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

dim(y_train)

NULL

dim(y_test)

NULL

Set Architecture

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

keras activation

model <- keras_model_sequential()
model |>  
  layer_dense(units = 4, activation = 'relu', input_shape = 2) |> 
  layer_dense(units = 1, activation = 'sigmoid')
model |> summary()

Model: "sequential"
________________________________________________________________________________
 Layer (type)                       Output Shape                    Param #     
================================================================================
 dense_1 (Dense)                    (None, 4)                       12          
 dense (Dense)                      (None, 1)                       5           
================================================================================
Total params: 17
Trainable params: 17
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: 0.7175 - accuracy: 0.5000 - val_loss: 0.7381 - val_accuracy: 0.4375 - 996ms/epoch - 142ms/step
Epoch 2/400
7/7 - 0s - loss: 0.7052 - accuracy: 0.5469 - val_loss: 0.7365 - val_accuracy: 0.5000 - 45ms/epoch - 6ms/step
Epoch 3/400
7/7 - 0s - loss: 0.6968 - accuracy: 0.5703 - val_loss: 0.7346 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 4/400
7/7 - 0s - loss: 0.6907 - accuracy: 0.6016 - val_loss: 0.7316 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 5/400
7/7 - 0s - loss: 0.6836 - accuracy: 0.6172 - val_loss: 0.7286 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 6/400
7/7 - 0s - loss: 0.6778 - accuracy: 0.6172 - val_loss: 0.7265 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 7/400
7/7 - 0s - loss: 0.6719 - accuracy: 0.6172 - val_loss: 0.7247 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 8/400
7/7 - 0s - loss: 0.6664 - accuracy: 0.6172 - val_loss: 0.7225 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 9/400
7/7 - 0s - loss: 0.6614 - accuracy: 0.6406 - val_loss: 0.7202 - val_accuracy: 0.5000 - 32ms/epoch - 5ms/step
Epoch 10/400
7/7 - 0s - loss: 0.6563 - accuracy: 0.6562 - val_loss: 0.7182 - val_accuracy: 0.5000 - 31ms/epoch - 4ms/step
Epoch 11/400
7/7 - 0s - loss: 0.6518 - accuracy: 0.6719 - val_loss: 0.7167 - val_accuracy: 0.5000 - 32ms/epoch - 5ms/step
Epoch 12/400
7/7 - 0s - loss: 0.6472 - accuracy: 0.6797 - val_loss: 0.7155 - val_accuracy: 0.5000 - 32ms/epoch - 5ms/step
Epoch 13/400
7/7 - 0s - loss: 0.6429 - accuracy: 0.6875 - val_loss: 0.7130 - val_accuracy: 0.5000 - 84ms/epoch - 12ms/step
Epoch 14/400
7/7 - 0s - loss: 0.6391 - accuracy: 0.6797 - val_loss: 0.7118 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 15/400
7/7 - 0s - loss: 0.6354 - accuracy: 0.6875 - val_loss: 0.7094 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 16/400
7/7 - 0s - loss: 0.6317 - accuracy: 0.6953 - val_loss: 0.7075 - val_accuracy: 0.5000 - 33ms/epoch - 5ms/step
Epoch 17/400
7/7 - 0s - loss: 0.6281 - accuracy: 0.6953 - val_loss: 0.7059 - val_accuracy: 0.5000 - 32ms/epoch - 5ms/step
Epoch 18/400
7/7 - 0s - loss: 0.6242 - accuracy: 0.6953 - val_loss: 0.7035 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 19/400
7/7 - 0s - loss: 0.6212 - accuracy: 0.6953 - val_loss: 0.7020 - val_accuracy: 0.5312 - 33ms/epoch - 5ms/step
Epoch 20/400
7/7 - 0s - loss: 0.6175 - accuracy: 0.6953 - val_loss: 0.7005 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 21/400
7/7 - 0s - loss: 0.6140 - accuracy: 0.7031 - val_loss: 0.6986 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 22/400
7/7 - 0s - loss: 0.6108 - accuracy: 0.7031 - val_loss: 0.6962 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 23/400
7/7 - 0s - loss: 0.6074 - accuracy: 0.7031 - val_loss: 0.6951 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 24/400
