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() |> 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 (Dense)                     │ (None, 4)                │            12 │
├───────────────────────────────────┼──────────────────────────┼───────────────┤
│ dense_1 (Dense)                   │ (None, 2)                │            10 │
└───────────────────────────────────┴──────────────────────────┴───────────────┘
 Total params: 22 (88.00 B)
 Trainable params: 22 (88.00 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 - 298ms/step - accuracy: 0.4609 - loss: 0.8665 - val_accuracy: 0.5938 - val_loss: 0.6483
Epoch 2/400
7/7 - 0s - 9ms/step - accuracy: 0.4453 - loss: 0.8448 - val_accuracy: 0.6250 - val_loss: 0.6447
Epoch 3/400
7/7 - 0s - 8ms/step - accuracy: 0.4531 - loss: 0.8294 - val_accuracy: 0.6250 - val_loss: 0.6415
Epoch 4/400
7/7 - 0s - 9ms/step - accuracy: 0.4531 - loss: 0.8158 - val_accuracy: 0.6562 - val_loss: 0.6392
Epoch 5/400
7/7 - 0s - 9ms/step - accuracy: 0.4531 - loss: 0.8031 - val_accuracy: 0.6562 - val_loss: 0.6370
Epoch 6/400
7/7 - 0s - 9ms/step - accuracy: 0.4375 - loss: 0.7919 - val_accuracy: 0.6562 - val_loss: 0.6353
Epoch 7/400
7/7 - 0s - 9ms/step - accuracy: 0.4375 - loss: 0.7812 - val_accuracy: 0.6875 - val_loss: 0.6338
Epoch 8/400
7/7 - 0s - 9ms/step - accuracy: 0.4375 - loss: 0.7710 - val_accuracy: 0.6875 - val_loss: 0.6325
Epoch 9/400
7/7 - 0s - 9ms/step - accuracy: 0.4141 - loss: 0.7609 - val_accuracy: 0.6875 - val_loss: 0.6314
Epoch 10/400
7/7 - 0s - 9ms/step - accuracy: 0.4062 - loss: 0.7508 - val_accuracy: 0.6875 - val_loss: 0.6308
Epoch 11/400
7/7 - 0s - 9ms/step - accuracy: 0.4297 - loss: 0.7415 - val_accuracy: 0.6562 - val_loss: 0.6309
Epoch 12/400
7/7 - 0s - 9ms/step - accuracy: 0.4375 - loss: 0.7326 - val_accuracy: 0.6562 - val_loss: 0.6308
Epoch 13/400
7/7 - 0s - 9ms/step - accuracy: 0.4766 - loss: 0.7240 - val_accuracy: 0.6562 - val_loss: 0.6309
Epoch 14/400
7/7 - 0s - 9ms/step - accuracy: 0.4922 - loss: 0.7163 - val_accuracy: 0.6562 - val_loss: 0.6306
Epoch 15/400
7/7 - 0s - 9ms/step - accuracy: 0.4922 - loss: 0.7092 - val_accuracy: 0.6250 - val_loss: 0.6305
Epoch 16/400
7/7 - 0s - 9ms/step - accuracy: 0.4922 - loss: 0.7017 - val_accuracy: 0.5938 - val_loss: 0.6310
Epoch 17/400
7/7 - 0s - 8ms/step - accuracy: 0.4844 - loss: 0.6942 - val_accuracy: 0.5938 - val_loss: 0.6309
Epoch 18/400
7/7 - 0s - 9ms/step - accuracy: 0.4844 - loss: 0.6874 - val_accuracy: 0.5625 - val_loss: 0.6312
Epoch 19/400
7/7 - 0s - 9ms/step - accuracy: 0.4844 - loss: 0.6806 - val_accuracy: 0.5625 - val_loss: 0.6309
Epoch 20/400
7/7 - 0s - 8ms/step - accuracy: 0.4844 - loss: 0.6749 - val_accuracy: 0.5625 - val_loss: 0.6309
Epoch 21/400
7/7 - 0s - 8ms/step - accuracy: 0.4844 - loss: 0.6689 - val_accuracy: 0.5000 - val_loss: 0.6310
Epoch 22/400
7/7 - 0s - 8ms/step - accuracy: 0.4844 - loss: 0.6628 - val_accuracy: 0.5312 - val_loss: 0.6307
Epoch 23/400
7/7 - 0s - 8ms/step - accuracy: 0.4922 - loss: 0.6568 - val_accuracy: 0.5625 - val_loss: 0.6309
Epoch 24/400
7/7 - 0s - 9ms/step - accuracy: 0.5312 - loss: 0.6510 - val_accuracy: 0.5625 - val_loss: 0.6305
Epoch 25/400
7/7 - 0s - 8ms/step - accuracy: 0.5234 - loss: 0.6450 - val_accuracy: 0.5625 - val_loss: 0.6302
Epoch 26/400
7/7 - 0s - 9ms/step - accuracy: 0.5703 - loss: 0.6393 - val_accuracy: 0.5625 - val_loss: 0.6302
Epoch 27/400
7/7 - 0s - 9ms/step - accuracy: 0.6172 - loss: 0.6333 - val_accuracy: 0.5625 - val_loss: 0.6298
Epoch 28/400
7/7 - 0s - 9ms/step - accuracy: 0.6250 - loss: 0.6278 - val_accuracy: 0.5938 - val_loss: 0.6293
Epoch 29/400
7/7 - 0s - 9ms/step - accuracy: 0.6719 - loss: 0.6225 - val_accuracy: 0.5938 - val_loss: 0.6293
Epoch 30/400
7/7 - 0s - 8ms/step - accuracy: 0.6797 - loss: 0.6172 - val_accuracy: 0.5938 - val_loss: 0.6289
Epoch 31/400
7/7 - 0s - 9ms/step - accuracy: 0.6797 - loss: 0.6124 - val_accuracy: 0.5938 - val_loss: 0.6288
Epoch 32/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.6073 - val_accuracy: 0.6250 - val_loss: 0.6289
Epoch 33/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.6019 - val_accuracy: 0.6250 - val_loss: 0.6287
Epoch 34/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5970 - val_accuracy: 0.6250 - val_loss: 0.6291
Epoch 35/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5920 - val_accuracy: 0.6250 - val_loss: 0.6289
Epoch 36/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5873 - val_accuracy: 0.6250 - val_loss: 0.6277
Epoch 37/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5833 - val_accuracy: 0.6250 - val_loss: 0.6275
Epoch 38/400
7/7 - 0s - 8ms/step - accuracy: 0.7344 - loss: 0.5788 - val_accuracy: 0.6250 - val_loss: 0.6276
Epoch 39/400
7/7 - 0s - 9ms/step - accuracy: 0.7266 - loss: 0.5742 - val_accuracy: 0.6250 - val_loss: 0.6269
Epoch 40/400
7/7 - 0s - 9ms/step - accuracy: 0.7266 - loss: 0.5698 - val_accuracy: 0.6250 - val_loss: 0.6265
Epoch 41/400
7/7 - 0s - 8ms/step - accuracy: 0.7344 - loss: 0.5655 - val_accuracy: 0.6250 - val_loss: 0.6249
Epoch 42/400
7/7 - 0s - 8ms/step - accuracy: 0.7344 - loss: 0.5613 - val_accuracy: 0.6250 - val_loss: 0.6235
Epoch 43/400
7/7 - 0s - 8ms/step - accuracy: 0.7344 - loss: 0.5575 - val_accuracy: 0.6250 - val_loss: 0.6230
Epoch 44/400
7/7 - 0s - 9ms/step - accuracy: 0.7344 - loss: 0.5538 - val_accuracy: 0.6250 - val_loss: 0.6228
Epoch 45/400
7/7 - 0s - 9ms/step - accuracy: 0.7344 - loss: 0.5497 - val_accuracy: 0.6250 - val_loss: 0.6227
Epoch 46/400
7/7 - 0s - 9ms/step - accuracy: 0.7344 - loss: 0.5459 - val_accuracy: 0.6250 - val_loss: 0.6220
Epoch 47/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.5421 - val_accuracy: 0.6250 - val_loss: 0.6208
