Stat. 654 Quiz keras

Author

Your Name Here

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

Clone the TFPlayground Github repository into your R Project folder.

To clone the repository you can use RStudio

File > New Project > Version Control > Git

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

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

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

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

Load the required libraries

library(tidyverse)

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

library(tidymodels)

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

library(readr)
library(janitor)


Attaching package: 'janitor'

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

    chisq.test, fisher.test

library(forcats)
library(keras)


Attaching package: 'keras'

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

    get_weights

Load the data

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

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

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

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

head(input)

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

Split the data into training and testing sets

n <- nrow(input)

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

train <- input_parts |>
  training()

test <- input_parts |>
  testing()

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

[1] 160  40

Visualize the data

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

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

Using keras and tensorflow

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

Do not forget to remove the ID variable pid.

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

length(y_train)

[1] 160

length(y_test)

[1] 40

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 = 8, activation = 'relu', input_shape = 2) |> 
  layer_dense(units = 3, activation = 'relu') |> 
  layer_dense(units = 1, activation = 'sigmoid')
model |> summary()

Model: "sequential"
________________________________________________________________________________
 Layer (type)                       Output Shape                    Param #     
================================================================================
 dense_2 (Dense)                    (None, 8)                       24          
 dense_1 (Dense)                    (None, 3)                       27          
 dense (Dense)                      (None, 1)                       4           
================================================================================
Total params: 55
Trainable params: 55
Non-trainable params: 0
________________________________________________________________________________