7/7 - 0s - loss: 0.6043 - accuracy: 0.7031 - val_loss: 0.6932 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 25/400
7/7 - 0s - loss: 0.6010 - accuracy: 0.7031 - val_loss: 0.6904 - val_accuracy: 0.5312 - 32ms/epoch - 5ms/step
Epoch 26/400
7/7 - 0s - loss: 0.5980 - accuracy: 0.7109 - val_loss: 0.6888 - val_accuracy: 0.5312 - 31ms/epoch - 4ms/step
Epoch 27/400
7/7 - 0s - loss: 0.5949 - accuracy: 0.7109 - val_loss: 0.6865 - val_accuracy: 0.5625 - 31ms/epoch - 4ms/step
Epoch 28/400
7/7 - 0s - loss: 0.5922 - accuracy: 0.7109 - val_loss: 0.6834 - val_accuracy: 0.5625 - 31ms/epoch - 4ms/step
Epoch 29/400
7/7 - 0s - loss: 0.5892 - accuracy: 0.7109 - val_loss: 0.6801 - val_accuracy: 0.5625 - 32ms/epoch - 5ms/step
Epoch 30/400
7/7 - 0s - loss: 0.5862 - accuracy: 0.7109 - val_loss: 0.6774 - val_accuracy: 0.5625 - 31ms/epoch - 4ms/step
Epoch 31/400
7/7 - 0s - loss: 0.5828 - accuracy: 0.7109 - val_loss: 0.6746 - val_accuracy: 0.5625 - 31ms/epoch - 4ms/step
Epoch 32/400
7/7 - 0s - loss: 0.5804 - accuracy: 0.7109 - val_loss: 0.6730 - val_accuracy: 0.5625 - 32ms/epoch - 5ms/step
Epoch 33/400
7/7 - 0s - loss: 0.5775 - accuracy: 0.7188 - val_loss: 0.6704 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 34/400
7/7 - 0s - loss: 0.5750 - accuracy: 0.7109 - val_loss: 0.6682 - val_accuracy: 0.5625 - 31ms/epoch - 4ms/step
Epoch 35/400
7/7 - 0s - loss: 0.5723 - accuracy: 0.7109 - val_loss: 0.6661 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 36/400
7/7 - 0s - loss: 0.5694 - accuracy: 0.7109 - val_loss: 0.6630 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 37/400
7/7 - 0s - loss: 0.5666 - accuracy: 0.7109 - val_loss: 0.6602 - val_accuracy: 0.5625 - 32ms/epoch - 5ms/step
Epoch 38/400
7/7 - 0s - loss: 0.5637 - accuracy: 0.7031 - val_loss: 0.6587 - val_accuracy: 0.5625 - 31ms/epoch - 4ms/step
Epoch 39/400
7/7 - 0s - loss: 0.5610 - accuracy: 0.7109 - val_loss: 0.6555 - val_accuracy: 0.5625 - 32ms/epoch - 5ms/step
Epoch 40/400
7/7 - 0s - loss: 0.5581 - accuracy: 0.7109 - val_loss: 0.6529 - val_accuracy: 0.5625 - 32ms/epoch - 5ms/step
Epoch 41/400
7/7 - 0s - loss: 0.5552 - accuracy: 0.7109 - val_loss: 0.6494 - val_accuracy: 0.5625 - 31ms/epoch - 4ms/step
Epoch 42/400
7/7 - 0s - loss: 0.5523 - accuracy: 0.7109 - val_loss: 0.6474 - val_accuracy: 0.5625 - 32ms/epoch - 5ms/step
Epoch 43/400
7/7 - 0s - loss: 0.5496 - accuracy: 0.7109 - val_loss: 0.6444 - val_accuracy: 0.5625 - 32ms/epoch - 5ms/step
Epoch 44/400
7/7 - 0s - loss: 0.5466 - accuracy: 0.7109 - val_loss: 0.6426 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 45/400
7/7 - 0s - loss: 0.5433 - accuracy: 0.7188 - val_loss: 0.6390 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 46/400
7/7 - 0s - loss: 0.5401 - accuracy: 0.7422 - val_loss: 0.6356 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 47/400
7/7 - 0s - loss: 0.5371 - accuracy: 0.7500 - val_loss: 0.6327 - val_accuracy: 0.5938 - 32ms/epoch - 5ms/step
Epoch 48/400
7/7 - 0s - loss: 0.5340 - accuracy: 0.7578 - val_loss: 0.6306 - val_accuracy: 0.6250 - 32ms/epoch - 5ms/step
Epoch 49/400
7/7 - 0s - loss: 0.5313 - accuracy: 0.7578 - val_loss: 0.6278 - val_accuracy: 0.6250 - 32ms/epoch - 5ms/step
Epoch 50/400
7/7 - 0s - loss: 0.5280 - accuracy: 0.7578 - val_loss: 0.6254 - val_accuracy: 0.6562 - 34ms/epoch - 5ms/step
Epoch 51/400
7/7 - 0s - loss: 0.5250 - accuracy: 0.7812 - val_loss: 0.6236 - val_accuracy: 0.6562 - 32ms/epoch - 5ms/step
Epoch 52/400
7/7 - 0s - loss: 0.5220 - accuracy: 0.7812 - val_loss: 0.6204 - val_accuracy: 0.6562 - 31ms/epoch - 4ms/step
Epoch 53/400
7/7 - 0s - loss: 0.5188 - accuracy: 0.7812 - val_loss: 0.6170 - val_accuracy: 0.6562 - 33ms/epoch - 5ms/step
Epoch 54/400
7/7 - 0s - loss: 0.5158 - accuracy: 0.8125 - val_loss: 0.6142 - val_accuracy: 0.6562 - 33ms/epoch - 5ms/step
Epoch 55/400
7/7 - 0s - loss: 0.5127 - accuracy: 0.8125 - val_loss: 0.6108 - val_accuracy: 0.6562 - 32ms/epoch - 5ms/step
