step
Epoch 257/400
7/7 - 0s - loss: 0.4049 - accuracy: 0.7344 - val_loss: 0.5071 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 258/400
7/7 - 0s - loss: 0.4047 - accuracy: 0.7344 - val_loss: 0.5070 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 259/400
7/7 - 0s - loss: 0.4046 - accuracy: 0.7344 - val_loss: 0.5068 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 260/400
7/7 - 0s - loss: 0.4044 - accuracy: 0.7344 - val_loss: 0.5056 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 261/400
7/7 - 0s - loss: 0.4040 - accuracy: 0.7344 - val_loss: 0.5045 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 262/400
7/7 - 0s - loss: 0.4042 - accuracy: 0.7344 - val_loss: 0.5038 - val_accuracy: 0.5312 - 38ms/epoch - 5ms/step
Epoch 263/400
7/7 - 0s - loss: 0.4037 - accuracy: 0.7344 - val_loss: 0.5041 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 264/400
7/7 - 0s - loss: 0.4037 - accuracy: 0.7344 - val_loss: 0.5031 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 265/400
7/7 - 0s - loss: 0.4034 - accuracy: 0.7344 - val_loss: 0.5027 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 266/400
7/7 - 0s - loss: 0.4035 - accuracy: 0.7344 - val_loss: 0.5029 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 267/400
7/7 - 0s - loss: 0.4032 - accuracy: 0.7344 - val_loss: 0.5039 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 268/400
7/7 - 0s - loss: 0.4029 - accuracy: 0.7344 - val_loss: 0.5040 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 269/400
7/7 - 0s - loss: 0.4030 - accuracy: 0.7344 - val_loss: 0.5030 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 270/400
7/7 - 0s - loss: 0.4028 - accuracy: 0.7344 - val_loss: 0.5025 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 271/400
7/7 - 0s - loss: 0.4026 - accuracy: 0.7344 - val_loss: 0.5029 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 272/400
7/7 - 0s - loss: 0.4025 - accuracy: 0.7344 - val_loss: 0.5030 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 273/400
7/7 - 0s - loss: 0.4024 - accuracy: 0.7344 - val_loss: 0.5034 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 274/400
7/7 - 0s - loss: 0.4021 - accuracy: 0.7344 - val_loss: 0.5031 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 275/400
7/7 - 0s - loss: 0.4021 - accuracy: 0.7344 - val_loss: 0.5026 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 276/400
7/7 - 0s - loss: 0.4019 - accuracy: 0.7344 - val_loss: 0.5022 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 277/400
7/7 - 0s - loss: 0.4016 - accuracy: 0.7344 - val_loss: 0.5014 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 278/400
7/7 - 0s - loss: 0.4017 - accuracy: 0.7344 - val_loss: 0.5019 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 279/400
7/7 - 0s - loss: 0.4013 - accuracy: 0.7344 - val_loss: 0.5013 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 280/400
7/7 - 0s - loss: 0.4013 - accuracy: 0.7344 - val_loss: 0.5010 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 281/400
7/7 - 0s - loss: 0.4011 - accuracy: 0.7344 - val_loss: 0.5009 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 282/400
7/7 - 0s - loss: 0.4008 - accuracy: 0.7344 - val_loss: 0.5005 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 283/400
7/7 - 0s - loss: 0.4007 - accuracy: 0.7344 - val_loss: 0.4996 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 284/400
7/7 - 0s - loss: 0.4006 - accuracy: 0.7344 - val_loss: 0.4999 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 285/400
7/7 - 0s - loss: 0.4006 - accuracy: 0.7344 - val_loss: 0.4994 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 286/400