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

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

Train the Artificial Neural Network

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

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

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

Epoch 1/400
7/7 - 1s - loss: 0.7813 - accuracy: 0.5312 - val_loss: 0.6980 - val_accuracy: 0.5312 - 1s/epoch - 172ms/step
Epoch 2/400
7/7 - 0s - loss: 0.7494 - accuracy: 0.5312 - val_loss: 0.6754 - val_accuracy: 0.5625 - 50ms/epoch - 7ms/step
Epoch 3/400
7/7 - 0s - loss: 0.7275 - accuracy: 0.5391 - val_loss: 0.6599 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 4/400
7/7 - 0s - loss: 0.7104 - accuracy: 0.5547 - val_loss: 0.6441 - val_accuracy: 0.6250 - 34ms/epoch - 5ms/step
Epoch 5/400
7/7 - 0s - loss: 0.6941 - accuracy: 0.5469 - val_loss: 0.6306 - val_accuracy: 0.6250 - 32ms/epoch - 5ms/step
Epoch 6/400
7/7 - 0s - loss: 0.6797 - accuracy: 0.5547 - val_loss: 0.6160 - val_accuracy: 0.6250 - 34ms/epoch - 5ms/step
Epoch 7/400
7/7 - 0s - loss: 0.6654 - accuracy: 0.5547 - val_loss: 0.6036 - val_accuracy: 0.6250 - 34ms/epoch - 5ms/step
Epoch 8/400
7/7 - 0s - loss: 0.6535 - accuracy: 0.5547 - val_loss: 0.5949 - val_accuracy: 0.6250 - 33ms/epoch - 5ms/step
Epoch 9/400
7/7 - 0s - loss: 0.6447 - accuracy: 0.5547 - val_loss: 0.5866 - val_accuracy: 0.6250 - 33ms/epoch - 5ms/step
Epoch 10/400
7/7 - 0s - loss: 0.6359 - accuracy: 0.5703 - val_loss: 0.5793 - val_accuracy: 0.5938 - 33ms/epoch - 5ms/step
Epoch 11/400
7/7 - 0s - loss: 0.6287 - accuracy: 0.5625 - val_loss: 0.5734 - val_accuracy: 0.6250 - 32ms/epoch - 5ms/step
Epoch 12/400
7/7 - 0s - loss: 0.6212 - accuracy: 0.5703 - val_loss: 0.5680 - val_accuracy: 0.5938 - 33ms/epoch - 5ms/step
Epoch 13/400
7/7 - 0s - loss: 0.6142 - accuracy: 0.5781 - val_loss: 0.5618 - val_accuracy: 0.6250 - 32ms/epoch - 5ms/step
Epoch 14/400
7/7 - 0s - loss: 0.6066 - accuracy: 0.6328 - val_loss: 0.5556 - val_accuracy: 0.7188 - 34ms/epoch - 5ms/step
Epoch 15/400
7/7 - 0s - loss: 0.5993 - accuracy: 0.6719 - val_loss: 0.5497 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 16/400
7/7 - 0s - loss: 0.5924 - accuracy: 0.6953 - val_loss: 0.5439 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 17/400
7/7 - 0s - loss: 0.5849 - accuracy: 0.7266 - val_loss: 0.5381 - val_accuracy: 0.7812 - 35ms/epoch - 5ms/step
Epoch 18/400
7/7 - 0s - loss: 0.5787 - accuracy: 0.7422 - val_loss: 0.5335 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 19/400
7/7 - 0s - loss: 0.5727 - accuracy: 0.7344 - val_loss: 0.5307 - val_accuracy: 0.7812 - 35ms/epoch - 5ms/step
Epoch 20/400
7/7 - 0s - loss: 0.5675 - accuracy: 0.7344 - val_loss: 0.5277 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 21/400
7/7 - 0s - loss: 0.5623 - accuracy: 0.7812 - val_loss: 0.5246 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 22/400
7/7 - 0s - loss: 0.5573 - accuracy: 0.7656 - val_loss: 0.5214 - val_accuracy: 0.7812 - 34ms/epoch - 5ms/step
Epoch 23/400
7/7 - 0s - loss: 0.5523 - accuracy: 0.7891 - val_loss: 0.5182 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 24/400
7/7 - 0s - loss: 0.5472 - accuracy: 0.7969 - val_loss: 0.5143 - val_accuracy: 0.7812 - 34ms/epoch - 5ms/step
Epoch 25/400
7/7 - 0s - loss: 0.5424 - accuracy: 0.7969 - val_loss: 0.5106 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 26/400
7/7 - 0s - loss: 0.5382 - accuracy: 0.8047 - val_loss: 0.5075 - val_accuracy: 0.7812 - 34ms/epoch - 5ms/step
Epoch 27/400
7/7 - 0s - loss: 0.5324 - accuracy: 0.8047 - val_loss: 0.5030 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 28/400
7/7 - 0s - loss: 0.5282 - accuracy: 0.8203 - val_loss: 0.5005 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 29/400
7/7 - 0s - loss: 0.5225 - accuracy: 0.8203 - val_loss: 0.4966 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 30/400
7/7 - 0s - loss: 0.5179 - accuracy: 0.8203 - val_loss: 0.4919 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 31/400
7/7 - 0s - loss: 0.5127 - accuracy: 0.8281 - val_loss: 0.4881 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 32/400
7/7 - 0s - loss: 0.5076 - accuracy: 0.8281 - val_loss: 0.4857 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 33/400
7/7 - 0s - loss: 0.5018 - accuracy: 0.8281 - val_loss: 0.4826 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 34/400
7/7 - 0s - loss: 0.4967 - accuracy: 0.8359 - val_loss: 0.4789 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 35/400
7/7 - 0s - loss: 0.4915 - accuracy: 0.8359 - val_loss: 0.4752 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 36/400
7/7 - 0s - loss: 0.4856 - accuracy: 0.8359 - val_loss: 0.4719 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 37/400
7/7 - 0s - loss: 0.4800 - accuracy: 0.8359 - val_loss: 0.4682 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 38/400
7/7 - 0s - loss: 0.4743 - accuracy: 0.8359 - val_loss: 0.4645 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 39/400
7/7 - 0s - loss: 0.4687 - accuracy: 0.8359 - val_loss: 0.4597 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 40/400
7/7 - 0s - loss: 0.4631 - accuracy: 0.8516 - val_loss: 0.4563 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 41/400
7/7 - 0s - loss: 0.4574 - accuracy: 0.8516 - val_loss: 0.4536 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 42/400
7/7 - 0s - loss: 0.4518 - accuracy: 0.8516 - val_loss: 0.4510 - val_accuracy: 0.7812 - 34ms/epoch - 5ms/step
Epoch 43/400
7/7 - 0s - loss: 0.4463 - accuracy: 0.8516 - val_loss: 0.4470 - val_accuracy: 0.7812 - 34ms/epoch - 5ms/step
Epoch 44/400
7/7 - 0s - loss: 0.4412 - accuracy: 0.8594 - val_loss: 0.4427 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 45/400
7/7 - 0s - loss: 0.4365 - accuracy: 0.8672 - val_loss: 0.4392 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 46/400
7/7 - 0s - loss: 0.4310 - accuracy: 0.8750 - val_loss: 0.4356 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 47/400
7/7 - 0s - loss: 0.4258 - accuracy: 0.8750 - val_loss: 0.4332 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 48/400
7/7 - 0s - loss: 0.4205 - accuracy: 0.8750 - val_loss: 0.4279 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 49/400
7/7 - 0s - loss: 0.4157 - accuracy: 0.8828 - val_loss: 0.4249 - val_accuracy: 0.8125 - 32ms/epoch - 5ms/step
Epoch 50/400
7/7 - 0s - loss: 0.4107 - accuracy: 0.8750 - val_loss: 0.4209 - val_accuracy: 0.8125 - 32ms/epoch - 5ms/step
Epoch 51/400
7/7 - 0s - loss: 0.4053 - accuracy: 0.8828 - val_loss: 0.4181 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 52/400
7/7 - 0s - loss: 0.4003 - accuracy: 0.8672 - val_loss: 0.4138 - val_accuracy: 0.8125 - 32ms/epoch - 5ms/step
Epoch 53/400
7/7 - 0s - loss: 0.3956 - accuracy: 0.8672 - val_loss: 0.4091 - val_accuracy: 0.8125 - 34ms/epoch - 5ms/step
Epoch 54/400
7/7 - 0s - loss: 0.3904 - accuracy: 0.8750 - val_loss: 0.4068 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 55/400
7/7 - 0s - loss: 0.3856 - accuracy: 0.8750 - val_loss: 0.4039 - val_accuracy: 0.8125 - 32ms/epoch - 5ms/step
Epoch 56/400
7/7 - 0s - loss: 0.3809 - accuracy: 0.8750 - val_loss: 0.4007 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 57/400