Epoch 56/400
7/7 - 0s - loss: 0.5091 - accuracy: 0.8125 - val_loss: 0.6068 - val_accuracy: 0.6562 - 34ms/epoch - 5ms/step
Epoch 57/400
7/7 - 0s - loss: 0.5064 - accuracy: 0.8203 - val_loss: 0.6046 - val_accuracy: 0.6562 - 32ms/epoch - 5ms/step
Epoch 58/400
7/7 - 0s - loss: 0.5030 - accuracy: 0.8281 - val_loss: 0.6021 - val_accuracy: 0.6562 - 32ms/epoch - 5ms/step
Epoch 59/400
7/7 - 0s - loss: 0.5002 - accuracy: 0.8281 - val_loss: 0.5981 - val_accuracy: 0.6562 - 31ms/epoch - 4ms/step
Epoch 60/400
7/7 - 0s - loss: 0.4969 - accuracy: 0.8438 - val_loss: 0.5951 - val_accuracy: 0.6562 - 32ms/epoch - 5ms/step
Epoch 61/400
7/7 - 0s - loss: 0.4940 - accuracy: 0.8359 - val_loss: 0.5916 - val_accuracy: 0.6562 - 34ms/epoch - 5ms/step
Epoch 62/400
7/7 - 0s - loss: 0.4912 - accuracy: 0.8438 - val_loss: 0.5880 - val_accuracy: 0.6875 - 33ms/epoch - 5ms/step
Epoch 63/400
7/7 - 0s - loss: 0.4881 - accuracy: 0.8281 - val_loss: 0.5859 - val_accuracy: 0.6875 - 31ms/epoch - 4ms/step
Epoch 64/400
7/7 - 0s - loss: 0.4853 - accuracy: 0.8359 - val_loss: 0.5823 - val_accuracy: 0.6875 - 33ms/epoch - 5ms/step
Epoch 65/400
7/7 - 0s - loss: 0.4822 - accuracy: 0.8203 - val_loss: 0.5796 - val_accuracy: 0.6875 - 36ms/epoch - 5ms/step
Epoch 66/400
7/7 - 0s - loss: 0.4793 - accuracy: 0.8281 - val_loss: 0.5775 - val_accuracy: 0.6875 - 33ms/epoch - 5ms/step
Epoch 67/400
7/7 - 0s - loss: 0.4767 - accuracy: 0.8281 - val_loss: 0.5746 - val_accuracy: 0.6562 - 32ms/epoch - 5ms/step
Epoch 68/400
7/7 - 0s - loss: 0.4738 - accuracy: 0.8281 - val_loss: 0.5708 - val_accuracy: 0.6875 - 32ms/epoch - 5ms/step
Epoch 69/400
7/7 - 0s - loss: 0.4709 - accuracy: 0.8281 - val_loss: 0.5674 - val_accuracy: 0.6875 - 42ms/epoch - 6ms/step
Epoch 70/400
7/7 - 0s - loss: 0.4682 - accuracy: 0.8359 - val_loss: 0.5642 - val_accuracy: 0.6875 - 33ms/epoch - 5ms/step
Epoch 71/400
7/7 - 0s - loss: 0.4654 - accuracy: 0.8359 - val_loss: 0.5609 - val_accuracy: 0.6875 - 32ms/epoch - 5ms/step
Epoch 72/400
7/7 - 0s - loss: 0.4627 - accuracy: 0.8359 - val_loss: 0.5572 - val_accuracy: 0.7188 - 33ms/epoch - 5ms/step
Epoch 73/400
7/7 - 0s - loss: 0.4602 - accuracy: 0.8359 - val_loss: 0.5543 - val_accuracy: 0.7500 - 32ms/epoch - 5ms/step
Epoch 74/400
7/7 - 0s - loss: 0.4574 - accuracy: 0.8438 - val_loss: 0.5525 - val_accuracy: 0.7500 - 32ms/epoch - 5ms/step
Epoch 75/400
7/7 - 0s - loss: 0.4550 - accuracy: 0.8594 - val_loss: 0.5498 - val_accuracy: 0.7500 - 33ms/epoch - 5ms/step
Epoch 76/400
7/7 - 0s - loss: 0.4522 - accuracy: 0.8594 - val_loss: 0.5473 - val_accuracy: 0.7500 - 34ms/epoch - 5ms/step
Epoch 77/400
7/7 - 0s - loss: 0.4500 - accuracy: 0.8594 - val_loss: 0.5457 - val_accuracy: 0.7500 - 35ms/epoch - 5ms/step
Epoch 78/400
7/7 - 0s - loss: 0.4476 - accuracy: 0.8594 - val_loss: 0.5434 - val_accuracy: 0.7500 - 32ms/epoch - 5ms/step
Epoch 79/400
7/7 - 0s - loss: 0.4449 - accuracy: 0.8594 - val_loss: 0.5400 - val_accuracy: 0.7500 - 33ms/epoch - 5ms/step
Epoch 80/400
7/7 - 0s - loss: 0.4424 - accuracy: 0.8594 - val_loss: 0.5375 - val_accuracy: 0.7500 - 33ms/epoch - 5ms/step
Epoch 81/400
7/7 - 0s - loss: 0.4400 - accuracy: 0.8594 - val_loss: 0.5343 - val_accuracy: 0.7500 - 33ms/epoch - 5ms/step
Epoch 82/400
7/7 - 0s - loss: 0.4375 - accuracy: 0.8594 - val_loss: 0.5323 - val_accuracy: 0.7812 - 34ms/epoch - 5ms/step
Epoch 83/400
7/7 - 0s - loss: 0.4352 - accuracy: 0.8594 - val_loss: 0.5295 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 84/400
7/7 - 0s - loss: 0.4329 - accuracy: 0.8594 - val_loss: 0.5272 - val_accuracy: 0.7812 - 31ms/epoch - 4ms/step
Epoch 85/400
7/7 - 0s - loss: 0.4304 - accuracy: 0.8594 - val_loss: 0.5250 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 86/400
7/7 - 0s - loss: 0.4283 - accuracy: 0.8594 - val_loss: 0.5218 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 87/400
