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     1.2.1     ✔ readr     2.2.0
✔ forcats   1.0.1     ✔ stringr   1.6.0
✔ ggplot2   4.0.2     ✔ tibble    3.3.1
✔ lubridate 1.9.5     ✔ tidyr     1.3.2
✔ purrr     1.2.2     
── 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 1.4.1 ──
✔ broom        1.0.12     ✔ rsample      1.3.2 
✔ dials        1.4.2      ✔ tailor       0.1.0 
✔ infer        1.1.0      ✔ tune         2.0.1 
✔ modeldata    1.5.1      ✔ workflows    1.3.0 
✔ parsnip      1.5.0      ✔ workflowsets 1.1.1 
✔ recipes      1.3.2      ✔ yardstick    1.4.0 
── 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(keras3)


Attaching package: 'keras3'

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

    get_weights

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

    generate

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()  |> as.numeric() 

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

dim(x_train)

[1] 160   2

dim(x_test)

[1] 40  2

dim(y_train)

NULL

dim(y_test)

NULL

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 = 1, activation = 'sigmoid')
model |> summary()

Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                      ┃ Output Shape             ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ dense (Dense)                     │ (None, 4)                │            12 │
├───────────────────────────────────┼──────────────────────────┼───────────────┤
│ dense_1 (Dense)                   │ (None, 1)                │             5 │
└───────────────────────────────────┴──────────────────────────┴───────────────┘
 Total params: 17 (68.00 B)
 Trainable params: 17 (68.00 B)
 Non-trainable params: 0 (0.00 B)