7/7 - 0s - loss: 0.3759 - accuracy: 0.8828 - val_loss: 0.3964 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 58/400
7/7 - 0s - loss: 0.3715 - accuracy: 0.8750 - val_loss: 0.3938 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 59/400
7/7 - 0s - loss: 0.3664 - accuracy: 0.8750 - val_loss: 0.3896 - val_accuracy: 0.8438 - 32ms/epoch - 5ms/step
Epoch 60/400
7/7 - 0s - loss: 0.3620 - accuracy: 0.8750 - val_loss: 0.3881 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 61/400
7/7 - 0s - loss: 0.3572 - accuracy: 0.8828 - val_loss: 0.3849 - val_accuracy: 0.8438 - 32ms/epoch - 5ms/step
Epoch 62/400
7/7 - 0s - loss: 0.3530 - accuracy: 0.8828 - val_loss: 0.3840 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 63/400
7/7 - 0s - loss: 0.3485 - accuracy: 0.8906 - val_loss: 0.3808 - val_accuracy: 0.8438 - 35ms/epoch - 5ms/step
Epoch 64/400
7/7 - 0s - loss: 0.3447 - accuracy: 0.8906 - val_loss: 0.3787 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 65/400
7/7 - 0s - loss: 0.3401 - accuracy: 0.8906 - val_loss: 0.3769 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 66/400
7/7 - 0s - loss: 0.3362 - accuracy: 0.8828 - val_loss: 0.3734 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 67/400
7/7 - 0s - loss: 0.3317 - accuracy: 0.8828 - val_loss: 0.3711 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 68/400
7/7 - 0s - loss: 0.3280 - accuracy: 0.8828 - val_loss: 0.3673 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 69/400
7/7 - 0s - loss: 0.3242 - accuracy: 0.8828 - val_loss: 0.3646 - val_accuracy: 0.8438 - 41ms/epoch - 6ms/step
Epoch 70/400
7/7 - 0s - loss: 0.3198 - accuracy: 0.8906 - val_loss: 0.3620 - val_accuracy: 0.8438 - 32ms/epoch - 5ms/step
Epoch 71/400
7/7 - 0s - loss: 0.3154 - accuracy: 0.8906 - val_loss: 0.3575 - val_accuracy: 0.8438 - 36ms/epoch - 5ms/step
Epoch 72/400
7/7 - 0s - loss: 0.3117 - accuracy: 0.8984 - val_loss: 0.3545 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 73/400
7/7 - 0s - loss: 0.3079 - accuracy: 0.8984 - val_loss: 0.3521 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 74/400
7/7 - 0s - loss: 0.3036 - accuracy: 0.8906 - val_loss: 0.3483 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 75/400
7/7 - 0s - loss: 0.2998 - accuracy: 0.8984 - val_loss: 0.3456 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 76/400
7/7 - 0s - loss: 0.2960 - accuracy: 0.9062 - val_loss: 0.3441 - val_accuracy: 0.8438 - 35ms/epoch - 5ms/step
Epoch 77/400
7/7 - 0s - loss: 0.2923 - accuracy: 0.9141 - val_loss: 0.3420 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 78/400
7/7 - 0s - loss: 0.2882 - accuracy: 0.9141 - val_loss: 0.3394 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 79/400
7/7 - 0s - loss: 0.2842 - accuracy: 0.9219 - val_loss: 0.3361 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 80/400
7/7 - 0s - loss: 0.2805 - accuracy: 0.9219 - val_loss: 0.3345 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 81/400
7/7 - 0s - loss: 0.2766 - accuracy: 0.9219 - val_loss: 0.3320 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 82/400
7/7 - 0s - loss: 0.2729 - accuracy: 0.9219 - val_loss: 0.3297 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 83/400
7/7 - 0s - loss: 0.2692 - accuracy: 0.9219 - val_loss: 0.3265 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 84/400
7/7 - 0s - loss: 0.2664 - accuracy: 0.9219 - val_loss: 0.3254 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 85/400
7/7 - 0s - loss: 0.2631 - accuracy: 0.9219 - val_loss: 0.3240 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 86/400
7/7 - 0s - loss: 0.2592 - accuracy: 0.9219 - val_loss: 0.3236 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 87/400
7/7 - 0s - loss: 0.2558 - accuracy: 0.9375 - val_loss: 0.3214 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 88/400
7/7 - 0s - loss: 0.2526 - accuracy: 0.9297 - val_loss: 0.3216 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 89/400
7/7 - 0s - loss: 0.2489 - accuracy: 0.9453 - val_loss: 0.3204 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 90/400
7/7 - 0s - loss: 0.2464 - accuracy: 0.9297 - val_loss: 0.3203 - val_accuracy: 0.8438 - 34ms/epoch - 5ms/step
Epoch 91/400
7/7 - 0s - loss: 0.2434 - accuracy: 0.9297 - val_loss: 0.3190 - val_accuracy: 0.8438 - 33ms/epoch - 5ms/step
Epoch 92/400
7/7 - 0s - loss: 0.2401 - accuracy: 0.9297 - val_loss: 0.3167 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 93/400
7/7 - 0s - loss: 0.2373 - accuracy: 0.9453 - val_loss: 0.3153 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 94/400
7/7 - 0s - loss: 0.2346 - accuracy: 0.9453 - val_loss: 0.3131 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 95/400
7/7 - 0s - loss: 0.2312 - accuracy: 0.9453 - val_loss: 0.3116 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 96/400
7/7 - 0s - loss: 0.2282 - accuracy: 0.9375 - val_loss: 0.3103 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 97/400
7/7 - 0s - loss: 0.2261 - accuracy: 0.9375 - val_loss: 0.3090 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 98/400
7/7 - 0s - loss: 0.2231 - accuracy: 0.9375 - val_loss: 0.3088 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 99/400
7/7 - 0s - loss: 0.2201 - accuracy: 0.9375 - val_loss: 0.3066 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 100/400
7/7 - 0s - loss: 0.2183 - accuracy: 0.9375 - val_loss: 0.3069 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 101/400
7/7 - 0s - loss: 0.2152 - accuracy: 0.9453 - val_loss: 0.3051 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 102/400
7/7 - 0s - loss: 0.2127 - accuracy: 0.9453 - val_loss: 0.3060 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 103/400
7/7 - 0s - loss: 0.2113 - accuracy: 0.9375 - val_loss: 0.3032 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 104/400
7/7 - 0s - loss: 0.2087 - accuracy: 0.9453 - val_loss: 0.3029 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 105/400
7/7 - 0s - loss: 0.2066 - accuracy: 0.9375 - val_loss: 0.3010 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 106/400
7/7 - 0s - loss: 0.2046 - accuracy: 0.9453 - val_loss: 0.3013 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 107/400
7/7 - 0s - loss: 0.2023 - accuracy: 0.9531 - val_loss: 0.3009 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 108/400
7/7 - 0s - loss: 0.2002 - accuracy: 0.9531 - val_loss: 0.3022 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 109/400
7/7 - 0s - loss: 0.1980 - accuracy: 0.9453 - val_loss: 0.2997 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 110/400
7/7 - 0s - loss: 0.1960 - accuracy: 0.9375 - val_loss: 0.2978 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 111/400
7/7 - 0s - loss: 0.1940 - accuracy: 0.9531 - val_loss: 0.2980 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 112/400
7/7 - 0s - loss: 0.1929 - accuracy: 0.9453 - val_loss: 0.2993 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 113/400
7/7 - 0s - loss: 0.1905 - accuracy: 0.9453 - val_loss: 0.2983 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 114/400
7/7 - 0s - loss: 0.1884 - accuracy: 0.9531 - val_loss: 0.2955 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 115/400