Epoch 48/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.5385 - val_accuracy: 0.6250 - val_loss: 0.6201
Epoch 49/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.5351 - val_accuracy: 0.6250 - val_loss: 0.6189
Epoch 50/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.5316 - val_accuracy: 0.6250 - val_loss: 0.6190
Epoch 51/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.5283 - val_accuracy: 0.6250 - val_loss: 0.6184
Epoch 52/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.5249 - val_accuracy: 0.6250 - val_loss: 0.6177
Epoch 53/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.5216 - val_accuracy: 0.6250 - val_loss: 0.6168
Epoch 54/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.5186 - val_accuracy: 0.6250 - val_loss: 0.6163
Epoch 55/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.5150 - val_accuracy: 0.6250 - val_loss: 0.6156
Epoch 56/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.5119 - val_accuracy: 0.6250 - val_loss: 0.6135
Epoch 57/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.5088 - val_accuracy: 0.6250 - val_loss: 0.6114
Epoch 58/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.5055 - val_accuracy: 0.6250 - val_loss: 0.6089
Epoch 59/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.5020 - val_accuracy: 0.6250 - val_loss: 0.6077
Epoch 60/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4985 - val_accuracy: 0.6250 - val_loss: 0.6064
Epoch 61/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4951 - val_accuracy: 0.6250 - val_loss: 0.6054
Epoch 62/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4918 - val_accuracy: 0.6250 - val_loss: 0.6029
Epoch 63/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4886 - val_accuracy: 0.6250 - val_loss: 0.6015
Epoch 64/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4853 - val_accuracy: 0.6250 - val_loss: 0.5994
Epoch 65/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4821 - val_accuracy: 0.6250 - val_loss: 0.5987
Epoch 66/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4789 - val_accuracy: 0.6250 - val_loss: 0.5973
Epoch 67/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.4759 - val_accuracy: 0.6250 - val_loss: 0.5970
Epoch 68/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4728 - val_accuracy: 0.6250 - val_loss: 0.5959
Epoch 69/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.4700 - val_accuracy: 0.6250 - val_loss: 0.5948
Epoch 70/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.4671 - val_accuracy: 0.6250 - val_loss: 0.5926
Epoch 71/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4642 - val_accuracy: 0.6250 - val_loss: 0.5917
Epoch 72/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4613 - val_accuracy: 0.6250 - val_loss: 0.5917
Epoch 73/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.4585 - val_accuracy: 0.6250 - val_loss: 0.5893
Epoch 74/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.4559 - val_accuracy: 0.6250 - val_loss: 0.5877
Epoch 75/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.4528 - val_accuracy: 0.6250 - val_loss: 0.5865
Epoch 76/400
7/7 - 0s - 8ms/step - accuracy: 0.7500 - loss: 0.4499 - val_accuracy: 0.6250 - val_loss: 0.5858
Epoch 77/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4472 - val_accuracy: 0.6250 - val_loss: 0.5853
Epoch 78/400
7/7 - 0s - 9ms/step - accuracy: 0.7500 - loss: 0.4447 - val_accuracy: 0.6250 - val_loss: 0.5833
Epoch 79/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4422 - val_accuracy: 0.6250 - val_loss: 0.5826
Epoch 80/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4401 - val_accuracy: 0.6250 - val_loss: 0.5818
Epoch 81/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4376 - val_accuracy: 0.6250 - val_loss: 0.5803
Epoch 82/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4352 - val_accuracy: 0.6250 - val_loss: 0.5788
Epoch 83/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4328 - val_accuracy: 0.6250 - val_loss: 0.5787
Epoch 84/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4302 - val_accuracy: 0.6250 - val_loss: 0.5778
Epoch 85/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4276 - val_accuracy: 0.6250 - val_loss: 0.5766
Epoch 86/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4249 - val_accuracy: 0.6250 - val_loss: 0.5759
Epoch 87/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4226 - val_accuracy: 0.6250 - val_loss: 0.5741
Epoch 88/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4201 - val_accuracy: 0.6250 - val_loss: 0.5726
Epoch 89/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4177 - val_accuracy: 0.6250 - val_loss: 0.5704
Epoch 90/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4154 - val_accuracy: 0.6250 - val_loss: 0.5687
Epoch 91/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4130 - val_accuracy: 0.6250 - val_loss: 0.5681
Epoch 92/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4106 - val_accuracy: 0.6250 - val_loss: 0.5665
Epoch 93/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4083 - val_accuracy: 0.6250 - val_loss: 0.5659
Epoch 94/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4061 - val_accuracy: 0.6250 - val_loss: 0.5646
Epoch 95/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4036 - val_accuracy: 0.6250 - val_loss: 0.5637
Epoch 96/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4014 - val_accuracy: 0.6250 - val_loss: 0.5624
Epoch 97/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3990 - val_accuracy: 0.6250 - val_loss: 0.5606
Epoch 98/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3970 - val_accuracy: 0.6250 - val_loss: 0.5606