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 - 2s - 263ms/step - accuracy: 0.4922 - loss: 0.8818 - val_accuracy: 0.4375 - val_loss: 0.8898
Epoch 2/400
7/7 - 0s - 9ms/step - accuracy: 0.4922 - loss: 0.8530 - val_accuracy: 0.4375 - val_loss: 0.8626
Epoch 3/400
7/7 - 0s - 9ms/step - accuracy: 0.4922 - loss: 0.8297 - val_accuracy: 0.4375 - val_loss: 0.8399
Epoch 4/400
7/7 - 0s - 9ms/step - accuracy: 0.4922 - loss: 0.8100 - val_accuracy: 0.4375 - val_loss: 0.8183
Epoch 5/400
7/7 - 0s - 9ms/step - accuracy: 0.4922 - loss: 0.7901 - val_accuracy: 0.4375 - val_loss: 0.7960
Epoch 6/400
7/7 - 0s - 9ms/step - accuracy: 0.4844 - loss: 0.7716 - val_accuracy: 0.4375 - val_loss: 0.7764
Epoch 7/400
7/7 - 0s - 8ms/step - accuracy: 0.4766 - loss: 0.7545 - val_accuracy: 0.4375 - val_loss: 0.7590
Epoch 8/400
7/7 - 0s - 9ms/step - accuracy: 0.4766 - loss: 0.7385 - val_accuracy: 0.4375 - val_loss: 0.7405
Epoch 9/400
7/7 - 0s - 9ms/step - accuracy: 0.4766 - loss: 0.7221 - val_accuracy: 0.4375 - val_loss: 0.7254
Epoch 10/400
7/7 - 0s - 9ms/step - accuracy: 0.4766 - loss: 0.7085 - val_accuracy: 0.4688 - val_loss: 0.7126
Epoch 11/400
7/7 - 0s - 8ms/step - accuracy: 0.4922 - loss: 0.6956 - val_accuracy: 0.4688 - val_loss: 0.6977
Epoch 12/400
7/7 - 0s - 9ms/step - accuracy: 0.5078 - loss: 0.6814 - val_accuracy: 0.5312 - val_loss: 0.6831
Epoch 13/400
7/7 - 0s - 9ms/step - accuracy: 0.5469 - loss: 0.6679 - val_accuracy: 0.5312 - val_loss: 0.6707
Epoch 14/400
7/7 - 0s - 9ms/step - accuracy: 0.5625 - loss: 0.6552 - val_accuracy: 0.5625 - val_loss: 0.6565
Epoch 15/400
7/7 - 0s - 8ms/step - accuracy: 0.5859 - loss: 0.6427 - val_accuracy: 0.5938 - val_loss: 0.6426
Epoch 16/400
7/7 - 0s - 9ms/step - accuracy: 0.6172 - loss: 0.6297 - val_accuracy: 0.5938 - val_loss: 0.6310
Epoch 17/400
7/7 - 0s - 8ms/step - accuracy: 0.6484 - loss: 0.6188 - val_accuracy: 0.5938 - val_loss: 0.6203
Epoch 18/400
7/7 - 0s - 8ms/step - accuracy: 0.6797 - loss: 0.6075 - val_accuracy: 0.6562 - val_loss: 0.6098
Epoch 19/400
7/7 - 0s - 8ms/step - accuracy: 0.6875 - loss: 0.5967 - val_accuracy: 0.6875 - val_loss: 0.5981
Epoch 20/400
7/7 - 0s - 8ms/step - accuracy: 0.6953 - loss: 0.5856 - val_accuracy: 0.6875 - val_loss: 0.5870
Epoch 21/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5744 - val_accuracy: 0.7188 - val_loss: 0.5757
Epoch 22/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5645 - val_accuracy: 0.7188 - val_loss: 0.5673
Epoch 23/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5558 - val_accuracy: 0.7188 - val_loss: 0.5559
Epoch 24/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5461 - val_accuracy: 0.7188 - val_loss: 0.5461
Epoch 25/400
7/7 - 0s - 8ms/step - accuracy: 0.7266 - loss: 0.5372 - val_accuracy: 0.7188 - val_loss: 0.5385
Epoch 26/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5297 - val_accuracy: 0.7188 - val_loss: 0.5295
Epoch 27/400
7/7 - 0s - 9ms/step - accuracy: 0.7344 - loss: 0.5220 - val_accuracy: 0.7188 - val_loss: 0.5214
Epoch 28/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.5147 - val_accuracy: 0.7188 - val_loss: 0.5128
Epoch 29/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.5078 - val_accuracy: 0.7188 - val_loss: 0.5059
Epoch 30/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.5016 - val_accuracy: 0.7188 - val_loss: 0.4981
Epoch 31/400
7/7 - 0s - 9ms/step - accuracy: 0.7578 - loss: 0.4957 - val_accuracy: 0.7188 - val_loss: 0.4907
Epoch 32/400
7/7 - 0s - 9ms/step - accuracy: 0.7578 - loss: 0.4903 - val_accuracy: 0.7188 - val_loss: 0.4835
Epoch 33/400
7/7 - 0s - 8ms/step - accuracy: 0.7734 - loss: 0.4845 - val_accuracy: 0.7812 - val_loss: 0.4774
Epoch 34/400
7/7 - 0s - 8ms/step - accuracy: 0.7969 - loss: 0.4785 - val_accuracy: 0.7812 - val_loss: 0.4701
Epoch 35/400
7/7 - 0s - 8ms/step - accuracy: 0.8359 - loss: 0.4730 - val_accuracy: 0.7812 - val_loss: 0.4643
Epoch 36/400
7/7 - 0s - 8ms/step - accuracy: 0.8516 - loss: 0.4680 - val_accuracy: 0.7812 - val_loss: 0.4583
Epoch 37/400
7/7 - 0s - 9ms/step - accuracy: 0.8516 - loss: 0.4633 - val_accuracy: 0.8125 - val_loss: 0.4527
Epoch 38/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4586 - val_accuracy: 0.8125 - val_loss: 0.4478
Epoch 39/400
7/7 - 0s - 9ms/step - accuracy: 0.8672 - loss: 0.4540 - val_accuracy: 0.8125 - val_loss: 0.4415
Epoch 40/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4493 - val_accuracy: 0.8438 - val_loss: 0.4370
Epoch 41/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4452 - val_accuracy: 0.8438 - val_loss: 0.4334
Epoch 42/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4414 - val_accuracy: 0.8438 - val_loss: 0.4303
Epoch 43/400
7/7 - 0s - 9ms/step - accuracy: 0.8672 - loss: 0.4376 - val_accuracy: 0.8438 - val_loss: 0.4273
Epoch 44/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4341 - val_accuracy: 0.8438 - val_loss: 0.4236
Epoch 45/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4310 - val_accuracy: 0.8438 - val_loss: 0.4204
Epoch 46/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4273 - val_accuracy: 0.8438 - val_loss: 0.4167
Epoch 47/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.4242 - val_accuracy: 0.8438 - val_loss: 0.4151
Epoch 48/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.4213 - val_accuracy: 0.8438 - val_loss: 0.4117
Epoch 49/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.4189 - val_accuracy: 0.8438 - val_loss: 0.4091
Epoch 50/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.4164 - val_accuracy: 0.8438 - val_loss: 0.4067
Epoch 51/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.4139 - val_accuracy: 0.8438 - val_loss: 0.4052
Epoch 52/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.4114 - val_accuracy: 0.8438 - val_loss: 0.4028
Epoch 53/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.4088 - val_accuracy: 0.8438 - val_loss: 0.4014
Epoch 54/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.4064 - val_accuracy: 0.8438 - val_loss: 0.3993
Epoch 55/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.4041 - val_accuracy: 0.8750 - val_loss: 0.3971
Epoch 56/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.4017 - val_accuracy: 0.8750 - val_loss: 0.3957
Epoch 57/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3992 - val_accuracy: 0.8750 - val_loss: 0.3922
Epoch 58/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.3969 - val_accuracy: 0.8750 - val_loss: 0.3908