7/7 - 0s - loss: 0.1864 - accuracy: 0.9531 - val_loss: 0.2945 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 116/400
7/7 - 0s - loss: 0.1846 - accuracy: 0.9531 - val_loss: 0.2944 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 117/400
7/7 - 0s - loss: 0.1829 - accuracy: 0.9531 - val_loss: 0.2947 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 118/400
7/7 - 0s - loss: 0.1814 - accuracy: 0.9453 - val_loss: 0.2974 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 119/400
7/7 - 0s - loss: 0.1794 - accuracy: 0.9531 - val_loss: 0.2951 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 120/400
7/7 - 0s - loss: 0.1781 - accuracy: 0.9531 - val_loss: 0.2967 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 121/400
7/7 - 0s - loss: 0.1764 - accuracy: 0.9531 - val_loss: 0.2972 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 122/400
7/7 - 0s - loss: 0.1747 - accuracy: 0.9531 - val_loss: 0.2980 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 123/400
7/7 - 0s - loss: 0.1728 - accuracy: 0.9531 - val_loss: 0.2981 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 124/400
7/7 - 0s - loss: 0.1714 - accuracy: 0.9531 - val_loss: 0.2999 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 125/400
7/7 - 0s - loss: 0.1694 - accuracy: 0.9531 - val_loss: 0.2999 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 126/400
7/7 - 0s - loss: 0.1684 - accuracy: 0.9531 - val_loss: 0.2980 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 127/400
7/7 - 0s - loss: 0.1667 - accuracy: 0.9531 - val_loss: 0.2962 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 128/400
7/7 - 0s - loss: 0.1650 - accuracy: 0.9531 - val_loss: 0.2935 - val_accuracy: 0.9062 - 37ms/epoch - 5ms/step
Epoch 129/400
7/7 - 0s - loss: 0.1637 - accuracy: 0.9609 - val_loss: 0.2946 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 130/400
7/7 - 0s - loss: 0.1624 - accuracy: 0.9453 - val_loss: 0.2969 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 131/400
7/7 - 0s - loss: 0.1609 - accuracy: 0.9609 - val_loss: 0.2976 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 132/400
7/7 - 0s - loss: 0.1595 - accuracy: 0.9531 - val_loss: 0.2951 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 133/400
7/7 - 0s - loss: 0.1579 - accuracy: 0.9688 - val_loss: 0.2945 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 134/400
7/7 - 0s - loss: 0.1569 - accuracy: 0.9609 - val_loss: 0.2968 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 135/400
7/7 - 0s - loss: 0.1555 - accuracy: 0.9688 - val_loss: 0.2976 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 136/400
7/7 - 0s - loss: 0.1541 - accuracy: 0.9688 - val_loss: 0.2986 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 137/400
7/7 - 0s - loss: 0.1532 - accuracy: 0.9688 - val_loss: 0.2986 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 138/400
7/7 - 0s - loss: 0.1520 - accuracy: 0.9688 - val_loss: 0.2977 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 139/400
7/7 - 0s - loss: 0.1502 - accuracy: 0.9688 - val_loss: 0.2981 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 140/400
7/7 - 0s - loss: 0.1496 - accuracy: 0.9609 - val_loss: 0.2981 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 141/400
7/7 - 0s - loss: 0.1484 - accuracy: 0.9531 - val_loss: 0.2981 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 142/400
7/7 - 0s - loss: 0.1471 - accuracy: 0.9609 - val_loss: 0.2990 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 143/400
7/7 - 0s - loss: 0.1458 - accuracy: 0.9609 - val_loss: 0.2998 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 144/400
7/7 - 0s - loss: 0.1449 - accuracy: 0.9688 - val_loss: 0.2969 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 145/400
7/7 - 0s - loss: 0.1439 - accuracy: 0.9531 - val_loss: 0.2961 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 146/400
7/7 - 0s - loss: 0.1432 - accuracy: 0.9531 - val_loss: 0.2977 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 147/400
7/7 - 0s - loss: 0.1420 - accuracy: 0.9531 - val_loss: 0.2971 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 148/400
7/7 - 0s - loss: 0.1412 - accuracy: 0.9609 - val_loss: 0.3011 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 149/400
7/7 - 0s - loss: 0.1403 - accuracy: 0.9609 - val_loss: 0.3036 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 150/400
7/7 - 0s - loss: 0.1393 - accuracy: 0.9688 - val_loss: 0.3040 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 151/400
7/7 - 0s - loss: 0.1387 - accuracy: 0.9609 - val_loss: 0.3050 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 152/400
7/7 - 0s - loss: 0.1380 - accuracy: 0.9688 - val_loss: 0.3052 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 153/400
7/7 - 0s - loss: 0.1368 - accuracy: 0.9688 - val_loss: 0.3068 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 154/400
7/7 - 0s - loss: 0.1357 - accuracy: 0.9688 - val_loss: 0.3055 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 155/400
7/7 - 0s - loss: 0.1351 - accuracy: 0.9609 - val_loss: 0.3062 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 156/400
7/7 - 0s - loss: 0.1341 - accuracy: 0.9531 - val_loss: 0.3062 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 157/400
7/7 - 0s - loss: 0.1328 - accuracy: 0.9609 - val_loss: 0.3069 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 158/400
7/7 - 0s - loss: 0.1321 - accuracy: 0.9531 - val_loss: 0.3078 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 159/400
7/7 - 0s - loss: 0.1319 - accuracy: 0.9531 - val_loss: 0.3066 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 160/400
7/7 - 0s - loss: 0.1304 - accuracy: 0.9609 - val_loss: 0.3081 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 161/400
7/7 - 0s - loss: 0.1300 - accuracy: 0.9609 - val_loss: 0.3102 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 162/400
7/7 - 0s - loss: 0.1292 - accuracy: 0.9609 - val_loss: 0.3102 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 163/400
7/7 - 0s - loss: 0.1283 - accuracy: 0.9609 - val_loss: 0.3104 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 164/400
7/7 - 0s - loss: 0.1281 - accuracy: 0.9453 - val_loss: 0.3140 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 165/400
7/7 - 0s - loss: 0.1266 - accuracy: 0.9609 - val_loss: 0.3146 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 166/400
7/7 - 0s - loss: 0.1262 - accuracy: 0.9609 - val_loss: 0.3145 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 167/400
7/7 - 0s - loss: 0.1256 - accuracy: 0.9609 - val_loss: 0.3148 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 168/400
7/7 - 0s - loss: 0.1250 - accuracy: 0.9609 - val_loss: 0.3168 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 169/400
7/7 - 0s - loss: 0.1240 - accuracy: 0.9609 - val_loss: 0.3182 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 170/400
7/7 - 0s - loss: 0.1238 - accuracy: 0.9609 - val_loss: 0.3174 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 171/400
7/7 - 0s - loss: 0.1226 - accuracy: 0.9531 - val_loss: 0.3190 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 172/400
7/7 - 0s - loss: 0.1223 - accuracy: 0.9531 - val_loss: 0.3225 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 173/400