Epoch 99/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3947 - val_accuracy: 0.6250 - val_loss: 0.5596
Epoch 100/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3924 - val_accuracy: 0.6250 - val_loss: 0.5579
Epoch 101/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3902 - val_accuracy: 0.6250 - val_loss: 0.5564
Epoch 102/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3879 - val_accuracy: 0.6250 - val_loss: 0.5549
Epoch 103/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3856 - val_accuracy: 0.6250 - val_loss: 0.5543
Epoch 104/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3835 - val_accuracy: 0.6250 - val_loss: 0.5533
Epoch 105/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3814 - val_accuracy: 0.6250 - val_loss: 0.5517
Epoch 106/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3793 - val_accuracy: 0.6250 - val_loss: 0.5497
Epoch 107/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3772 - val_accuracy: 0.6250 - val_loss: 0.5481
Epoch 108/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3752 - val_accuracy: 0.6250 - val_loss: 0.5465
Epoch 109/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3732 - val_accuracy: 0.6250 - val_loss: 0.5466
Epoch 110/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3711 - val_accuracy: 0.6250 - val_loss: 0.5448
Epoch 111/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3694 - val_accuracy: 0.6250 - val_loss: 0.5442
Epoch 112/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3675 - val_accuracy: 0.6250 - val_loss: 0.5430
Epoch 113/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3653 - val_accuracy: 0.6250 - val_loss: 0.5416
Epoch 114/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.3634 - val_accuracy: 0.6250 - val_loss: 0.5408
Epoch 115/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.3613 - val_accuracy: 0.6562 - val_loss: 0.5399
Epoch 116/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.3592 - val_accuracy: 0.6562 - val_loss: 0.5393
Epoch 117/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.3573 - val_accuracy: 0.6562 - val_loss: 0.5389
Epoch 118/400
7/7 - 0s - 8ms/step - accuracy: 0.8672 - loss: 0.3555 - val_accuracy: 0.6562 - val_loss: 0.5381
Epoch 119/400
7/7 - 0s - 9ms/step - accuracy: 0.8672 - loss: 0.3538 - val_accuracy: 0.6562 - val_loss: 0.5357
Epoch 120/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.3519 - val_accuracy: 0.6562 - val_loss: 0.5353
Epoch 121/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3503 - val_accuracy: 0.6562 - val_loss: 0.5330
Epoch 122/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3484 - val_accuracy: 0.6562 - val_loss: 0.5314
Epoch 123/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3464 - val_accuracy: 0.6562 - val_loss: 0.5302
Epoch 124/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3444 - val_accuracy: 0.6562 - val_loss: 0.5294
Epoch 125/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.3426 - val_accuracy: 0.6562 - val_loss: 0.5280
Epoch 126/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.3409 - val_accuracy: 0.6562 - val_loss: 0.5274
Epoch 127/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3392 - val_accuracy: 0.6562 - val_loss: 0.5256
Epoch 128/400
7/7 - 0s - 9ms/step - accuracy: 0.8750 - loss: 0.3376 - val_accuracy: 0.6875 - val_loss: 0.5235
Epoch 129/400
7/7 - 0s - 8ms/step - accuracy: 0.8750 - loss: 0.3358 - val_accuracy: 0.6875 - val_loss: 0.5226
Epoch 130/400
7/7 - 0s - 9ms/step - accuracy: 0.8828 - loss: 0.3344 - val_accuracy: 0.6875 - val_loss: 0.5209
Epoch 131/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3327 - val_accuracy: 0.6875 - val_loss: 0.5197
Epoch 132/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3311 - val_accuracy: 0.6875 - val_loss: 0.5178
Epoch 133/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3295 - val_accuracy: 0.6875 - val_loss: 0.5168
Epoch 134/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3278 - val_accuracy: 0.6875 - val_loss: 0.5164
Epoch 135/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3263 - val_accuracy: 0.6875 - val_loss: 0.5161
Epoch 136/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3246 - val_accuracy: 0.6875 - val_loss: 0.5145
Epoch 137/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3230 - val_accuracy: 0.6875 - val_loss: 0.5131
Epoch 138/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3215 - val_accuracy: 0.6875 - val_loss: 0.5119
Epoch 139/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3200 - val_accuracy: 0.7188 - val_loss: 0.5113
Epoch 140/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3185 - val_accuracy: 0.7188 - val_loss: 0.5086
Epoch 141/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3171 - val_accuracy: 0.7188 - val_loss: 0.5072
Epoch 142/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3160 - val_accuracy: 0.7188 - val_loss: 0.5056
Epoch 143/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3148 - val_accuracy: 0.7188 - val_loss: 0.5043
Epoch 144/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3135 - val_accuracy: 0.7188 - val_loss: 0.5027
Epoch 145/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3121 - val_accuracy: 0.7188 - val_loss: 0.5015
Epoch 146/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3106 - val_accuracy: 0.7188 - val_loss: 0.4997
Epoch 147/400
7/7 - 0s - 9ms/step - accuracy: 0.8984 - loss: 0.3091 - val_accuracy: 0.7188 - val_loss: 0.4987
Epoch 148/400
7/7 - 0s - 8ms/step - accuracy: 0.8984 - loss: 0.3078 - val_accuracy: 0.7188 - val_loss: 0.4982
Epoch 149/400
7/7 - 0s - 8ms/step - accuracy: 0.8984 - loss: 0.3064 - val_accuracy: 0.7188 - val_loss: 0.4963