Epoch 59/400
7/7 - 0s - 8ms/step - accuracy: 0.8828 - loss: 0.3948 - val_accuracy: 0.8750 - val_loss: 0.3888
Epoch 60/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3927 - val_accuracy: 0.8750 - val_loss: 0.3857
Epoch 61/400
7/7 - 0s - 8ms/step - accuracy: 0.8828 - loss: 0.3902 - val_accuracy: 0.8750 - val_loss: 0.3834
Epoch 62/400
7/7 - 0s - 9ms/step - accuracy: 0.8828 - loss: 0.3880 - val_accuracy: 0.8750 - val_loss: 0.3816
Epoch 63/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3859 - val_accuracy: 0.8750 - val_loss: 0.3786
Epoch 64/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3838 - val_accuracy: 0.8750 - val_loss: 0.3760
Epoch 65/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3819 - val_accuracy: 0.8750 - val_loss: 0.3737
Epoch 66/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3800 - val_accuracy: 0.8750 - val_loss: 0.3712
Epoch 67/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3783 - val_accuracy: 0.8750 - val_loss: 0.3687
Epoch 68/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3765 - val_accuracy: 0.8750 - val_loss: 0.3666
Epoch 69/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3747 - val_accuracy: 0.8750 - val_loss: 0.3656
Epoch 70/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3730 - val_accuracy: 0.8750 - val_loss: 0.3634
Epoch 71/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3713 - val_accuracy: 0.8750 - val_loss: 0.3614
Epoch 72/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3697 - val_accuracy: 0.8750 - val_loss: 0.3592
Epoch 73/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3681 - val_accuracy: 0.8750 - val_loss: 0.3586
Epoch 74/400
7/7 - 0s - 8ms/step - accuracy: 0.8984 - loss: 0.3664 - val_accuracy: 0.8750 - val_loss: 0.3569
Epoch 75/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.3646 - val_accuracy: 0.9062 - val_loss: 0.3544
Epoch 76/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3631 - val_accuracy: 0.9062 - val_loss: 0.3521
Epoch 77/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3613 - val_accuracy: 0.9062 - val_loss: 0.3504
Epoch 78/400
7/7 - 0s - 8ms/step - accuracy: 0.9141 - loss: 0.3599 - val_accuracy: 0.9062 - val_loss: 0.3490
Epoch 79/400
7/7 - 0s - 8ms/step - accuracy: 0.9141 - loss: 0.3583 - val_accuracy: 0.9062 - val_loss: 0.3486
Epoch 80/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3568 - val_accuracy: 0.9062 - val_loss: 0.3475
Epoch 81/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3554 - val_accuracy: 0.9062 - val_loss: 0.3453
Epoch 82/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3539 - val_accuracy: 0.9062 - val_loss: 0.3426
Epoch 83/400
7/7 - 0s - 8ms/step - accuracy: 0.9141 - loss: 0.3523 - val_accuracy: 0.9062 - val_loss: 0.3410
Epoch 84/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3508 - val_accuracy: 0.9062 - val_loss: 0.3402
Epoch 85/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3491 - val_accuracy: 0.9062 - val_loss: 0.3387
Epoch 86/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.3479 - val_accuracy: 0.9062 - val_loss: 0.3372
Epoch 87/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3465 - val_accuracy: 0.9062 - val_loss: 0.3361
Epoch 88/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.3449 - val_accuracy: 0.9062 - val_loss: 0.3352
Epoch 89/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3437 - val_accuracy: 0.9062 - val_loss: 0.3333
Epoch 90/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3420 - val_accuracy: 0.9062 - val_loss: 0.3315
Epoch 91/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.3408 - val_accuracy: 0.9062 - val_loss: 0.3305
Epoch 92/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.3392 - val_accuracy: 0.9062 - val_loss: 0.3286
Epoch 93/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.3380 - val_accuracy: 0.9062 - val_loss: 0.3269
Epoch 94/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3368 - val_accuracy: 0.9062 - val_loss: 0.3253
Epoch 95/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3354 - val_accuracy: 0.9062 - val_loss: 0.3250
Epoch 96/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.3341 - val_accuracy: 0.9062 - val_loss: 0.3232
Epoch 97/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3327 - val_accuracy: 0.9062 - val_loss: 0.3219
Epoch 98/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.3314 - val_accuracy: 0.9062 - val_loss: 0.3198
Epoch 99/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3303 - val_accuracy: 0.9062 - val_loss: 0.3182
Epoch 100/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.3290 - val_accuracy: 0.9062 - val_loss: 0.3170
Epoch 101/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.3278 - val_accuracy: 0.9062 - val_loss: 0.3160
Epoch 102/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.3264 - val_accuracy: 0.9062 - val_loss: 0.3150
Epoch 103/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.3251 - val_accuracy: 0.9062 - val_loss: 0.3132
Epoch 104/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.3239 - val_accuracy: 0.9062 - val_loss: 0.3112
Epoch 105/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3223 - val_accuracy: 0.9062 - val_loss: 0.3099
Epoch 106/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3212 - val_accuracy: 0.9062 - val_loss: 0.3090
Epoch 107/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3198 - val_accuracy: 0.9062 - val_loss: 0.3080
Epoch 108/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3183 - val_accuracy: 0.9062 - val_loss: 0.3060
Epoch 109/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3172 - val_accuracy: 0.9062 - val_loss: 0.3043
Epoch 110/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3163 - val_accuracy: 0.9062 - val_loss: 0.3023
Epoch 111/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3146 - val_accuracy: 0.9062 - val_loss: 0.3009
Epoch 112/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3140 - val_accuracy: 0.9062 - val_loss: 0.3000
Epoch 113/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3125 - val_accuracy: 0.9062 - val_loss: 0.2991
Epoch 114/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3114 - val_accuracy: 0.9062 - val_loss: 0.2978
Epoch 115/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3101 - val_accuracy: 0.9062 - val_loss: 0.2957