7/7 - 0s - loss: 0.4261 - accuracy: 0.8594 - val_loss: 0.5198 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 88/400
7/7 - 0s - loss: 0.4240 - accuracy: 0.8594 - val_loss: 0.5180 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 89/400
7/7 - 0s - loss: 0.4220 - accuracy: 0.8594 - val_loss: 0.5161 - val_accuracy: 0.7812 - 35ms/epoch - 5ms/step
Epoch 90/400
7/7 - 0s - loss: 0.4201 - accuracy: 0.8516 - val_loss: 0.5129 - val_accuracy: 0.7812 - 34ms/epoch - 5ms/step
Epoch 91/400
7/7 - 0s - loss: 0.4180 - accuracy: 0.8594 - val_loss: 0.5102 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 92/400
7/7 - 0s - loss: 0.4159 - accuracy: 0.8516 - val_loss: 0.5087 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 93/400
7/7 - 0s - loss: 0.4143 - accuracy: 0.8516 - val_loss: 0.5075 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 94/400
7/7 - 0s - loss: 0.4124 - accuracy: 0.8516 - val_loss: 0.5054 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 95/400
7/7 - 0s - loss: 0.4104 - accuracy: 0.8516 - val_loss: 0.5036 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 96/400
7/7 - 0s - loss: 0.4085 - accuracy: 0.8516 - val_loss: 0.5012 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 97/400
7/7 - 0s - loss: 0.4065 - accuracy: 0.8516 - val_loss: 0.4993 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 98/400
7/7 - 0s - loss: 0.4046 - accuracy: 0.8516 - val_loss: 0.4972 - val_accuracy: 0.7812 - 31ms/epoch - 4ms/step
Epoch 99/400
7/7 - 0s - loss: 0.4026 - accuracy: 0.8516 - val_loss: 0.4950 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 100/400
7/7 - 0s - loss: 0.4010 - accuracy: 0.8438 - val_loss: 0.4932 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 101/400
7/7 - 0s - loss: 0.3989 - accuracy: 0.8516 - val_loss: 0.4914 - val_accuracy: 0.7812 - 32ms/epoch - 5ms/step
Epoch 102/400
7/7 - 0s - loss: 0.3972 - accuracy: 0.8438 - val_loss: 0.4892 - val_accuracy: 0.7812 - 33ms/epoch - 5ms/step
Epoch 103/400
7/7 - 0s - loss: 0.3954 - accuracy: 0.8516 - val_loss: 0.4869 - val_accuracy: 0.7812 - 31ms/epoch - 4ms/step
Epoch 104/400
7/7 - 0s - loss: 0.3938 - accuracy: 0.8516 - val_loss: 0.4853 - val_accuracy: 0.8125 - 32ms/epoch - 5ms/step
Epoch 105/400
7/7 - 0s - loss: 0.3919 - accuracy: 0.8516 - val_loss: 0.4831 - val_accuracy: 0.8125 - 35ms/epoch - 5ms/step
Epoch 106/400
7/7 - 0s - loss: 0.3903 - accuracy: 0.8516 - val_loss: 0.4809 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 107/400
7/7 - 0s - loss: 0.3884 - accuracy: 0.8594 - val_loss: 0.4778 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 108/400
7/7 - 0s - loss: 0.3868 - accuracy: 0.8594 - val_loss: 0.4769 - val_accuracy: 0.8125 - 36ms/epoch - 5ms/step
Epoch 109/400
7/7 - 0s - loss: 0.3852 - accuracy: 0.8594 - val_loss: 0.4746 - val_accuracy: 0.8125 - 32ms/epoch - 5ms/step
Epoch 110/400
7/7 - 0s - loss: 0.3837 - accuracy: 0.8672 - val_loss: 0.4731 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 111/400
7/7 - 0s - loss: 0.3819 - accuracy: 0.8672 - val_loss: 0.4705 - val_accuracy: 0.8125 - 34ms/epoch - 5ms/step
Epoch 112/400
7/7 - 0s - loss: 0.3800 - accuracy: 0.8750 - val_loss: 0.4690 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 113/400
7/7 - 0s - loss: 0.3784 - accuracy: 0.8750 - val_loss: 0.4673 - val_accuracy: 0.8125 - 32ms/epoch - 5ms/step
Epoch 114/400
7/7 - 0s - loss: 0.3765 - accuracy: 0.8750 - val_loss: 0.4652 - val_accuracy: 0.8125 - 34ms/epoch - 5ms/step
Epoch 115/400
7/7 - 0s - loss: 0.3749 - accuracy: 0.8750 - val_loss: 0.4631 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 116/400
7/7 - 0s - loss: 0.3730 - accuracy: 0.8750 - val_loss: 0.4602 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 117/400
7/7 - 0s - loss: 0.3715 - accuracy: 0.8750 - val_loss: 0.4590 - val_accuracy: 0.8125 - 33ms/epoch - 5ms/step