Epoch 150/400
7/7 - 0s - 8ms/step - accuracy: 0.8984 - loss: 0.3049 - val_accuracy: 0.7188 - val_loss: 0.4951
Epoch 151/400
7/7 - 0s - 8ms/step - accuracy: 0.8984 - loss: 0.3036 - val_accuracy: 0.7188 - val_loss: 0.4935
Epoch 152/400
7/7 - 0s - 9ms/step - accuracy: 0.8984 - loss: 0.3019 - val_accuracy: 0.7188 - val_loss: 0.4921
Epoch 153/400
7/7 - 0s - 9ms/step - accuracy: 0.8984 - loss: 0.3006 - val_accuracy: 0.7188 - val_loss: 0.4912
Epoch 154/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.2991 - val_accuracy: 0.7188 - val_loss: 0.4903
Epoch 155/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.2976 - val_accuracy: 0.7188 - val_loss: 0.4890
Epoch 156/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.2961 - val_accuracy: 0.7188 - val_loss: 0.4887
Epoch 157/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2947 - val_accuracy: 0.7188 - val_loss: 0.4872
Epoch 158/400
7/7 - 0s - 8ms/step - accuracy: 0.9141 - loss: 0.2933 - val_accuracy: 0.7188 - val_loss: 0.4865
Epoch 159/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.2922 - val_accuracy: 0.7188 - val_loss: 0.4854
Epoch 160/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.2909 - val_accuracy: 0.7188 - val_loss: 0.4838
Epoch 161/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2893 - val_accuracy: 0.7188 - val_loss: 0.4828
Epoch 162/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2882 - val_accuracy: 0.7188 - val_loss: 0.4815
Epoch 163/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.2865 - val_accuracy: 0.7188 - val_loss: 0.4793
Epoch 164/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.2851 - val_accuracy: 0.7500 - val_loss: 0.4778
Epoch 165/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.2839 - val_accuracy: 0.7500 - val_loss: 0.4765
Epoch 166/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2827 - val_accuracy: 0.7500 - val_loss: 0.4752
Epoch 167/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2815 - val_accuracy: 0.7812 - val_loss: 0.4733
Epoch 168/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2802 - val_accuracy: 0.7812 - val_loss: 0.4725
Epoch 169/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2791 - val_accuracy: 0.7812 - val_loss: 0.4716
Epoch 170/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2781 - val_accuracy: 0.7812 - val_loss: 0.4701
Epoch 171/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2766 - val_accuracy: 0.7812 - val_loss: 0.4688
Epoch 172/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2756 - val_accuracy: 0.7812 - val_loss: 0.4682
Epoch 173/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2745 - val_accuracy: 0.7812 - val_loss: 0.4663
Epoch 174/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2733 - val_accuracy: 0.7812 - val_loss: 0.4643
Epoch 175/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2722 - val_accuracy: 0.7812 - val_loss: 0.4635
Epoch 176/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2711 - val_accuracy: 0.8125 - val_loss: 0.4623
Epoch 177/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2701 - val_accuracy: 0.8125 - val_loss: 0.4608
Epoch 178/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2692 - val_accuracy: 0.8125 - val_loss: 0.4598
Epoch 179/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2681 - val_accuracy: 0.8125 - val_loss: 0.4593
Epoch 180/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2674 - val_accuracy: 0.8125 - val_loss: 0.4581
Epoch 181/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2662 - val_accuracy: 0.8125 - val_loss: 0.4570
Epoch 182/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2653 - val_accuracy: 0.8125 - val_loss: 0.4564
Epoch 183/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2640 - val_accuracy: 0.8125 - val_loss: 0.4555
Epoch 184/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2632 - val_accuracy: 0.8125 - val_loss: 0.4539
Epoch 185/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2619 - val_accuracy: 0.8125 - val_loss: 0.4531
Epoch 186/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2610 - val_accuracy: 0.8125 - val_loss: 0.4516
Epoch 187/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2599 - val_accuracy: 0.8125 - val_loss: 0.4517
Epoch 188/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2589 - val_accuracy: 0.8125 - val_loss: 0.4507
Epoch 189/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2580 - val_accuracy: 0.8125 - val_loss: 0.4493
Epoch 190/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2571 - val_accuracy: 0.8125 - val_loss: 0.4481
Epoch 191/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2561 - val_accuracy: 0.8125 - val_loss: 0.4473
Epoch 192/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2552 - val_accuracy: 0.8125 - val_loss: 0.4462
Epoch 193/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2541 - val_accuracy: 0.8125 - val_loss: 0.4456
Epoch 194/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2533 - val_accuracy: 0.8125 - val_loss: 0.4448
Epoch 195/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2521 - val_accuracy: 0.8125 - val_loss: 0.4438
Epoch 196/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2510 - val_accuracy: 0.8125 - val_loss: 0.4422
Epoch 197/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2500 - val_accuracy: 0.8125 - val_loss: 0.4411
Epoch 198/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2493 - val_accuracy: 0.8125 - val_loss: 0.4403
Epoch 199/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2483 - val_accuracy: 0.8125 - val_loss: 0.4400