Epoch 116/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3091 - val_accuracy: 0.9062 - val_loss: 0.2949
Epoch 117/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3080 - val_accuracy: 0.9062 - val_loss: 0.2943
Epoch 118/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3069 - val_accuracy: 0.9062 - val_loss: 0.2939
Epoch 119/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3058 - val_accuracy: 0.9062 - val_loss: 0.2927
Epoch 120/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3048 - val_accuracy: 0.9062 - val_loss: 0.2913
Epoch 121/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.3038 - val_accuracy: 0.9062 - val_loss: 0.2904
Epoch 122/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3031 - val_accuracy: 0.9062 - val_loss: 0.2890
Epoch 123/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3020 - val_accuracy: 0.9062 - val_loss: 0.2875
Epoch 124/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.3006 - val_accuracy: 0.9062 - val_loss: 0.2864
Epoch 125/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2996 - val_accuracy: 0.9062 - val_loss: 0.2858
Epoch 126/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2988 - val_accuracy: 0.9062 - val_loss: 0.2843
Epoch 127/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2976 - val_accuracy: 0.9062 - val_loss: 0.2832
Epoch 128/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2965 - val_accuracy: 0.9062 - val_loss: 0.2817
Epoch 129/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2957 - val_accuracy: 0.9062 - val_loss: 0.2804
Epoch 130/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2943 - val_accuracy: 0.9062 - val_loss: 0.2796
Epoch 131/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2933 - val_accuracy: 0.9062 - val_loss: 0.2777
Epoch 132/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2923 - val_accuracy: 0.9062 - val_loss: 0.2768
Epoch 133/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2914 - val_accuracy: 0.9062 - val_loss: 0.2755
Epoch 134/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2904 - val_accuracy: 0.9062 - val_loss: 0.2743
Epoch 135/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2895 - val_accuracy: 0.9062 - val_loss: 0.2726
Epoch 136/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2884 - val_accuracy: 0.9062 - val_loss: 0.2721
Epoch 137/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2879 - val_accuracy: 0.9062 - val_loss: 0.2704
Epoch 138/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2866 - val_accuracy: 0.9062 - val_loss: 0.2694
Epoch 139/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2857 - val_accuracy: 0.9062 - val_loss: 0.2683
Epoch 140/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2848 - val_accuracy: 0.9062 - val_loss: 0.2670
Epoch 141/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2839 - val_accuracy: 0.9062 - val_loss: 0.2662
Epoch 142/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2829 - val_accuracy: 0.9062 - val_loss: 0.2644
Epoch 143/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2820 - val_accuracy: 0.9062 - val_loss: 0.2624
Epoch 144/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2811 - val_accuracy: 0.9062 - val_loss: 0.2610
Epoch 145/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2805 - val_accuracy: 0.9062 - val_loss: 0.2605
Epoch 146/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2795 - val_accuracy: 0.9062 - val_loss: 0.2602
Epoch 147/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2787 - val_accuracy: 0.9062 - val_loss: 0.2592
Epoch 148/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2778 - val_accuracy: 0.9062 - val_loss: 0.2580
Epoch 149/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2770 - val_accuracy: 0.9062 - val_loss: 0.2581
Epoch 150/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2760 - val_accuracy: 0.9062 - val_loss: 0.2567
Epoch 151/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2752 - val_accuracy: 0.9062 - val_loss: 0.2560
Epoch 152/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2745 - val_accuracy: 0.9062 - val_loss: 0.2553
Epoch 153/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2736 - val_accuracy: 0.9062 - val_loss: 0.2556
Epoch 154/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2727 - val_accuracy: 0.9062 - val_loss: 0.2542
Epoch 155/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2718 - val_accuracy: 0.9062 - val_loss: 0.2525
Epoch 156/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2710 - val_accuracy: 0.9062 - val_loss: 0.2513
Epoch 157/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2702 - val_accuracy: 0.9062 - val_loss: 0.2506
Epoch 158/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2695 - val_accuracy: 0.9062 - val_loss: 0.2501
Epoch 159/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2685 - val_accuracy: 0.9062 - val_loss: 0.2498
Epoch 160/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2678 - val_accuracy: 0.9062 - val_loss: 0.2485
Epoch 161/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2670 - val_accuracy: 0.9062 - val_loss: 0.2468
Epoch 162/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2661 - val_accuracy: 0.9062 - val_loss: 0.2461
Epoch 163/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2653 - val_accuracy: 0.9062 - val_loss: 0.2449
Epoch 164/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2645 - val_accuracy: 0.9062 - val_loss: 0.2434
Epoch 165/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2635 - val_accuracy: 0.9062 - val_loss: 0.2426
Epoch 166/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2630 - val_accuracy: 0.9062 - val_loss: 0.2423
Epoch 167/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2621 - val_accuracy: 0.9062 - val_loss: 0.2419
Epoch 168/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2612 - val_accuracy: 0.9062 - val_loss: 0.2408
Epoch 169/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2606 - val_accuracy: 0.9062 - val_loss: 0.2405
Epoch 170/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2599 - val_accuracy: 0.9062 - val_loss: 0.2403
Epoch 171/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2591 - val_accuracy: 0.9062 - val_loss: 0.2390
Epoch 172/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2583 - val_accuracy: 0.9062 - val_loss: 0.2376
Epoch 173/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2575 - val_accuracy: 0.9062 - val_loss: 0.2374