7/7 - 0s - loss: 0.1210 - accuracy: 0.9609 - val_loss: 0.3214 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 174/400
7/7 - 0s - loss: 0.1209 - accuracy: 0.9609 - val_loss: 0.3216 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 175/400
7/7 - 0s - loss: 0.1198 - accuracy: 0.9609 - val_loss: 0.3220 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 176/400
7/7 - 0s - loss: 0.1194 - accuracy: 0.9609 - val_loss: 0.3210 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 177/400
7/7 - 0s - loss: 0.1190 - accuracy: 0.9609 - val_loss: 0.3187 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 178/400
7/7 - 0s - loss: 0.1182 - accuracy: 0.9609 - val_loss: 0.3209 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 179/400
7/7 - 0s - loss: 0.1177 - accuracy: 0.9609 - val_loss: 0.3240 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 180/400
7/7 - 0s - loss: 0.1172 - accuracy: 0.9609 - val_loss: 0.3257 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 181/400
7/7 - 0s - loss: 0.1164 - accuracy: 0.9609 - val_loss: 0.3284 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 182/400
7/7 - 0s - loss: 0.1156 - accuracy: 0.9609 - val_loss: 0.3277 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 183/400
7/7 - 0s - loss: 0.1153 - accuracy: 0.9609 - val_loss: 0.3290 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 184/400
7/7 - 0s - loss: 0.1154 - accuracy: 0.9609 - val_loss: 0.3300 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 185/400
7/7 - 0s - loss: 0.1148 - accuracy: 0.9609 - val_loss: 0.3301 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 186/400
7/7 - 0s - loss: 0.1145 - accuracy: 0.9609 - val_loss: 0.3310 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 187/400
7/7 - 0s - loss: 0.1139 - accuracy: 0.9609 - val_loss: 0.3308 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 188/400
7/7 - 0s - loss: 0.1133 - accuracy: 0.9609 - val_loss: 0.3322 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 189/400
7/7 - 0s - loss: 0.1129 - accuracy: 0.9609 - val_loss: 0.3315 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 190/400
7/7 - 0s - loss: 0.1129 - accuracy: 0.9609 - val_loss: 0.3293 - val_accuracy: 0.9062 - 40ms/epoch - 6ms/step
Epoch 191/400
7/7 - 0s - loss: 0.1120 - accuracy: 0.9609 - val_loss: 0.3304 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 192/400
7/7 - 0s - loss: 0.1119 - accuracy: 0.9609 - val_loss: 0.3317 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 193/400
7/7 - 0s - loss: 0.1109 - accuracy: 0.9609 - val_loss: 0.3336 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 194/400
7/7 - 0s - loss: 0.1112 - accuracy: 0.9609 - val_loss: 0.3347 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 195/400
7/7 - 0s - loss: 0.1103 - accuracy: 0.9609 - val_loss: 0.3377 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 196/400
7/7 - 0s - loss: 0.1101 - accuracy: 0.9609 - val_loss: 0.3396 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 197/400
7/7 - 0s - loss: 0.1092 - accuracy: 0.9609 - val_loss: 0.3400 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 198/400
7/7 - 0s - loss: 0.1093 - accuracy: 0.9609 - val_loss: 0.3407 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 199/400
7/7 - 0s - loss: 0.1085 - accuracy: 0.9609 - val_loss: 0.3439 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 200/400
7/7 - 0s - loss: 0.1083 - accuracy: 0.9609 - val_loss: 0.3425 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 201/400
7/7 - 0s - loss: 0.1080 - accuracy: 0.9609 - val_loss: 0.3458 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 202/400
7/7 - 0s - loss: 0.1071 - accuracy: 0.9609 - val_loss: 0.3481 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 203/400
7/7 - 0s - loss: 0.1069 - accuracy: 0.9609 - val_loss: 0.3503 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 204/400
7/7 - 0s - loss: 0.1066 - accuracy: 0.9531 - val_loss: 0.3511 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 205/400
7/7 - 0s - loss: 0.1062 - accuracy: 0.9609 - val_loss: 0.3538 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 206/400
7/7 - 0s - loss: 0.1061 - accuracy: 0.9609 - val_loss: 0.3532 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 207/400
7/7 - 0s - loss: 0.1062 - accuracy: 0.9531 - val_loss: 0.3525 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 208/400
7/7 - 0s - loss: 0.1054 - accuracy: 0.9609 - val_loss: 0.3542 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 209/400
7/7 - 0s - loss: 0.1047 - accuracy: 0.9609 - val_loss: 0.3549 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 210/400
7/7 - 0s - loss: 0.1050 - accuracy: 0.9609 - val_loss: 0.3574 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 211/400
7/7 - 0s - loss: 0.1034 - accuracy: 0.9688 - val_loss: 0.3583 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 212/400
7/7 - 0s - loss: 0.1036 - accuracy: 0.9609 - val_loss: 0.3594 - val_accuracy: 0.9062 - 39ms/epoch - 6ms/step
Epoch 213/400
7/7 - 0s - loss: 0.1032 - accuracy: 0.9609 - val_loss: 0.3641 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 214/400
7/7 - 0s - loss: 0.1029 - accuracy: 0.9688 - val_loss: 0.3650 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 215/400
7/7 - 0s - loss: 0.1024 - accuracy: 0.9609 - val_loss: 0.3636 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 216/400
7/7 - 0s - loss: 0.1020 - accuracy: 0.9688 - val_loss: 0.3658 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 217/400
7/7 - 0s - loss: 0.1018 - accuracy: 0.9609 - val_loss: 0.3638 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 218/400
7/7 - 0s - loss: 0.1010 - accuracy: 0.9688 - val_loss: 0.3662 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 219/400
7/7 - 0s - loss: 0.1020 - accuracy: 0.9609 - val_loss: 0.3667 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 220/400
7/7 - 0s - loss: 0.1008 - accuracy: 0.9688 - val_loss: 0.3654 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 221/400
7/7 - 0s - loss: 0.1007 - accuracy: 0.9609 - val_loss: 0.3647 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 222/400
7/7 - 0s - loss: 0.1003 - accuracy: 0.9609 - val_loss: 0.3665 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 223/400
7/7 - 0s - loss: 0.1001 - accuracy: 0.9609 - val_loss: 0.3650 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 224/400
7/7 - 0s - loss: 0.0995 - accuracy: 0.9609 - val_loss: 0.3692 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 225/400
7/7 - 0s - loss: 0.0988 - accuracy: 0.9609 - val_loss: 0.3706 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 226/400
7/7 - 0s - loss: 0.0986 - accuracy: 0.9609 - val_loss: 0.3705 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 227/400
7/7 - 0s - loss: 0.0987 - accuracy: 0.9609 - val_loss: 0.3731 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 228/400
7/7 - 0s - loss: 0.0981 - accuracy: 0.9609 - val_loss: 0.3743 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 229/400
7/7 - 0s - loss: 0.0976 - accuracy: 0.9609 - val_loss: 0.3749 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 230/400
7/7 - 0s - loss: 0.0976 - accuracy: 0.9609 - val_loss: 0.3741 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 231/400