7/7 - 0s - loss: 0.4002 - accuracy: 0.7344 - val_loss: 0.4986 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 287/400
7/7 - 0s - loss: 0.4001 - accuracy: 0.7344 - val_loss: 0.4984 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 288/400
7/7 - 0s - loss: 0.4000 - accuracy: 0.7344 - val_loss: 0.4981 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 289/400
7/7 - 0s - loss: 0.3997 - accuracy: 0.7344 - val_loss: 0.4973 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 290/400
7/7 - 0s - loss: 0.3996 - accuracy: 0.7344 - val_loss: 0.4974 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 291/400
7/7 - 0s - loss: 0.3994 - accuracy: 0.7344 - val_loss: 0.4974 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 292/400
7/7 - 0s - loss: 0.3992 - accuracy: 0.7344 - val_loss: 0.4979 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 293/400
7/7 - 0s - loss: 0.3991 - accuracy: 0.7344 - val_loss: 0.4973 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 294/400
7/7 - 0s - loss: 0.3993 - accuracy: 0.7344 - val_loss: 0.4974 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 295/400
7/7 - 0s - loss: 0.3990 - accuracy: 0.7344 - val_loss: 0.4965 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 296/400
7/7 - 0s - loss: 0.3986 - accuracy: 0.7344 - val_loss: 0.4967 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 297/400
7/7 - 0s - loss: 0.3985 - accuracy: 0.7344 - val_loss: 0.4966 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 298/400
7/7 - 0s - loss: 0.3986 - accuracy: 0.7344 - val_loss: 0.4956 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 299/400
7/7 - 0s - loss: 0.3983 - accuracy: 0.7344 - val_loss: 0.4963 - val_accuracy: 0.5312 - 50ms/epoch - 7ms/step
Epoch 300/400
7/7 - 0s - loss: 0.3981 - accuracy: 0.7344 - val_loss: 0.4957 - val_accuracy: 0.5312 - 54ms/epoch - 8ms/step
Epoch 301/400
7/7 - 0s - loss: 0.3980 - accuracy: 0.7344 - val_loss: 0.4951 - val_accuracy: 0.5312 - 57ms/epoch - 8ms/step
Epoch 302/400
7/7 - 0s - loss: 0.3977 - accuracy: 0.7344 - val_loss: 0.4949 - val_accuracy: 0.5312 - 55ms/epoch - 8ms/step
Epoch 303/400
7/7 - 0s - loss: 0.3978 - accuracy: 0.7344 - val_loss: 0.4947 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 304/400
7/7 - 0s - loss: 0.3976 - accuracy: 0.7344 - val_loss: 0.4953 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 305/400
7/7 - 0s - loss: 0.3975 - accuracy: 0.7344 - val_loss: 0.4945 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 306/400
7/7 - 0s - loss: 0.3973 - accuracy: 0.7344 - val_loss: 0.4945 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 307/400
7/7 - 0s - loss: 0.3971 - accuracy: 0.7344 - val_loss: 0.4935 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 308/400
7/7 - 0s - loss: 0.3972 - accuracy: 0.7344 - val_loss: 0.4935 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 309/400
7/7 - 0s - loss: 0.3969 - accuracy: 0.7344 - val_loss: 0.4945 - val_accuracy: 0.5312 - 50ms/epoch - 7ms/step
Epoch 310/400
7/7 - 0s - loss: 0.3968 - accuracy: 0.7344 - val_loss: 0.4939 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 311/400
7/7 - 0s - loss: 0.3966 - accuracy: 0.7344 - val_loss: 0.4922 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 312/400
7/7 - 0s - loss: 0.3963 - accuracy: 0.7344 - val_loss: 0.4922 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 313/400
7/7 - 0s - loss: 0.3963 - accuracy: 0.7344 - val_loss: 0.4922 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 314/400
7/7 - 0s - loss: 0.3962 - accuracy: 0.7344 - val_loss: 0.4924 - val_accuracy: 0.5312 - 54ms/epoch - 8ms/step
Epoch 315/400
7/7 - 0s - loss: 0.3962 - accuracy: 0.7344 - val_loss: 0.4931 - val_accuracy: 0.5312 - 59ms/epoch - 8ms/step
Epoch 316/400