Epoch 174/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2566 - val_accuracy: 0.9062 - val_loss: 0.2366
Epoch 175/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2561 - val_accuracy: 0.9062 - val_loss: 0.2364
Epoch 176/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2554 - val_accuracy: 0.9062 - val_loss: 0.2353
Epoch 177/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2547 - val_accuracy: 0.9062 - val_loss: 0.2336
Epoch 178/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2539 - val_accuracy: 0.9062 - val_loss: 0.2336
Epoch 179/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2532 - val_accuracy: 0.9062 - val_loss: 0.2331
Epoch 180/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2526 - val_accuracy: 0.9062 - val_loss: 0.2331
Epoch 181/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2521 - val_accuracy: 0.9062 - val_loss: 0.2318
Epoch 182/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2515 - val_accuracy: 0.9062 - val_loss: 0.2311
Epoch 183/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2506 - val_accuracy: 0.9062 - val_loss: 0.2301
Epoch 184/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2499 - val_accuracy: 0.9062 - val_loss: 0.2291
Epoch 185/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2492 - val_accuracy: 0.9062 - val_loss: 0.2278
Epoch 186/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2484 - val_accuracy: 0.9062 - val_loss: 0.2262
Epoch 187/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2479 - val_accuracy: 0.9062 - val_loss: 0.2261
Epoch 188/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2471 - val_accuracy: 0.9062 - val_loss: 0.2245
Epoch 189/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2463 - val_accuracy: 0.9062 - val_loss: 0.2247
Epoch 190/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2457 - val_accuracy: 0.9062 - val_loss: 0.2229
Epoch 191/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2450 - val_accuracy: 0.9062 - val_loss: 0.2222
Epoch 192/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2445 - val_accuracy: 0.9062 - val_loss: 0.2221
Epoch 193/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2438 - val_accuracy: 0.9062 - val_loss: 0.2223
Epoch 194/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2432 - val_accuracy: 0.9062 - val_loss: 0.2215
Epoch 195/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2425 - val_accuracy: 0.9062 - val_loss: 0.2201
Epoch 196/400
7/7 - 0s - 9ms/step - accuracy: 0.9297 - loss: 0.2420 - val_accuracy: 0.9062 - val_loss: 0.2193
Epoch 197/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2414 - val_accuracy: 0.9062 - val_loss: 0.2192
Epoch 198/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2407 - val_accuracy: 0.9062 - val_loss: 0.2180
Epoch 199/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2403 - val_accuracy: 0.9062 - val_loss: 0.2173
Epoch 200/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2396 - val_accuracy: 0.9062 - val_loss: 0.2158
Epoch 201/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2389 - val_accuracy: 0.9062 - val_loss: 0.2158
Epoch 202/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2384 - val_accuracy: 0.9062 - val_loss: 0.2149
Epoch 203/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2378 - val_accuracy: 0.9062 - val_loss: 0.2135
Epoch 204/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2372 - val_accuracy: 0.9062 - val_loss: 0.2127
Epoch 205/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2366 - val_accuracy: 0.9062 - val_loss: 0.2114
Epoch 206/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2359 - val_accuracy: 0.9062 - val_loss: 0.2106
Epoch 207/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2355 - val_accuracy: 0.9062 - val_loss: 0.2096
Epoch 208/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2348 - val_accuracy: 0.9062 - val_loss: 0.2095
Epoch 209/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2341 - val_accuracy: 0.9062 - val_loss: 0.2090
Epoch 210/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2336 - val_accuracy: 0.9062 - val_loss: 0.2091
Epoch 211/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2330 - val_accuracy: 0.9062 - val_loss: 0.2078
Epoch 212/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2323 - val_accuracy: 0.9062 - val_loss: 0.2083
Epoch 213/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2322 - val_accuracy: 0.9062 - val_loss: 0.2075
Epoch 214/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2314 - val_accuracy: 0.9062 - val_loss: 0.2081
Epoch 215/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2309 - val_accuracy: 0.9062 - val_loss: 0.2074
Epoch 216/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2304 - val_accuracy: 0.9062 - val_loss: 0.2069
Epoch 217/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2296 - val_accuracy: 0.9062 - val_loss: 0.2058
Epoch 218/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2293 - val_accuracy: 0.9062 - val_loss: 0.2054
Epoch 219/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2287 - val_accuracy: 0.9062 - val_loss: 0.2052
Epoch 220/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2281 - val_accuracy: 0.9062 - val_loss: 0.2037
Epoch 221/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2276 - val_accuracy: 0.9062 - val_loss: 0.2033
Epoch 222/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2272 - val_accuracy: 0.9062 - val_loss: 0.2029
Epoch 223/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2268 - val_accuracy: 0.9062 - val_loss: 0.2031
Epoch 224/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2262 - val_accuracy: 0.9062 - val_loss: 0.2021
Epoch 225/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2258 - val_accuracy: 0.9062 - val_loss: 0.2009
Epoch 226/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2251 - val_accuracy: 0.9062 - val_loss: 0.2004
Epoch 227/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2249 - val_accuracy: 0.9062 - val_loss: 0.1997
Epoch 228/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2243 - val_accuracy: 0.9062 - val_loss: 0.1993
Epoch 229/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2239 - val_accuracy: 0.9062 - val_loss: 0.1990
Epoch 230/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2234 - val_accuracy: 0.9062 - val_loss: 0.1981