7/7 - 0s - loss: 0.0972 - accuracy: 0.9609 - val_loss: 0.3788 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 232/400
7/7 - 0s - loss: 0.0971 - accuracy: 0.9688 - val_loss: 0.3819 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 233/400
7/7 - 0s - loss: 0.0968 - accuracy: 0.9688 - val_loss: 0.3823 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 234/400
7/7 - 0s - loss: 0.0959 - accuracy: 0.9688 - val_loss: 0.3806 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 235/400
7/7 - 0s - loss: 0.0969 - accuracy: 0.9609 - val_loss: 0.3823 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 236/400
7/7 - 0s - loss: 0.0960 - accuracy: 0.9609 - val_loss: 0.3828 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 237/400
7/7 - 0s - loss: 0.0955 - accuracy: 0.9688 - val_loss: 0.3824 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 238/400
7/7 - 0s - loss: 0.0950 - accuracy: 0.9688 - val_loss: 0.3824 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 239/400
7/7 - 0s - loss: 0.0956 - accuracy: 0.9688 - val_loss: 0.3819 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 240/400
7/7 - 0s - loss: 0.0948 - accuracy: 0.9688 - val_loss: 0.3834 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 241/400
7/7 - 0s - loss: 0.0947 - accuracy: 0.9688 - val_loss: 0.3833 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 242/400
7/7 - 0s - loss: 0.0938 - accuracy: 0.9609 - val_loss: 0.3859 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 243/400
7/7 - 0s - loss: 0.0941 - accuracy: 0.9609 - val_loss: 0.3835 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 244/400
7/7 - 0s - loss: 0.0934 - accuracy: 0.9609 - val_loss: 0.3858 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 245/400
7/7 - 0s - loss: 0.0939 - accuracy: 0.9609 - val_loss: 0.3882 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 246/400
7/7 - 0s - loss: 0.0933 - accuracy: 0.9609 - val_loss: 0.3906 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 247/400
7/7 - 0s - loss: 0.0928 - accuracy: 0.9609 - val_loss: 0.3931 - val_accuracy: 0.9062 - 43ms/epoch - 6ms/step
Epoch 248/400
7/7 - 0s - loss: 0.0925 - accuracy: 0.9688 - val_loss: 0.3929 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 249/400
7/7 - 0s - loss: 0.0925 - accuracy: 0.9688 - val_loss: 0.3953 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 250/400
7/7 - 0s - loss: 0.0918 - accuracy: 0.9688 - val_loss: 0.3940 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 251/400
7/7 - 0s - loss: 0.0921 - accuracy: 0.9609 - val_loss: 0.3984 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 252/400
7/7 - 0s - loss: 0.0912 - accuracy: 0.9688 - val_loss: 0.4019 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 253/400
7/7 - 0s - loss: 0.0912 - accuracy: 0.9609 - val_loss: 0.4022 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 254/400
7/7 - 0s - loss: 0.0910 - accuracy: 0.9609 - val_loss: 0.4020 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 255/400
7/7 - 0s - loss: 0.0903 - accuracy: 0.9688 - val_loss: 0.4017 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 256/400
7/7 - 0s - loss: 0.0901 - accuracy: 0.9688 - val_loss: 0.4025 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 257/400
7/7 - 0s - loss: 0.0902 - accuracy: 0.9688 - val_loss: 0.4032 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 258/400
7/7 - 0s - loss: 0.0897 - accuracy: 0.9688 - val_loss: 0.4038 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 259/400
7/7 - 0s - loss: 0.0897 - accuracy: 0.9531 - val_loss: 0.4045 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 260/400
7/7 - 0s - loss: 0.0899 - accuracy: 0.9609 - val_loss: 0.4050 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 261/400
7/7 - 0s - loss: 0.0887 - accuracy: 0.9688 - val_loss: 0.4054 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 262/400
7/7 - 0s - loss: 0.0887 - accuracy: 0.9609 - val_loss: 0.4068 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 263/400
7/7 - 0s - loss: 0.0885 - accuracy: 0.9609 - val_loss: 0.4087 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 264/400
7/7 - 0s - loss: 0.0881 - accuracy: 0.9609 - val_loss: 0.4098 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 265/400
7/7 - 0s - loss: 0.0884 - accuracy: 0.9688 - val_loss: 0.4085 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 266/400
7/7 - 0s - loss: 0.0881 - accuracy: 0.9609 - val_loss: 0.4101 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 267/400
7/7 - 0s - loss: 0.0876 - accuracy: 0.9609 - val_loss: 0.4114 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 268/400
7/7 - 0s - loss: 0.0880 - accuracy: 0.9609 - val_loss: 0.4110 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 269/400
7/7 - 0s - loss: 0.0877 - accuracy: 0.9609 - val_loss: 0.4109 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 270/400
7/7 - 0s - loss: 0.0866 - accuracy: 0.9609 - val_loss: 0.4165 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 271/400
7/7 - 0s - loss: 0.0864 - accuracy: 0.9609 - val_loss: 0.4165 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 272/400
7/7 - 0s - loss: 0.0861 - accuracy: 0.9688 - val_loss: 0.4195 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 273/400
7/7 - 0s - loss: 0.0863 - accuracy: 0.9609 - val_loss: 0.4200 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 274/400
7/7 - 0s - loss: 0.0861 - accuracy: 0.9609 - val_loss: 0.4205 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 275/400
7/7 - 0s - loss: 0.0860 - accuracy: 0.9609 - val_loss: 0.4221 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 276/400
7/7 - 0s - loss: 0.0855 - accuracy: 0.9688 - val_loss: 0.4222 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 277/400
7/7 - 0s - loss: 0.0857 - accuracy: 0.9688 - val_loss: 0.4272 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 278/400
7/7 - 0s - loss: 0.0849 - accuracy: 0.9688 - val_loss: 0.4331 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 279/400
7/7 - 0s - loss: 0.0846 - accuracy: 0.9609 - val_loss: 0.4308 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 280/400
7/7 - 0s - loss: 0.0845 - accuracy: 0.9609 - val_loss: 0.4326 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 281/400
7/7 - 0s - loss: 0.0844 - accuracy: 0.9609 - val_loss: 0.4318 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 282/400
7/7 - 0s - loss: 0.0849 - accuracy: 0.9609 - val_loss: 0.4351 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 283/400
7/7 - 0s - loss: 0.0839 - accuracy: 0.9609 - val_loss: 0.4329 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 284/400
7/7 - 0s - loss: 0.0837 - accuracy: 0.9688 - val_loss: 0.4322 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 285/400
7/7 - 0s - loss: 0.0833 - accuracy: 0.9688 - val_loss: 0.4354 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 286/400
7/7 - 0s - loss: 0.0832 - accuracy: 0.9688 - val_loss: 0.4352 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 287/400
7/7 - 0s - loss: 0.0833 - accuracy: 0.9609 - val_loss: 0.4354 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 288/400
7/7 - 0s - loss: 0.0829 - accuracy: 0.9609 - val_loss: 0.4327 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 289/400