7/7 - 0s - loss: 0.3962 - accuracy: 0.7344 - val_loss: 0.4937 - val_accuracy: 0.5312 - 49ms/epoch - 7ms/step
Epoch 317/400
7/7 - 0s - loss: 0.3960 - accuracy: 0.7344 - val_loss: 0.4933 - val_accuracy: 0.5312 - 51ms/epoch - 7ms/step
Epoch 318/400
7/7 - 0s - loss: 0.3957 - accuracy: 0.7344 - val_loss: 0.4929 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 319/400
7/7 - 0s - loss: 0.3956 - accuracy: 0.7344 - val_loss: 0.4922 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 320/400
7/7 - 0s - loss: 0.3953 - accuracy: 0.7344 - val_loss: 0.4914 - val_accuracy: 0.5312 - 39ms/epoch - 6ms/step
Epoch 321/400
7/7 - 0s - loss: 0.3954 - accuracy: 0.7344 - val_loss: 0.4914 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 322/400
7/7 - 0s - loss: 0.3952 - accuracy: 0.7344 - val_loss: 0.4912 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 323/400
7/7 - 0s - loss: 0.3952 - accuracy: 0.7344 - val_loss: 0.4914 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 324/400
7/7 - 0s - loss: 0.3949 - accuracy: 0.7344 - val_loss: 0.4915 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 325/400
7/7 - 0s - loss: 0.3948 - accuracy: 0.7344 - val_loss: 0.4903 - val_accuracy: 0.5312 - 39ms/epoch - 6ms/step
Epoch 326/400
7/7 - 0s - loss: 0.3946 - accuracy: 0.7344 - val_loss: 0.4891 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 327/400
7/7 - 0s - loss: 0.3945 - accuracy: 0.7344 - val_loss: 0.4899 - val_accuracy: 0.5312 - 39ms/epoch - 6ms/step
Epoch 328/400
7/7 - 0s - loss: 0.3944 - accuracy: 0.7344 - val_loss: 0.4896 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 329/400
7/7 - 0s - loss: 0.3944 - accuracy: 0.7344 - val_loss: 0.4897 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 330/400
7/7 - 0s - loss: 0.3942 - accuracy: 0.7344 - val_loss: 0.4893 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 331/400
7/7 - 0s - loss: 0.3940 - accuracy: 0.7344 - val_loss: 0.4890 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 332/400
7/7 - 0s - loss: 0.3941 - accuracy: 0.7344 - val_loss: 0.4895 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 333/400
7/7 - 0s - loss: 0.3938 - accuracy: 0.7344 - val_loss: 0.4883 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 334/400
7/7 - 0s - loss: 0.3937 - accuracy: 0.7344 - val_loss: 0.4884 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 335/400
7/7 - 0s - loss: 0.3936 - accuracy: 0.7344 - val_loss: 0.4884 - val_accuracy: 0.5312 - 52ms/epoch - 7ms/step
Epoch 336/400
7/7 - 0s - loss: 0.3934 - accuracy: 0.7344 - val_loss: 0.4884 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 337/400
7/7 - 0s - loss: 0.3931 - accuracy: 0.7344 - val_loss: 0.4886 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 338/400
7/7 - 0s - loss: 0.3932 - accuracy: 0.7344 - val_loss: 0.4879 - val_accuracy: 0.5312 - 55ms/epoch - 8ms/step
Epoch 339/400
7/7 - 0s - loss: 0.3932 - accuracy: 0.7344 - val_loss: 0.4882 - val_accuracy: 0.5312 - 57ms/epoch - 8ms/step
Epoch 340/400
7/7 - 0s - loss: 0.3929 - accuracy: 0.7344 - val_loss: 0.4884 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 341/400
7/7 - 0s - loss: 0.3927 - accuracy: 0.7344 - val_loss: 0.4875 - val_accuracy: 0.5312 - 51ms/epoch - 7ms/step
Epoch 342/400
7/7 - 0s - loss: 0.3927 - accuracy: 0.7344 - val_loss: 0.4870 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 343/400
7/7 - 0s - loss: 0.3927 - accuracy: 0.7344 - val_loss: 0.4862 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 344/400
7/7 - 0s - loss: 0.3923 - accuracy: 0.7344 - val_loss: 0.4861 - val_accuracy: 0.5312 - 42ms/epoch - 6ms/step
Epoch 345/400
7/7 - 0s - loss: 0.3923 - accuracy: 0.7344 - val_loss: 0.4862 - val_accuracy: 0.5312 - 52ms/epoch - 7ms/step