Epoch 231/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2228 - val_accuracy: 0.9062 - val_loss: 0.1967
Epoch 232/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2223 - val_accuracy: 0.9062 - val_loss: 0.1960
Epoch 233/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2218 - val_accuracy: 0.9062 - val_loss: 0.1951
Epoch 234/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2214 - val_accuracy: 0.9062 - val_loss: 0.1949
Epoch 235/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2211 - val_accuracy: 0.9062 - val_loss: 0.1947
Epoch 236/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2206 - val_accuracy: 0.9062 - val_loss: 0.1947
Epoch 237/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2201 - val_accuracy: 0.9062 - val_loss: 0.1948
Epoch 238/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2195 - val_accuracy: 0.9062 - val_loss: 0.1937
Epoch 239/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2192 - val_accuracy: 0.9062 - val_loss: 0.1929
Epoch 240/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2184 - val_accuracy: 0.9062 - val_loss: 0.1927
Epoch 241/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2182 - val_accuracy: 0.9375 - val_loss: 0.1920
Epoch 242/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2177 - val_accuracy: 0.9375 - val_loss: 0.1913
Epoch 243/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2173 - val_accuracy: 0.9375 - val_loss: 0.1913
Epoch 244/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2167 - val_accuracy: 0.9375 - val_loss: 0.1905
Epoch 245/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2162 - val_accuracy: 0.9375 - val_loss: 0.1901
Epoch 246/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2157 - val_accuracy: 0.9375 - val_loss: 0.1894
Epoch 247/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2154 - val_accuracy: 0.9375 - val_loss: 0.1897
Epoch 248/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2147 - val_accuracy: 0.9375 - val_loss: 0.1897
Epoch 249/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2146 - val_accuracy: 0.9375 - val_loss: 0.1896
Epoch 250/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2140 - val_accuracy: 0.9375 - val_loss: 0.1884
Epoch 251/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2137 - val_accuracy: 0.9375 - val_loss: 0.1882
Epoch 252/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2132 - val_accuracy: 0.9375 - val_loss: 0.1880
Epoch 253/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2127 - val_accuracy: 0.9375 - val_loss: 0.1874
Epoch 254/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2123 - val_accuracy: 0.9375 - val_loss: 0.1869
Epoch 255/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2119 - val_accuracy: 0.9375 - val_loss: 0.1864
Epoch 256/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2115 - val_accuracy: 0.9375 - val_loss: 0.1853
Epoch 257/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2110 - val_accuracy: 0.9375 - val_loss: 0.1849
Epoch 258/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2104 - val_accuracy: 0.9375 - val_loss: 0.1835
Epoch 259/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2100 - val_accuracy: 0.9375 - val_loss: 0.1823
Epoch 260/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2095 - val_accuracy: 0.9375 - val_loss: 0.1829
Epoch 261/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2091 - val_accuracy: 0.9375 - val_loss: 0.1823
Epoch 262/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2090 - val_accuracy: 0.9375 - val_loss: 0.1820
Epoch 263/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2084 - val_accuracy: 0.9375 - val_loss: 0.1809
Epoch 264/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2081 - val_accuracy: 0.9375 - val_loss: 0.1803
Epoch 265/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2076 - val_accuracy: 0.9375 - val_loss: 0.1801
Epoch 266/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2072 - val_accuracy: 0.9375 - val_loss: 0.1801
Epoch 267/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2068 - val_accuracy: 0.9375 - val_loss: 0.1797
Epoch 268/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2064 - val_accuracy: 0.9375 - val_loss: 0.1801
Epoch 269/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2058 - val_accuracy: 0.9375 - val_loss: 0.1794
Epoch 270/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2054 - val_accuracy: 0.9375 - val_loss: 0.1783
Epoch 271/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2050 - val_accuracy: 0.9375 - val_loss: 0.1776
Epoch 272/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2046 - val_accuracy: 0.9375 - val_loss: 0.1769
Epoch 273/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2040 - val_accuracy: 0.9375 - val_loss: 0.1765
Epoch 274/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2038 - val_accuracy: 0.9375 - val_loss: 0.1759
Epoch 275/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2034 - val_accuracy: 0.9375 - val_loss: 0.1750
Epoch 276/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2028 - val_accuracy: 0.9375 - val_loss: 0.1739
Epoch 277/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2023 - val_accuracy: 0.9375 - val_loss: 0.1737
Epoch 278/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2018 - val_accuracy: 0.9375 - val_loss: 0.1734
Epoch 279/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2017 - val_accuracy: 0.9375 - val_loss: 0.1731
Epoch 280/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2009 - val_accuracy: 0.9375 - val_loss: 0.1726
Epoch 281/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2007 - val_accuracy: 0.9375 - val_loss: 0.1730
Epoch 282/400
7/7 - 0s - 10ms/step - accuracy: 0.9609 - loss: 0.2001 - val_accuracy: 0.9375 - val_loss: 0.1725
Epoch 283/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1996 - val_accuracy: 0.9375 - val_loss: 0.1728
Epoch 284/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1994 - val_accuracy: 0.9375 - val_loss: 0.1725
Epoch 285/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1990 - val_accuracy: 0.9375 - val_loss: 0.1722
Epoch 286/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1985 - val_accuracy: 0.9375 - val_loss: 0.1713
Epoch 287/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1983 - val_accuracy: 0.9375 - val_loss: 0.1702
Epoch 288/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1978 - val_accuracy: 0.9375 - val_loss: 0.1696