7/7 - 0s - loss: 0.0826 - accuracy: 0.9688 - val_loss: 0.4330 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 290/400
7/7 - 0s - loss: 0.0824 - accuracy: 0.9688 - val_loss: 0.4330 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 291/400
7/7 - 0s - loss: 0.0815 - accuracy: 0.9688 - val_loss: 0.4320 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 292/400
7/7 - 0s - loss: 0.0825 - accuracy: 0.9609 - val_loss: 0.4355 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 293/400
7/7 - 0s - loss: 0.0821 - accuracy: 0.9609 - val_loss: 0.4363 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 294/400
7/7 - 0s - loss: 0.0815 - accuracy: 0.9688 - val_loss: 0.4371 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 295/400
7/7 - 0s - loss: 0.0817 - accuracy: 0.9688 - val_loss: 0.4395 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 296/400
7/7 - 0s - loss: 0.0816 - accuracy: 0.9609 - val_loss: 0.4398 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 297/400
7/7 - 0s - loss: 0.0811 - accuracy: 0.9688 - val_loss: 0.4419 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 298/400
7/7 - 0s - loss: 0.0806 - accuracy: 0.9609 - val_loss: 0.4432 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 299/400
7/7 - 0s - loss: 0.0811 - accuracy: 0.9688 - val_loss: 0.4436 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 300/400
7/7 - 0s - loss: 0.0810 - accuracy: 0.9688 - val_loss: 0.4460 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 301/400
7/7 - 0s - loss: 0.0811 - accuracy: 0.9688 - val_loss: 0.4453 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 302/400
7/7 - 0s - loss: 0.0803 - accuracy: 0.9688 - val_loss: 0.4464 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 303/400
7/7 - 0s - loss: 0.0801 - accuracy: 0.9688 - val_loss: 0.4466 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 304/400
7/7 - 0s - loss: 0.0798 - accuracy: 0.9609 - val_loss: 0.4473 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 305/400
7/7 - 0s - loss: 0.0806 - accuracy: 0.9609 - val_loss: 0.4465 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 306/400
7/7 - 0s - loss: 0.0801 - accuracy: 0.9688 - val_loss: 0.4511 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 307/400
7/7 - 0s - loss: 0.0796 - accuracy: 0.9688 - val_loss: 0.4513 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 308/400
7/7 - 0s - loss: 0.0791 - accuracy: 0.9688 - val_loss: 0.4515 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 309/400
7/7 - 0s - loss: 0.0795 - accuracy: 0.9688 - val_loss: 0.4548 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 310/400
7/7 - 0s - loss: 0.0788 - accuracy: 0.9609 - val_loss: 0.4529 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 311/400
7/7 - 0s - loss: 0.0795 - accuracy: 0.9688 - val_loss: 0.4538 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 312/400
7/7 - 0s - loss: 0.0790 - accuracy: 0.9688 - val_loss: 0.4535 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 313/400
7/7 - 0s - loss: 0.0787 - accuracy: 0.9688 - val_loss: 0.4545 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 314/400
7/7 - 0s - loss: 0.0790 - accuracy: 0.9688 - val_loss: 0.4543 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 315/400
7/7 - 0s - loss: 0.0787 - accuracy: 0.9688 - val_loss: 0.4558 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 316/400
7/7 - 0s - loss: 0.0786 - accuracy: 0.9609 - val_loss: 0.4558 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 317/400
7/7 - 0s - loss: 0.0784 - accuracy: 0.9609 - val_loss: 0.4552 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 318/400
7/7 - 0s - loss: 0.0787 - accuracy: 0.9688 - val_loss: 0.4560 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 319/400
7/7 - 0s - loss: 0.0778 - accuracy: 0.9609 - val_loss: 0.4555 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 320/400
7/7 - 0s - loss: 0.0774 - accuracy: 0.9609 - val_loss: 0.4564 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 321/400
7/7 - 0s - loss: 0.0779 - accuracy: 0.9688 - val_loss: 0.4580 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 322/400
7/7 - 0s - loss: 0.0777 - accuracy: 0.9688 - val_loss: 0.4587 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 323/400
7/7 - 0s - loss: 0.0778 - accuracy: 0.9688 - val_loss: 0.4631 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 324/400
7/7 - 0s - loss: 0.0770 - accuracy: 0.9688 - val_loss: 0.4657 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 325/400
7/7 - 0s - loss: 0.0771 - accuracy: 0.9609 - val_loss: 0.4675 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 326/400
7/7 - 0s - loss: 0.0772 - accuracy: 0.9609 - val_loss: 0.4657 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 327/400
7/7 - 0s - loss: 0.0766 - accuracy: 0.9609 - val_loss: 0.4680 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 328/400
7/7 - 0s - loss: 0.0771 - accuracy: 0.9609 - val_loss: 0.4673 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 329/400
7/7 - 0s - loss: 0.0768 - accuracy: 0.9609 - val_loss: 0.4681 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 330/400
7/7 - 0s - loss: 0.0766 - accuracy: 0.9609 - val_loss: 0.4723 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 331/400
7/7 - 0s - loss: 0.0757 - accuracy: 0.9609 - val_loss: 0.4752 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 332/400
7/7 - 0s - loss: 0.0765 - accuracy: 0.9609 - val_loss: 0.4728 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 333/400
7/7 - 0s - loss: 0.0758 - accuracy: 0.9609 - val_loss: 0.4731 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 334/400
7/7 - 0s - loss: 0.0763 - accuracy: 0.9609 - val_loss: 0.4678 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 335/400
7/7 - 0s - loss: 0.0749 - accuracy: 0.9688 - val_loss: 0.4682 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 336/400
7/7 - 0s - loss: 0.0758 - accuracy: 0.9688 - val_loss: 0.4656 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 337/400
7/7 - 0s - loss: 0.0756 - accuracy: 0.9688 - val_loss: 0.4670 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 338/400
7/7 - 0s - loss: 0.0754 - accuracy: 0.9609 - val_loss: 0.4689 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 339/400
7/7 - 0s - loss: 0.0762 - accuracy: 0.9609 - val_loss: 0.4697 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 340/400
7/7 - 0s - loss: 0.0756 - accuracy: 0.9688 - val_loss: 0.4718 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 341/400
7/7 - 0s - loss: 0.0749 - accuracy: 0.9609 - val_loss: 0.4725 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 342/400
7/7 - 0s - loss: 0.0755 - accuracy: 0.9609 - val_loss: 0.4720 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 343/400
7/7 - 0s - loss: 0.0745 - accuracy: 0.9688 - val_loss: 0.4725 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 344/400
7/7 - 0s - loss: 0.0744 - accuracy: 0.9688 - val_loss: 0.4754 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 345/400
7/7 - 0s - loss: 0.0749 - accuracy: 0.9609 - val_loss: 0.4771 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 346/400
7/7 - 0s - loss: 0.0747 - accuracy: 0.9609 - val_loss: 0.4819 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 347/400