Epoch 200/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2473 - val_accuracy: 0.8125 - val_loss: 0.4388
Epoch 201/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2465 - val_accuracy: 0.8125 - val_loss: 0.4385
Epoch 202/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2455 - val_accuracy: 0.8125 - val_loss: 0.4381
Epoch 203/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2446 - val_accuracy: 0.8125 - val_loss: 0.4381
Epoch 204/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2437 - val_accuracy: 0.8125 - val_loss: 0.4376
Epoch 205/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2427 - val_accuracy: 0.8125 - val_loss: 0.4369
Epoch 206/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2419 - val_accuracy: 0.8125 - val_loss: 0.4369
Epoch 207/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2409 - val_accuracy: 0.8125 - val_loss: 0.4351
Epoch 208/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2401 - val_accuracy: 0.8125 - val_loss: 0.4349
Epoch 209/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2392 - val_accuracy: 0.8125 - val_loss: 0.4346
Epoch 210/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2384 - val_accuracy: 0.8125 - val_loss: 0.4340
Epoch 211/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2375 - val_accuracy: 0.8125 - val_loss: 0.4327
Epoch 212/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2366 - val_accuracy: 0.8125 - val_loss: 0.4322
Epoch 213/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2355 - val_accuracy: 0.8125 - val_loss: 0.4321
Epoch 214/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2347 - val_accuracy: 0.8125 - val_loss: 0.4313
Epoch 215/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2340 - val_accuracy: 0.8125 - val_loss: 0.4307
Epoch 216/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2331 - val_accuracy: 0.8438 - val_loss: 0.4299
Epoch 217/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2324 - val_accuracy: 0.8438 - val_loss: 0.4307
Epoch 218/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2315 - val_accuracy: 0.8438 - val_loss: 0.4297
Epoch 219/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2308 - val_accuracy: 0.8438 - val_loss: 0.4294
Epoch 220/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2303 - val_accuracy: 0.8438 - val_loss: 0.4288
Epoch 221/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2293 - val_accuracy: 0.8438 - val_loss: 0.4277
Epoch 222/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2287 - val_accuracy: 0.8438 - val_loss: 0.4268
Epoch 223/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2279 - val_accuracy: 0.8438 - val_loss: 0.4272
Epoch 224/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2275 - val_accuracy: 0.8438 - val_loss: 0.4266
Epoch 225/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2265 - val_accuracy: 0.8438 - val_loss: 0.4265
Epoch 226/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2259 - val_accuracy: 0.8438 - val_loss: 0.4260
Epoch 227/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2250 - val_accuracy: 0.8438 - val_loss: 0.4258
Epoch 228/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2245 - val_accuracy: 0.8438 - val_loss: 0.4257
Epoch 229/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2237 - val_accuracy: 0.8438 - val_loss: 0.4247
Epoch 230/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2228 - val_accuracy: 0.8438 - val_loss: 0.4239
Epoch 231/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2222 - val_accuracy: 0.8438 - val_loss: 0.4229
Epoch 232/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2215 - val_accuracy: 0.8438 - val_loss: 0.4225
Epoch 233/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2208 - val_accuracy: 0.8438 - val_loss: 0.4218
Epoch 234/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2204 - val_accuracy: 0.8438 - val_loss: 0.4218
Epoch 235/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2194 - val_accuracy: 0.8438 - val_loss: 0.4218
Epoch 236/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2189 - val_accuracy: 0.8438 - val_loss: 0.4217
Epoch 237/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2181 - val_accuracy: 0.8438 - val_loss: 0.4202
Epoch 238/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2174 - val_accuracy: 0.8438 - val_loss: 0.4200
Epoch 239/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2166 - val_accuracy: 0.8750 - val_loss: 0.4193
Epoch 240/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2161 - val_accuracy: 0.8750 - val_loss: 0.4185
Epoch 241/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2151 - val_accuracy: 0.8750 - val_loss: 0.4187
Epoch 242/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2150 - val_accuracy: 0.8750 - val_loss: 0.4178
Epoch 243/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2139 - val_accuracy: 0.8750 - val_loss: 0.4170
Epoch 244/400
7/7 - 0s - 9ms/step - accuracy: 0.9375 - loss: 0.2133 - val_accuracy: 0.8750 - val_loss: 0.4159
Epoch 245/400
7/7 - 0s - 8ms/step - accuracy: 0.9375 - loss: 0.2127 - val_accuracy: 0.8750 - val_loss: 0.4151
Epoch 246/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2118 - val_accuracy: 0.8750 - val_loss: 0.4145
Epoch 247/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2115 - val_accuracy: 0.8750 - val_loss: 0.4134
Epoch 248/400
7/7 - 0s - 8ms/step - accuracy: 0.9453 - loss: 0.2107 - val_accuracy: 0.8750 - val_loss: 0.4128
Epoch 249/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2101 - val_accuracy: 0.8750 - val_loss: 0.4125
Epoch 250/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2096 - val_accuracy: 0.8750 - val_loss: 0.4122