Epoch 118/400
7/7 - 0s - loss: 0.3700 - accuracy: 0.8750 - val_loss: 0.4563 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 119/400
7/7 - 0s - loss: 0.3684 - accuracy: 0.8750 - val_loss: 0.4549 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 120/400
7/7 - 0s - loss: 0.3671 - accuracy: 0.8750 - val_loss: 0.4530 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 121/400
7/7 - 0s - loss: 0.3659 - accuracy: 0.8828 - val_loss: 0.4519 - val_accuracy: 0.8750 - 34ms/epoch - 5ms/step
Epoch 122/400
7/7 - 0s - loss: 0.3641 - accuracy: 0.8828 - val_loss: 0.4506 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 123/400
7/7 - 0s - loss: 0.3627 - accuracy: 0.8828 - val_loss: 0.4487 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 124/400
7/7 - 0s - loss: 0.3614 - accuracy: 0.8828 - val_loss: 0.4475 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 125/400
7/7 - 0s - loss: 0.3600 - accuracy: 0.8828 - val_loss: 0.4459 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 126/400
7/7 - 0s - loss: 0.3582 - accuracy: 0.8828 - val_loss: 0.4443 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 127/400
7/7 - 0s - loss: 0.3568 - accuracy: 0.8906 - val_loss: 0.4430 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 128/400
7/7 - 0s - loss: 0.3553 - accuracy: 0.8828 - val_loss: 0.4407 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 129/400
7/7 - 0s - loss: 0.3537 - accuracy: 0.8906 - val_loss: 0.4388 - val_accuracy: 0.8750 - 31ms/epoch - 4ms/step
Epoch 130/400
7/7 - 0s - loss: 0.3518 - accuracy: 0.8984 - val_loss: 0.4376 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 131/400
7/7 - 0s - loss: 0.3504 - accuracy: 0.8984 - val_loss: 0.4364 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 132/400
7/7 - 0s - loss: 0.3491 - accuracy: 0.8984 - val_loss: 0.4353 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 133/400
7/7 - 0s - loss: 0.3474 - accuracy: 0.8984 - val_loss: 0.4345 - val_accuracy: 0.8750 - 32ms/epoch - 5ms/step
Epoch 134/400
7/7 - 0s - loss: 0.3460 - accuracy: 0.8984 - val_loss: 0.4328 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 135/400
7/7 - 0s - loss: 0.3450 - accuracy: 0.8984 - val_loss: 0.4318 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 136/400
7/7 - 0s - loss: 0.3433 - accuracy: 0.8984 - val_loss: 0.4300 - val_accuracy: 0.8750 - 33ms/epoch - 5ms/step
Epoch 137/400
7/7 - 0s - loss: 0.3421 - accuracy: 0.8984 - val_loss: 0.4288 - val_accuracy: 0.8750 - 36ms/epoch - 5ms/step
Epoch 138/400
7/7 - 0s - loss: 0.3411 - accuracy: 0.8984 - val_loss: 0.4273 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 139/400
7/7 - 0s - loss: 0.3399 - accuracy: 0.8984 - val_loss: 0.4255 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 140/400
7/7 - 0s - loss: 0.3388 - accuracy: 0.8984 - val_loss: 0.4244 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 141/400
7/7 - 0s - loss: 0.3376 - accuracy: 0.8984 - val_loss: 0.4234 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 142/400
7/7 - 0s - loss: 0.3361 - accuracy: 0.8984 - val_loss: 0.4228 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 143/400
7/7 - 0s - loss: 0.3350 - accuracy: 0.8984 - val_loss: 0.4223 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 144/400
7/7 - 0s - loss: 0.3335 - accuracy: 0.8984 - val_loss: 0.4209 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 145/400
7/7 - 0s - loss: 0.3326 - accuracy: 0.8984 - val_loss: 0.4202 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 146/400
7/7 - 0s - loss: 0.3315 - accuracy: 0.8984 - val_loss: 0.4188 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 147/400
7/7 - 0s - loss: 0.3302 - accuracy: 0.8984 - val_loss: 0.4180 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 148/400