Epoch 346/400
7/7 - 0s - loss: 0.3922 - accuracy: 0.7344 - val_loss: 0.4857 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 347/400
7/7 - 0s - loss: 0.3920 - accuracy: 0.7344 - val_loss: 0.4862 - val_accuracy: 0.5312 - 54ms/epoch - 8ms/step
Epoch 348/400
7/7 - 0s - loss: 0.3919 - accuracy: 0.7344 - val_loss: 0.4853 - val_accuracy: 0.5312 - 54ms/epoch - 8ms/step
Epoch 349/400
7/7 - 0s - loss: 0.3918 - accuracy: 0.7344 - val_loss: 0.4858 - val_accuracy: 0.5312 - 52ms/epoch - 7ms/step
Epoch 350/400
7/7 - 0s - loss: 0.3917 - accuracy: 0.7344 - val_loss: 0.4866 - val_accuracy: 0.5312 - 51ms/epoch - 7ms/step
Epoch 351/400
7/7 - 0s - loss: 0.3915 - accuracy: 0.7344 - val_loss: 0.4867 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 352/400
7/7 - 0s - loss: 0.3915 - accuracy: 0.7344 - val_loss: 0.4868 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 353/400
7/7 - 0s - loss: 0.3913 - accuracy: 0.7344 - val_loss: 0.4870 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 354/400
7/7 - 0s - loss: 0.3915 - accuracy: 0.7344 - val_loss: 0.4876 - val_accuracy: 0.5312 - 56ms/epoch - 8ms/step
Epoch 355/400
7/7 - 0s - loss: 0.3914 - accuracy: 0.7344 - val_loss: 0.4865 - val_accuracy: 0.5312 - 50ms/epoch - 7ms/step
Epoch 356/400
7/7 - 0s - loss: 0.3910 - accuracy: 0.7344 - val_loss: 0.4864 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 357/400
7/7 - 0s - loss: 0.3909 - accuracy: 0.7344 - val_loss: 0.4853 - val_accuracy: 0.5312 - 38ms/epoch - 5ms/step
Epoch 358/400
7/7 - 0s - loss: 0.3908 - accuracy: 0.7344 - val_loss: 0.4851 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 359/400
7/7 - 0s - loss: 0.3908 - accuracy: 0.7344 - val_loss: 0.4843 - val_accuracy: 0.5312 - 39ms/epoch - 6ms/step
Epoch 360/400
7/7 - 0s - loss: 0.3905 - accuracy: 0.7422 - val_loss: 0.4848 - val_accuracy: 0.5312 - 43ms/epoch - 6ms/step
Epoch 361/400
7/7 - 0s - loss: 0.3905 - accuracy: 0.7422 - val_loss: 0.4838 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 362/400
7/7 - 0s - loss: 0.3903 - accuracy: 0.7344 - val_loss: 0.4837 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 363/400
7/7 - 0s - loss: 0.3901 - accuracy: 0.7422 - val_loss: 0.4844 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 364/400
7/7 - 0s - loss: 0.3901 - accuracy: 0.7422 - val_loss: 0.4840 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 365/400
7/7 - 0s - loss: 0.3901 - accuracy: 0.7422 - val_loss: 0.4840 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 366/400
7/7 - 0s - loss: 0.3899 - accuracy: 0.7500 - val_loss: 0.4841 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 367/400
7/7 - 0s - loss: 0.3899 - accuracy: 0.7422 - val_loss: 0.4851 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 368/400
7/7 - 0s - loss: 0.3897 - accuracy: 0.7422 - val_loss: 0.4849 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 369/400
7/7 - 0s - loss: 0.3895 - accuracy: 0.7422 - val_loss: 0.4833 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 370/400
7/7 - 0s - loss: 0.3894 - accuracy: 0.7500 - val_loss: 0.4833 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 371/400
7/7 - 0s - loss: 0.3893 - accuracy: 0.7422 - val_loss: 0.4840 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 372/400
7/7 - 0s - loss: 0.3894 - accuracy: 0.7422 - val_loss: 0.4834 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 373/400
7/7 - 0s - loss: 0.3891 - accuracy: 0.7422 - val_loss: 0.4838 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 374/400
7/7 - 0s - loss: 0.3890 - accuracy: 0.7422 - val_loss: 0.4840 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 375/400