Epoch 251/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2090 - val_accuracy: 0.8750 - val_loss: 0.4107
Epoch 252/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2084 - val_accuracy: 0.8750 - val_loss: 0.4096
Epoch 253/400
7/7 - 0s - 9ms/step - accuracy: 0.9453 - loss: 0.2077 - val_accuracy: 0.8750 - val_loss: 0.4090
Epoch 254/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.2071 - val_accuracy: 0.8750 - val_loss: 0.4087
Epoch 255/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2064 - val_accuracy: 0.8750 - val_loss: 0.4077
Epoch 256/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2057 - val_accuracy: 0.8750 - val_loss: 0.4072
Epoch 257/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2052 - val_accuracy: 0.8750 - val_loss: 0.4071
Epoch 258/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.2045 - val_accuracy: 0.8750 - val_loss: 0.4069
Epoch 259/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2038 - val_accuracy: 0.8750 - val_loss: 0.4069
Epoch 260/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2035 - val_accuracy: 0.8750 - val_loss: 0.4058
Epoch 261/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.2027 - val_accuracy: 0.8750 - val_loss: 0.4047
Epoch 262/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2020 - val_accuracy: 0.8750 - val_loss: 0.4044
Epoch 263/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2015 - val_accuracy: 0.8750 - val_loss: 0.4038
Epoch 264/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2011 - val_accuracy: 0.8750 - val_loss: 0.4038
Epoch 265/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.2007 - val_accuracy: 0.8750 - val_loss: 0.4025
Epoch 266/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.2001 - val_accuracy: 0.8750 - val_loss: 0.4018
Epoch 267/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1995 - val_accuracy: 0.8750 - val_loss: 0.4011
Epoch 268/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1989 - val_accuracy: 0.8750 - val_loss: 0.4016
Epoch 269/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1983 - val_accuracy: 0.8750 - val_loss: 0.4009
Epoch 270/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1978 - val_accuracy: 0.8750 - val_loss: 0.4003
Epoch 271/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1973 - val_accuracy: 0.8750 - val_loss: 0.3989
Epoch 272/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1966 - val_accuracy: 0.8750 - val_loss: 0.3989
Epoch 273/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1961 - val_accuracy: 0.8750 - val_loss: 0.3986
Epoch 274/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1958 - val_accuracy: 0.8750 - val_loss: 0.3982
Epoch 275/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1951 - val_accuracy: 0.8750 - val_loss: 0.3981
Epoch 276/400
7/7 - 0s - 10ms/step - accuracy: 0.9531 - loss: 0.1946 - val_accuracy: 0.8750 - val_loss: 0.3977
Epoch 277/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1941 - val_accuracy: 0.8750 - val_loss: 0.3972
Epoch 278/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1934 - val_accuracy: 0.8750 - val_loss: 0.3965
Epoch 279/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1931 - val_accuracy: 0.8750 - val_loss: 0.3965
Epoch 280/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1922 - val_accuracy: 0.8750 - val_loss: 0.3962
Epoch 281/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1917 - val_accuracy: 0.8750 - val_loss: 0.3958
Epoch 282/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1915 - val_accuracy: 0.8750 - val_loss: 0.3962
Epoch 283/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1906 - val_accuracy: 0.8750 - val_loss: 0.3959
Epoch 284/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1900 - val_accuracy: 0.8750 - val_loss: 0.3952
Epoch 285/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1896 - val_accuracy: 0.8750 - val_loss: 0.3952
Epoch 286/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1892 - val_accuracy: 0.8750 - val_loss: 0.3955
Epoch 287/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1886 - val_accuracy: 0.8750 - val_loss: 0.3954
Epoch 288/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1882 - val_accuracy: 0.8750 - val_loss: 0.3951
Epoch 289/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1876 - val_accuracy: 0.8750 - val_loss: 0.3948
Epoch 290/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1872 - val_accuracy: 0.8750 - val_loss: 0.3944
Epoch 291/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1866 - val_accuracy: 0.8750 - val_loss: 0.3947
Epoch 292/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1863 - val_accuracy: 0.8750 - val_loss: 0.3952
Epoch 293/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1859 - val_accuracy: 0.8750 - val_loss: 0.3951
Epoch 294/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1853 - val_accuracy: 0.8750 - val_loss: 0.3950
Epoch 295/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1847 - val_accuracy: 0.8750 - val_loss: 0.3946
Epoch 296/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1844 - val_accuracy: 0.8750 - val_loss: 0.3939
Epoch 297/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1838 - val_accuracy: 0.8750 - val_loss: 0.3938
Epoch 298/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1833 - val_accuracy: 0.8750 - val_loss: 0.3938
Epoch 299/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1828 - val_accuracy: 0.8750 - val_loss: 0.3932
Epoch 300/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1823 - val_accuracy: 0.8750 - val_loss: 0.3935
Epoch 301/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1819 - val_accuracy: 0.8750 - val_loss: 0.3935