7/7 - 0s - loss: 0.3289 - accuracy: 0.8984 - val_loss: 0.4166 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 149/400
7/7 - 0s - loss: 0.3277 - accuracy: 0.8984 - val_loss: 0.4160 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 150/400
7/7 - 0s - loss: 0.3265 - accuracy: 0.8984 - val_loss: 0.4144 - val_accuracy: 0.9062 - 37ms/epoch - 5ms/step
Epoch 151/400
7/7 - 0s - loss: 0.3254 - accuracy: 0.8984 - val_loss: 0.4132 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 152/400
7/7 - 0s - loss: 0.3238 - accuracy: 0.8984 - val_loss: 0.4116 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 153/400
7/7 - 0s - loss: 0.3229 - accuracy: 0.8984 - val_loss: 0.4098 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 154/400
7/7 - 0s - loss: 0.3217 - accuracy: 0.8984 - val_loss: 0.4091 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 155/400
7/7 - 0s - loss: 0.3209 - accuracy: 0.8984 - val_loss: 0.4074 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 156/400
7/7 - 0s - loss: 0.3198 - accuracy: 0.8984 - val_loss: 0.4068 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 157/400
7/7 - 0s - loss: 0.3188 - accuracy: 0.8984 - val_loss: 0.4061 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 158/400
7/7 - 0s - loss: 0.3179 - accuracy: 0.8984 - val_loss: 0.4056 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 159/400
7/7 - 0s - loss: 0.3168 - accuracy: 0.8984 - val_loss: 0.4039 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 160/400
7/7 - 0s - loss: 0.3156 - accuracy: 0.8984 - val_loss: 0.4023 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 161/400
7/7 - 0s - loss: 0.3146 - accuracy: 0.8984 - val_loss: 0.4022 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 162/400
7/7 - 0s - loss: 0.3135 - accuracy: 0.8984 - val_loss: 0.4014 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 163/400
7/7 - 0s - loss: 0.3124 - accuracy: 0.8984 - val_loss: 0.3999 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 164/400
7/7 - 0s - loss: 0.3113 - accuracy: 0.8984 - val_loss: 0.3990 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 165/400
7/7 - 0s - loss: 0.3104 - accuracy: 0.8984 - val_loss: 0.3975 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 166/400
7/7 - 0s - loss: 0.3092 - accuracy: 0.8984 - val_loss: 0.3962 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 167/400
7/7 - 0s - loss: 0.3085 - accuracy: 0.8984 - val_loss: 0.3949 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 168/400
7/7 - 0s - loss: 0.3073 - accuracy: 0.8984 - val_loss: 0.3947 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 169/400
7/7 - 0s - loss: 0.3063 - accuracy: 0.8984 - val_loss: 0.3930 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 170/400
7/7 - 0s - loss: 0.3055 - accuracy: 0.8984 - val_loss: 0.3925 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 171/400
7/7 - 0s - loss: 0.3044 - accuracy: 0.8984 - val_loss: 0.3920 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 172/400
7/7 - 0s - loss: 0.3034 - accuracy: 0.8984 - val_loss: 0.3913 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 173/400
7/7 - 0s - loss: 0.3022 - accuracy: 0.8984 - val_loss: 0.3904 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 174/400
7/7 - 0s - loss: 0.3013 - accuracy: 0.8984 - val_loss: 0.3901 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 175/400
7/7 - 0s - loss: 0.3003 - accuracy: 0.9062 - val_loss: 0.3901 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 176/400
7/7 - 0s - loss: 0.2996 - accuracy: 0.9062 - val_loss: 0.3890 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 177/400
7/7 - 0s - loss: 0.2986 - accuracy: 0.9062 - val_loss: 0.3876 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 178/400
7/7 - 0s - loss: 0.2977 - accuracy: 0.9062 - val_loss: 0.3868 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 179/400