7/7 - 0s - loss: 0.3889 - accuracy: 0.7422 - val_loss: 0.4849 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 376/400
7/7 - 0s - loss: 0.3891 - accuracy: 0.7422 - val_loss: 0.4852 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 377/400
7/7 - 0s - loss: 0.3889 - accuracy: 0.7422 - val_loss: 0.4851 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 378/400
7/7 - 0s - loss: 0.3886 - accuracy: 0.7422 - val_loss: 0.4842 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 379/400
7/7 - 0s - loss: 0.3887 - accuracy: 0.7500 - val_loss: 0.4846 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 380/400
7/7 - 0s - loss: 0.3887 - accuracy: 0.7422 - val_loss: 0.4848 - val_accuracy: 0.5312 - 37ms/epoch - 5ms/step
Epoch 381/400
7/7 - 0s - loss: 0.3884 - accuracy: 0.7500 - val_loss: 0.4847 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 382/400
7/7 - 0s - loss: 0.3883 - accuracy: 0.7500 - val_loss: 0.4851 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 383/400
7/7 - 0s - loss: 0.3882 - accuracy: 0.7422 - val_loss: 0.4846 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 384/400
7/7 - 0s - loss: 0.3880 - accuracy: 0.7422 - val_loss: 0.4840 - val_accuracy: 0.5312 - 35ms/epoch - 5ms/step
Epoch 385/400
7/7 - 0s - loss: 0.3883 - accuracy: 0.7500 - val_loss: 0.4837 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 386/400
7/7 - 0s - loss: 0.3879 - accuracy: 0.7500 - val_loss: 0.4844 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 387/400
7/7 - 0s - loss: 0.3878 - accuracy: 0.7422 - val_loss: 0.4843 - val_accuracy: 0.5312 - 34ms/epoch - 5ms/step
Epoch 388/400
7/7 - 0s - loss: 0.3878 - accuracy: 0.7422 - val_loss: 0.4845 - val_accuracy: 0.5312 - 36ms/epoch - 5ms/step
Epoch 389/400
7/7 - 0s - loss: 0.3876 - accuracy: 0.7422 - val_loss: 0.4836 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 390/400
7/7 - 0s - loss: 0.3874 - accuracy: 0.7422 - val_loss: 0.4834 - val_accuracy: 0.5312 - 41ms/epoch - 6ms/step
Epoch 391/400
7/7 - 0s - loss: 0.3874 - accuracy: 0.7422 - val_loss: 0.4837 - val_accuracy: 0.5312 - 44ms/epoch - 6ms/step
Epoch 392/400
7/7 - 0s - loss: 0.3872 - accuracy: 0.7422 - val_loss: 0.4832 - val_accuracy: 0.5312 - 46ms/epoch - 7ms/step
Epoch 393/400
7/7 - 0s - loss: 0.3871 - accuracy: 0.7422 - val_loss: 0.4821 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 394/400
7/7 - 0s - loss: 0.3871 - accuracy: 0.7422 - val_loss: 0.4831 - val_accuracy: 0.5312 - 45ms/epoch - 6ms/step
Epoch 395/400
7/7 - 0s - loss: 0.3870 - accuracy: 0.7422 - val_loss: 0.4829 - val_accuracy: 0.5312 - 49ms/epoch - 7ms/step
Epoch 396/400
7/7 - 0s - loss: 0.3867 - accuracy: 0.7422 - val_loss: 0.4827 - val_accuracy: 0.5312 - 53ms/epoch - 8ms/step
Epoch 397/400
7/7 - 0s - loss: 0.3866 - accuracy: 0.7422 - val_loss: 0.4823 - val_accuracy: 0.5312 - 54ms/epoch - 8ms/step
Epoch 398/400
7/7 - 0s - loss: 0.3867 - accuracy: 0.7422 - val_loss: 0.4816 - val_accuracy: 0.5312 - 47ms/epoch - 7ms/step
Epoch 399/400
7/7 - 0s - loss: 0.3864 - accuracy: 0.7422 - val_loss: 0.4815 - val_accuracy: 0.5312 - 48ms/epoch - 7ms/step
Epoch 400/400
7/7 - 0s - loss: 0.3864 - accuracy: 0.7422 - val_loss: 0.4820 - val_accuracy: 0.5312 - 55ms/epoch - 8ms/step

plot(history) +
  ggtitle("Training a neural network based classifier on the iris data set") +
  theme_bw()

Evaluate Network Performance

The final performance can be obtained like so.

perf <- model %>% evaluate(x_train, y_train)

5/5 - 0s - loss: 0.4052 - accuracy: 0.7000 - 24ms/epoch - 5ms/step

print(perf)

     loss  accuracy 
0.4051836 0.7000000

perf <- model %>% evaluate(x_test, y_test)

2/2 - 0s - loss: 0.5910 - accuracy: 0.6000 - 18ms/epoch - 9ms/step

print(perf)

     loss  accuracy 
0.5910424 0.6000000