Epoch 289/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1973 - val_accuracy: 0.9375 - val_loss: 0.1691
Epoch 290/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1971 - val_accuracy: 0.9375 - val_loss: 0.1681
Epoch 291/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1965 - val_accuracy: 0.9375 - val_loss: 0.1681
Epoch 292/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1962 - val_accuracy: 0.9375 - val_loss: 0.1677
Epoch 293/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1959 - val_accuracy: 0.9375 - val_loss: 0.1674
Epoch 294/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1953 - val_accuracy: 0.9375 - val_loss: 0.1676
Epoch 295/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1951 - val_accuracy: 0.9375 - val_loss: 0.1671
Epoch 296/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1944 - val_accuracy: 0.9375 - val_loss: 0.1672
Epoch 297/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1939 - val_accuracy: 0.9375 - val_loss: 0.1671
Epoch 298/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1937 - val_accuracy: 0.9375 - val_loss: 0.1676
Epoch 299/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1934 - val_accuracy: 0.9375 - val_loss: 0.1673
Epoch 300/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1930 - val_accuracy: 0.9375 - val_loss: 0.1669
Epoch 301/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1926 - val_accuracy: 0.9375 - val_loss: 0.1676
Epoch 302/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1923 - val_accuracy: 0.9375 - val_loss: 0.1667
Epoch 303/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1919 - val_accuracy: 0.9375 - val_loss: 0.1665
Epoch 304/400
7/7 - 0s - 10ms/step - accuracy: 0.9609 - loss: 0.1916 - val_accuracy: 0.9375 - val_loss: 0.1660
Epoch 305/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1910 - val_accuracy: 0.9375 - val_loss: 0.1649
Epoch 306/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1906 - val_accuracy: 0.9375 - val_loss: 0.1635
Epoch 307/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1903 - val_accuracy: 0.9375 - val_loss: 0.1634
Epoch 308/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1900 - val_accuracy: 0.9375 - val_loss: 0.1628
Epoch 309/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1897 - val_accuracy: 0.9375 - val_loss: 0.1623
Epoch 310/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1892 - val_accuracy: 0.9375 - val_loss: 0.1614
Epoch 311/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1889 - val_accuracy: 0.9375 - val_loss: 0.1618
Epoch 312/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1887 - val_accuracy: 0.9375 - val_loss: 0.1617
Epoch 313/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1881 - val_accuracy: 0.9375 - val_loss: 0.1614
Epoch 314/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1879 - val_accuracy: 0.9375 - val_loss: 0.1609
Epoch 315/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1875 - val_accuracy: 0.9375 - val_loss: 0.1601
Epoch 316/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1872 - val_accuracy: 0.9375 - val_loss: 0.1609
Epoch 317/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1868 - val_accuracy: 0.9375 - val_loss: 0.1597
Epoch 318/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1863 - val_accuracy: 0.9375 - val_loss: 0.1601
Epoch 319/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1860 - val_accuracy: 0.9375 - val_loss: 0.1594
Epoch 320/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1856 - val_accuracy: 0.9375 - val_loss: 0.1590
Epoch 321/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1853 - val_accuracy: 0.9375 - val_loss: 0.1586
Epoch 322/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1849 - val_accuracy: 0.9375 - val_loss: 0.1583
Epoch 323/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1848 - val_accuracy: 0.9375 - val_loss: 0.1576
Epoch 324/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1843 - val_accuracy: 0.9375 - val_loss: 0.1574
Epoch 325/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1840 - val_accuracy: 0.9375 - val_loss: 0.1574
Epoch 326/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1836 - val_accuracy: 0.9375 - val_loss: 0.1569
Epoch 327/400
7/7 - 0s - 10ms/step - accuracy: 0.9609 - loss: 0.1831 - val_accuracy: 0.9375 - val_loss: 0.1569
Epoch 328/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1828 - val_accuracy: 0.9375 - val_loss: 0.1562
Epoch 329/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1825 - val_accuracy: 0.9375 - val_loss: 0.1553
Epoch 330/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1822 - val_accuracy: 0.9375 - val_loss: 0.1547
Epoch 331/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1819 - val_accuracy: 0.9375 - val_loss: 0.1542
Epoch 332/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1814 - val_accuracy: 0.9375 - val_loss: 0.1539
Epoch 333/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1813 - val_accuracy: 0.9375 - val_loss: 0.1534
Epoch 334/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1808 - val_accuracy: 0.9375 - val_loss: 0.1530
Epoch 335/400
7/7 - 0s - 10ms/step - accuracy: 0.9609 - loss: 0.1804 - val_accuracy: 0.9375 - val_loss: 0.1539
Epoch 336/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1802 - val_accuracy: 0.9375 - val_loss: 0.1535
Epoch 337/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1796 - val_accuracy: 0.9375 - val_loss: 0.1533
Epoch 338/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1795 - val_accuracy: 0.9375 - val_loss: 0.1524
Epoch 339/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1791 - val_accuracy: 0.9375 - val_loss: 0.1518
Epoch 340/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1788 - val_accuracy: 0.9375 - val_loss: 0.1518
Epoch 341/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1785 - val_accuracy: 0.9375 - val_loss: 0.1515
Epoch 342/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1784 - val_accuracy: 0.9375 - val_loss: 0.1515
Epoch 343/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1779 - val_accuracy: 0.9375 - val_loss: 0.1513
Epoch 344/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1777 - val_accuracy: 0.9375 - val_loss: 0.1505
Epoch 345/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1773 - val_accuracy: 0.9375 - val_loss: 0.1511