7/7 - 0s - loss: 0.2969 - accuracy: 0.9141 - val_loss: 0.3866 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 180/400
7/7 - 0s - loss: 0.2958 - accuracy: 0.9141 - val_loss: 0.3858 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 181/400
7/7 - 0s - loss: 0.2949 - accuracy: 0.9062 - val_loss: 0.3843 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 182/400
7/7 - 0s - loss: 0.2938 - accuracy: 0.9141 - val_loss: 0.3839 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 183/400
7/7 - 0s - loss: 0.2930 - accuracy: 0.9141 - val_loss: 0.3828 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 184/400
7/7 - 0s - loss: 0.2921 - accuracy: 0.9297 - val_loss: 0.3821 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 185/400
7/7 - 0s - loss: 0.2911 - accuracy: 0.9297 - val_loss: 0.3817 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 186/400
7/7 - 0s - loss: 0.2904 - accuracy: 0.9297 - val_loss: 0.3802 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 187/400
7/7 - 0s - loss: 0.2894 - accuracy: 0.9297 - val_loss: 0.3795 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 188/400
7/7 - 0s - loss: 0.2888 - accuracy: 0.9297 - val_loss: 0.3786 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 189/400
7/7 - 0s - loss: 0.2877 - accuracy: 0.9297 - val_loss: 0.3779 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 190/400
7/7 - 0s - loss: 0.2869 - accuracy: 0.9297 - val_loss: 0.3772 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 191/400
7/7 - 0s - loss: 0.2860 - accuracy: 0.9297 - val_loss: 0.3756 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 192/400
7/7 - 0s - loss: 0.2854 - accuracy: 0.9297 - val_loss: 0.3753 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 193/400
7/7 - 0s - loss: 0.2845 - accuracy: 0.9297 - val_loss: 0.3741 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 194/400
7/7 - 0s - loss: 0.2838 - accuracy: 0.9297 - val_loss: 0.3737 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 195/400
7/7 - 0s - loss: 0.2830 - accuracy: 0.9297 - val_loss: 0.3734 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 196/400
7/7 - 0s - loss: 0.2821 - accuracy: 0.9297 - val_loss: 0.3731 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 197/400
7/7 - 0s - loss: 0.2816 - accuracy: 0.9297 - val_loss: 0.3724 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 198/400
7/7 - 0s - loss: 0.2810 - accuracy: 0.9219 - val_loss: 0.3718 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 199/400
7/7 - 0s - loss: 0.2802 - accuracy: 0.9297 - val_loss: 0.3711 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 200/400
7/7 - 0s - loss: 0.2795 - accuracy: 0.9297 - val_loss: 0.3707 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 201/400
7/7 - 0s - loss: 0.2789 - accuracy: 0.9297 - val_loss: 0.3693 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 202/400
7/7 - 0s - loss: 0.2781 - accuracy: 0.9297 - val_loss: 0.3685 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 203/400
7/7 - 0s - loss: 0.2774 - accuracy: 0.9297 - val_loss: 0.3678 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 204/400
7/7 - 0s - loss: 0.2770 - accuracy: 0.9297 - val_loss: 0.3675 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 205/400
7/7 - 0s - loss: 0.2760 - accuracy: 0.9297 - val_loss: 0.3677 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 206/400
7/7 - 0s - loss: 0.2754 - accuracy: 0.9297 - val_loss: 0.3666 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 207/400
7/7 - 0s - loss: 0.2746 - accuracy: 0.9297 - val_loss: 0.3652 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 208/400
7/7 - 0s - loss: 0.2739 - accuracy: 0.9297 - val_loss: 0.3644 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 209/400
7/7 - 0s - loss: 0.2734 - accuracy: 0.9297 - val_loss: 0.3634 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 210/400