Epoch 302/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1813 - val_accuracy: 0.8750 - val_loss: 0.3931
Epoch 303/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1811 - val_accuracy: 0.8750 - val_loss: 0.3929
Epoch 304/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1806 - val_accuracy: 0.8750 - val_loss: 0.3924
Epoch 305/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1801 - val_accuracy: 0.8750 - val_loss: 0.3926
Epoch 306/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1794 - val_accuracy: 0.8750 - val_loss: 0.3927
Epoch 307/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1792 - val_accuracy: 0.8750 - val_loss: 0.3923
Epoch 308/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1789 - val_accuracy: 0.8750 - val_loss: 0.3919
Epoch 309/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1784 - val_accuracy: 0.8750 - val_loss: 0.3915
Epoch 310/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1778 - val_accuracy: 0.8750 - val_loss: 0.3913
Epoch 311/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1775 - val_accuracy: 0.8750 - val_loss: 0.3908
Epoch 312/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1770 - val_accuracy: 0.8750 - val_loss: 0.3908
Epoch 313/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1766 - val_accuracy: 0.8750 - val_loss: 0.3912
Epoch 314/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1761 - val_accuracy: 0.8750 - val_loss: 0.3915
Epoch 315/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1758 - val_accuracy: 0.8750 - val_loss: 0.3921
Epoch 316/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1753 - val_accuracy: 0.8750 - val_loss: 0.3918
Epoch 317/400
7/7 - 0s - 10ms/step - accuracy: 0.9531 - loss: 0.1750 - val_accuracy: 0.8750 - val_loss: 0.3922
Epoch 318/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1746 - val_accuracy: 0.8750 - val_loss: 0.3919
Epoch 319/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1744 - val_accuracy: 0.8750 - val_loss: 0.3913
Epoch 320/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1740 - val_accuracy: 0.8750 - val_loss: 0.3907
Epoch 321/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1737 - val_accuracy: 0.8750 - val_loss: 0.3898
Epoch 322/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1731 - val_accuracy: 0.8750 - val_loss: 0.3895
Epoch 323/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1729 - val_accuracy: 0.8750 - val_loss: 0.3893
Epoch 324/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1724 - val_accuracy: 0.8750 - val_loss: 0.3893
Epoch 325/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1721 - val_accuracy: 0.8750 - val_loss: 0.3892
Epoch 326/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1717 - val_accuracy: 0.8750 - val_loss: 0.3887
Epoch 327/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1713 - val_accuracy: 0.8750 - val_loss: 0.3888
Epoch 328/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1709 - val_accuracy: 0.8750 - val_loss: 0.3885
Epoch 329/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1705 - val_accuracy: 0.8750 - val_loss: 0.3879
Epoch 330/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1701 - val_accuracy: 0.8750 - val_loss: 0.3881
Epoch 331/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1698 - val_accuracy: 0.8750 - val_loss: 0.3882
Epoch 332/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1693 - val_accuracy: 0.8750 - val_loss: 0.3877
Epoch 333/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1691 - val_accuracy: 0.8750 - val_loss: 0.3881
Epoch 334/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1685 - val_accuracy: 0.8750 - val_loss: 0.3888
Epoch 335/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1683 - val_accuracy: 0.8750 - val_loss: 0.3886
Epoch 336/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1679 - val_accuracy: 0.8750 - val_loss: 0.3884
Epoch 337/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1676 - val_accuracy: 0.8750 - val_loss: 0.3884
Epoch 338/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1674 - val_accuracy: 0.8750 - val_loss: 0.3887
Epoch 339/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1670 - val_accuracy: 0.8750 - val_loss: 0.3879
Epoch 340/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1667 - val_accuracy: 0.8750 - val_loss: 0.3889
Epoch 341/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1659 - val_accuracy: 0.8750 - val_loss: 0.3888
Epoch 342/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1657 - val_accuracy: 0.8750 - val_loss: 0.3895
Epoch 343/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1653 - val_accuracy: 0.8750 - val_loss: 0.3897
Epoch 344/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1652 - val_accuracy: 0.8750 - val_loss: 0.3892
Epoch 345/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1648 - val_accuracy: 0.8750 - val_loss: 0.3886
Epoch 346/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1645 - val_accuracy: 0.8750 - val_loss: 0.3887
Epoch 347/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1641 - val_accuracy: 0.8750 - val_loss: 0.3886
Epoch 348/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1638 - val_accuracy: 0.8750 - val_loss: 0.3885
Epoch 349/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1633 - val_accuracy: 0.8750 - val_loss: 0.3876
Epoch 350/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1632 - val_accuracy: 0.8750 - val_loss: 0.3872
Epoch 351/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1626 - val_accuracy: 0.8750 - val_loss: 0.3873
Epoch 352/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1626 - val_accuracy: 0.8750 - val_loss: 0.3867