Epoch 346/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1770 - val_accuracy: 0.9375 - val_loss: 0.1517
Epoch 347/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1766 - val_accuracy: 0.9375 - val_loss: 0.1518
Epoch 348/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1766 - val_accuracy: 0.9375 - val_loss: 0.1517
Epoch 349/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1761 - val_accuracy: 0.9375 - val_loss: 0.1510
Epoch 350/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1756 - val_accuracy: 0.9375 - val_loss: 0.1507
Epoch 351/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1755 - val_accuracy: 0.9375 - val_loss: 0.1497
Epoch 352/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1750 - val_accuracy: 0.9375 - val_loss: 0.1491
Epoch 353/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1748 - val_accuracy: 0.9375 - val_loss: 0.1490
Epoch 354/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1744 - val_accuracy: 0.9375 - val_loss: 0.1485
Epoch 355/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1741 - val_accuracy: 0.9375 - val_loss: 0.1489
Epoch 356/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1737 - val_accuracy: 0.9375 - val_loss: 0.1484
Epoch 357/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1734 - val_accuracy: 0.9375 - val_loss: 0.1480
Epoch 358/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1731 - val_accuracy: 0.9375 - val_loss: 0.1482
Epoch 359/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1729 - val_accuracy: 0.9375 - val_loss: 0.1479
Epoch 360/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1725 - val_accuracy: 0.9375 - val_loss: 0.1479
Epoch 361/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1722 - val_accuracy: 0.9375 - val_loss: 0.1473
Epoch 362/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1719 - val_accuracy: 0.9375 - val_loss: 0.1464
Epoch 363/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1715 - val_accuracy: 0.9375 - val_loss: 0.1460
Epoch 364/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1714 - val_accuracy: 0.9375 - val_loss: 0.1465
Epoch 365/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1708 - val_accuracy: 0.9375 - val_loss: 0.1456
Epoch 366/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1705 - val_accuracy: 0.9375 - val_loss: 0.1455
Epoch 367/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1704 - val_accuracy: 0.9375 - val_loss: 0.1461
Epoch 368/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1700 - val_accuracy: 0.9375 - val_loss: 0.1466
Epoch 369/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1698 - val_accuracy: 0.9375 - val_loss: 0.1463
Epoch 370/400
7/7 - 0s - 10ms/step - accuracy: 0.9609 - loss: 0.1696 - val_accuracy: 0.9375 - val_loss: 0.1459
Epoch 371/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1692 - val_accuracy: 0.9375 - val_loss: 0.1458
Epoch 372/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1690 - val_accuracy: 0.9375 - val_loss: 0.1450
Epoch 373/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1686 - val_accuracy: 0.9375 - val_loss: 0.1446
Epoch 374/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1684 - val_accuracy: 0.9375 - val_loss: 0.1441
Epoch 375/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1682 - val_accuracy: 0.9375 - val_loss: 0.1442
Epoch 376/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1677 - val_accuracy: 0.9375 - val_loss: 0.1438
Epoch 377/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1673 - val_accuracy: 0.9375 - val_loss: 0.1434
Epoch 378/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1673 - val_accuracy: 0.9375 - val_loss: 0.1422
Epoch 379/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1668 - val_accuracy: 0.9375 - val_loss: 0.1423
Epoch 380/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1667 - val_accuracy: 0.9375 - val_loss: 0.1425
Epoch 381/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1664 - val_accuracy: 0.9375 - val_loss: 0.1426
Epoch 382/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1661 - val_accuracy: 0.9375 - val_loss: 0.1423
Epoch 383/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1657 - val_accuracy: 0.9375 - val_loss: 0.1438
Epoch 384/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1655 - val_accuracy: 0.9375 - val_loss: 0.1443
Epoch 385/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1651 - val_accuracy: 0.9375 - val_loss: 0.1448
Epoch 386/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1650 - val_accuracy: 0.9375 - val_loss: 0.1436
Epoch 387/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1647 - val_accuracy: 0.9375 - val_loss: 0.1434
Epoch 388/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1645 - val_accuracy: 0.9375 - val_loss: 0.1425
Epoch 389/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1644 - val_accuracy: 0.9375 - val_loss: 0.1428
Epoch 390/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1642 - val_accuracy: 0.9375 - val_loss: 0.1425
Epoch 391/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1639 - val_accuracy: 0.9375 - val_loss: 0.1420
Epoch 392/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1636 - val_accuracy: 0.9375 - val_loss: 0.1412
Epoch 393/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1634 - val_accuracy: 0.9375 - val_loss: 0.1419
Epoch 394/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.1630 - val_accuracy: 0.9375 - val_loss: 0.1418
Epoch 395/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1627 - val_accuracy: 0.9375 - val_loss: 0.1413
Epoch 396/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1626 - val_accuracy: 0.9375 - val_loss: 0.1425
Epoch 397/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1624 - val_accuracy: 0.9375 - val_loss: 0.1422
Epoch 398/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1620 - val_accuracy: 0.9375 - val_loss: 0.1423
Epoch 399/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1618 - val_accuracy: 0.9375 - val_loss: 0.1422
Epoch 400/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.1614 - val_accuracy: 0.9375 - val_loss: 0.1425

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 - 39ms/step - accuracy: 0.9563 - loss: 0.1573

print(perf)

$accuracy
[1] 0.95625

$loss
[1] 0.1572939

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

2/2 - 0s - 91ms/step - accuracy: 0.8750 - loss: 0.3317

print(perf)

$accuracy
[1] 0.875

$loss
[1] 0.3317485