7/7 - 0s - loss: 0.0745 - accuracy: 0.9609 - val_loss: 0.4812 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 348/400
7/7 - 0s - loss: 0.0740 - accuracy: 0.9609 - val_loss: 0.4803 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 349/400
7/7 - 0s - loss: 0.0746 - accuracy: 0.9609 - val_loss: 0.4804 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 350/400
7/7 - 0s - loss: 0.0741 - accuracy: 0.9609 - val_loss: 0.4806 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 351/400
7/7 - 0s - loss: 0.0744 - accuracy: 0.9609 - val_loss: 0.4828 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 352/400
7/7 - 0s - loss: 0.0733 - accuracy: 0.9609 - val_loss: 0.4824 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 353/400
7/7 - 0s - loss: 0.0744 - accuracy: 0.9609 - val_loss: 0.4823 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 354/400
7/7 - 0s - loss: 0.0739 - accuracy: 0.9609 - val_loss: 0.4833 - val_accuracy: 0.8750 - 38ms/epoch - 5ms/step
Epoch 355/400
7/7 - 0s - loss: 0.0735 - accuracy: 0.9609 - val_loss: 0.4870 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 356/400
7/7 - 0s - loss: 0.0738 - accuracy: 0.9609 - val_loss: 0.4867 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 357/400
7/7 - 0s - loss: 0.0738 - accuracy: 0.9609 - val_loss: 0.4860 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 358/400
7/7 - 0s - loss: 0.0741 - accuracy: 0.9609 - val_loss: 0.4886 - val_accuracy: 0.8750 - 38ms/epoch - 5ms/step
Epoch 359/400
7/7 - 0s - loss: 0.0735 - accuracy: 0.9609 - val_loss: 0.4877 - val_accuracy: 0.8750 - 38ms/epoch - 5ms/step
Epoch 360/400
7/7 - 0s - loss: 0.0731 - accuracy: 0.9609 - val_loss: 0.4844 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 361/400
7/7 - 0s - loss: 0.0729 - accuracy: 0.9609 - val_loss: 0.4863 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 362/400
7/7 - 0s - loss: 0.0731 - accuracy: 0.9609 - val_loss: 0.4863 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 363/400
7/7 - 0s - loss: 0.0731 - accuracy: 0.9609 - val_loss: 0.4864 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 364/400
7/7 - 0s - loss: 0.0726 - accuracy: 0.9609 - val_loss: 0.4884 - val_accuracy: 0.8750 - 38ms/epoch - 5ms/step
Epoch 365/400
7/7 - 0s - loss: 0.0740 - accuracy: 0.9609 - val_loss: 0.4876 - val_accuracy: 0.8750 - 38ms/epoch - 5ms/step
Epoch 366/400
7/7 - 0s - loss: 0.0727 - accuracy: 0.9609 - val_loss: 0.4858 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 367/400
7/7 - 0s - loss: 0.0724 - accuracy: 0.9609 - val_loss: 0.4878 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 368/400
7/7 - 0s - loss: 0.0732 - accuracy: 0.9609 - val_loss: 0.4881 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 369/400
7/7 - 0s - loss: 0.0728 - accuracy: 0.9609 - val_loss: 0.4891 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 370/400
7/7 - 0s - loss: 0.0726 - accuracy: 0.9609 - val_loss: 0.4905 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 371/400
7/7 - 0s - loss: 0.0720 - accuracy: 0.9688 - val_loss: 0.4944 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 372/400
7/7 - 0s - loss: 0.0727 - accuracy: 0.9609 - val_loss: 0.4938 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 373/400
7/7 - 0s - loss: 0.0716 - accuracy: 0.9609 - val_loss: 0.4942 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 374/400
7/7 - 0s - loss: 0.0720 - accuracy: 0.9609 - val_loss: 0.4908 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 375/400
7/7 - 0s - loss: 0.0717 - accuracy: 0.9609 - val_loss: 0.4927 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 376/400
7/7 - 0s - loss: 0.0725 - accuracy: 0.9609 - val_loss: 0.4926 - val_accuracy: 0.8750 - 46ms/epoch - 7ms/step
Epoch 377/400
7/7 - 0s - loss: 0.0715 - accuracy: 0.9609 - val_loss: 0.4937 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 378/400
7/7 - 0s - loss: 0.0716 - accuracy: 0.9609 - val_loss: 0.4953 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 379/400
7/7 - 0s - loss: 0.0717 - accuracy: 0.9609 - val_loss: 0.4982 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 380/400
7/7 - 0s - loss: 0.0715 - accuracy: 0.9609 - val_loss: 0.4976 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 381/400
7/7 - 0s - loss: 0.0712 - accuracy: 0.9609 - val_loss: 0.4965 - val_accuracy: 0.8750 - 41ms/epoch - 6ms/step
Epoch 382/400
7/7 - 0s - loss: 0.0719 - accuracy: 0.9609 - val_loss: 0.4977 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 383/400
7/7 - 0s - loss: 0.0706 - accuracy: 0.9609 - val_loss: 0.4979 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 384/400
7/7 - 0s - loss: 0.0711 - accuracy: 0.9609 - val_loss: 0.5000 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 385/400
7/7 - 0s - loss: 0.0711 - accuracy: 0.9609 - val_loss: 0.5002 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 386/400
7/7 - 0s - loss: 0.0711 - accuracy: 0.9609 - val_loss: 0.4984 - val_accuracy: 0.8750 - 38ms/epoch - 5ms/step
Epoch 387/400
7/7 - 0s - loss: 0.0715 - accuracy: 0.9609 - val_loss: 0.4989 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 388/400
7/7 - 0s - loss: 0.0709 - accuracy: 0.9609 - val_loss: 0.4970 - val_accuracy: 0.8750 - 37ms/epoch - 5ms/step
Epoch 389/400
7/7 - 0s - loss: 0.0707 - accuracy: 0.9609 - val_loss: 0.4985 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 390/400
7/7 - 0s - loss: 0.0702 - accuracy: 0.9609 - val_loss: 0.4996 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 391/400
7/7 - 0s - loss: 0.0702 - accuracy: 0.9609 - val_loss: 0.5030 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 392/400
7/7 - 0s - loss: 0.0706 - accuracy: 0.9609 - val_loss: 0.5039 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 393/400
7/7 - 0s - loss: 0.0701 - accuracy: 0.9609 - val_loss: 0.5036 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 394/400
7/7 - 0s - loss: 0.0710 - accuracy: 0.9609 - val_loss: 0.4993 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 395/400
7/7 - 0s - loss: 0.0696 - accuracy: 0.9609 - val_loss: 0.5013 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 396/400
7/7 - 0s - loss: 0.0707 - accuracy: 0.9609 - val_loss: 0.5024 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 397/400
7/7 - 0s - loss: 0.0706 - accuracy: 0.9609 - val_loss: 0.5030 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 398/400
7/7 - 0s - loss: 0.0696 - accuracy: 0.9609 - val_loss: 0.5037 - val_accuracy: 0.8750 - 35ms/epoch - 5ms/step
Epoch 399/400
7/7 - 0s - loss: 0.0701 - accuracy: 0.9609 - val_loss: 0.5023 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 400/400
7/7 - 0s - loss: 0.0698 - accuracy: 0.9609 - val_loss: 0.5016 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step

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

Evaluate Network Performance

The final performance can be obtained like so.

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

5/5 - 0s - loss: 0.1552 - accuracy: 0.9438 - 20ms/epoch - 4ms/step

print(perf)

     loss  accuracy 
0.1551989 0.9437500

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

2/2 - 0s - loss: 0.0539 - accuracy: 0.9750 - 18ms/epoch - 9ms/step

print(perf)

      loss   accuracy 
0.05392377 0.97500002