Epoch 353/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1620 - val_accuracy: 0.8750 - val_loss: 0.3868
Epoch 354/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1618 - val_accuracy: 0.8750 - val_loss: 0.3861
Epoch 355/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1616 - val_accuracy: 0.8750 - val_loss: 0.3857
Epoch 356/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1611 - val_accuracy: 0.8750 - val_loss: 0.3854
Epoch 357/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1607 - val_accuracy: 0.8750 - val_loss: 0.3849
Epoch 358/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1605 - val_accuracy: 0.8750 - val_loss: 0.3847
Epoch 359/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1603 - val_accuracy: 0.8750 - val_loss: 0.3845
Epoch 360/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1598 - val_accuracy: 0.8750 - val_loss: 0.3842
Epoch 361/400
7/7 - 0s - 10ms/step - accuracy: 0.9531 - loss: 0.1596 - val_accuracy: 0.8750 - val_loss: 0.3842
Epoch 362/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1592 - val_accuracy: 0.8750 - val_loss: 0.3831
Epoch 363/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1590 - val_accuracy: 0.8750 - val_loss: 0.3831
Epoch 364/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1585 - val_accuracy: 0.8750 - val_loss: 0.3829
Epoch 365/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1582 - val_accuracy: 0.8750 - val_loss: 0.3829
Epoch 366/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1580 - val_accuracy: 0.8750 - val_loss: 0.3826
Epoch 367/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1577 - val_accuracy: 0.8750 - val_loss: 0.3832
Epoch 368/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1573 - val_accuracy: 0.8438 - val_loss: 0.3833
Epoch 369/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1569 - val_accuracy: 0.8438 - val_loss: 0.3831
Epoch 370/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1568 - val_accuracy: 0.8438 - val_loss: 0.3833
Epoch 371/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1564 - val_accuracy: 0.8438 - val_loss: 0.3830
Epoch 372/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1561 - val_accuracy: 0.8438 - val_loss: 0.3822
Epoch 373/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1557 - val_accuracy: 0.8750 - val_loss: 0.3817
Epoch 374/400
7/7 - 0s - 10ms/step - accuracy: 0.9531 - loss: 0.1558 - val_accuracy: 0.8438 - val_loss: 0.3818
Epoch 375/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1551 - val_accuracy: 0.8438 - val_loss: 0.3819
Epoch 376/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1549 - val_accuracy: 0.8438 - val_loss: 0.3816
Epoch 377/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1544 - val_accuracy: 0.8438 - val_loss: 0.3808
Epoch 378/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1543 - val_accuracy: 0.8438 - val_loss: 0.3806
Epoch 379/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1538 - val_accuracy: 0.8438 - val_loss: 0.3804
Epoch 380/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1537 - val_accuracy: 0.8438 - val_loss: 0.3805
Epoch 381/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1534 - val_accuracy: 0.8438 - val_loss: 0.3804
Epoch 382/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1528 - val_accuracy: 0.8438 - val_loss: 0.3797
Epoch 383/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1527 - val_accuracy: 0.8438 - val_loss: 0.3797
Epoch 384/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1524 - val_accuracy: 0.8438 - val_loss: 0.3797
Epoch 385/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1522 - val_accuracy: 0.8438 - val_loss: 0.3802
Epoch 386/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1519 - val_accuracy: 0.8438 - val_loss: 0.3797
Epoch 387/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1516 - val_accuracy: 0.8438 - val_loss: 0.3797
Epoch 388/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1513 - val_accuracy: 0.8438 - val_loss: 0.3792
Epoch 389/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1510 - val_accuracy: 0.8438 - val_loss: 0.3789
Epoch 390/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1509 - val_accuracy: 0.8438 - val_loss: 0.3791
Epoch 391/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1504 - val_accuracy: 0.8438 - val_loss: 0.3794
Epoch 392/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1503 - val_accuracy: 0.8438 - val_loss: 0.3792
Epoch 393/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1500 - val_accuracy: 0.8438 - val_loss: 0.3791
Epoch 394/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1495 - val_accuracy: 0.8438 - val_loss: 0.3797
Epoch 395/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1495 - val_accuracy: 0.8438 - val_loss: 0.3801
Epoch 396/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1491 - val_accuracy: 0.8438 - val_loss: 0.3795
Epoch 397/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1489 - val_accuracy: 0.8438 - val_loss: 0.3792
Epoch 398/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1487 - val_accuracy: 0.8438 - val_loss: 0.3796
Epoch 399/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.1483 - val_accuracy: 0.8438 - val_loss: 0.3794
Epoch 400/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.1482 - val_accuracy: 0.8438 - val_loss: 0.3796

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 - 76ms/step - accuracy: 0.9312 - loss: 0.1939

print(perf)

$accuracy
[1] 0.93125

$loss
[1] 0.1938855

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

2/2 - 0s - 164ms/step - accuracy: 0.9750 - loss: 0.2245

print(perf)

$accuracy
[1] 0.975

$loss
[1] 0.224549