7/7 - 0s - loss: 0.2727 - accuracy: 0.9297 - val_loss: 0.3622 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 211/400
7/7 - 0s - loss: 0.2717 - accuracy: 0.9297 - val_loss: 0.3621 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 212/400
7/7 - 0s - loss: 0.2713 - accuracy: 0.9297 - val_loss: 0.3614 - val_accuracy: 0.9062 - 40ms/epoch - 6ms/step
Epoch 213/400
7/7 - 0s - loss: 0.2707 - accuracy: 0.9297 - val_loss: 0.3607 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 214/400
7/7 - 0s - loss: 0.2699 - accuracy: 0.9297 - val_loss: 0.3600 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 215/400
7/7 - 0s - loss: 0.2691 - accuracy: 0.9297 - val_loss: 0.3598 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 216/400
7/7 - 0s - loss: 0.2686 - accuracy: 0.9297 - val_loss: 0.3597 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 217/400
7/7 - 0s - loss: 0.2680 - accuracy: 0.9297 - val_loss: 0.3585 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 218/400
7/7 - 0s - loss: 0.2675 - accuracy: 0.9297 - val_loss: 0.3585 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 219/400
7/7 - 0s - loss: 0.2668 - accuracy: 0.9297 - val_loss: 0.3579 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 220/400
7/7 - 0s - loss: 0.2662 - accuracy: 0.9297 - val_loss: 0.3570 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 221/400
7/7 - 0s - loss: 0.2656 - accuracy: 0.9219 - val_loss: 0.3565 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 222/400
7/7 - 0s - loss: 0.2651 - accuracy: 0.9297 - val_loss: 0.3563 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 223/400
7/7 - 0s - loss: 0.2644 - accuracy: 0.9297 - val_loss: 0.3560 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 224/400
7/7 - 0s - loss: 0.2640 - accuracy: 0.9219 - val_loss: 0.3554 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 225/400
7/7 - 0s - loss: 0.2633 - accuracy: 0.9219 - val_loss: 0.3549 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 226/400
7/7 - 0s - loss: 0.2623 - accuracy: 0.9219 - val_loss: 0.3536 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 227/400
7/7 - 0s - loss: 0.2620 - accuracy: 0.9219 - val_loss: 0.3532 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 228/400
7/7 - 0s - loss: 0.2612 - accuracy: 0.9219 - val_loss: 0.3529 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 229/400
7/7 - 0s - loss: 0.2605 - accuracy: 0.9219 - val_loss: 0.3517 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 230/400
7/7 - 0s - loss: 0.2602 - accuracy: 0.9219 - val_loss: 0.3508 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 231/400
7/7 - 0s - loss: 0.2595 - accuracy: 0.9297 - val_loss: 0.3500 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 232/400
7/7 - 0s - loss: 0.2588 - accuracy: 0.9297 - val_loss: 0.3500 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 233/400
7/7 - 0s - loss: 0.2582 - accuracy: 0.9219 - val_loss: 0.3494 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 234/400
7/7 - 0s - loss: 0.2577 - accuracy: 0.9219 - val_loss: 0.3487 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 235/400
7/7 - 0s - loss: 0.2568 - accuracy: 0.9219 - val_loss: 0.3481 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 236/400
7/7 - 0s - loss: 0.2562 - accuracy: 0.9219 - val_loss: 0.3475 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 237/400
7/7 - 0s - loss: 0.2559 - accuracy: 0.9219 - val_loss: 0.3472 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 238/400
7/7 - 0s - loss: 0.2552 - accuracy: 0.9219 - val_loss: 0.3459 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 239/400
7/7 - 0s - loss: 0.2547 - accuracy: 0.9219 - val_loss: 0.3450 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 240/400
7/7 - 0s - loss: 0.2542 - accuracy: 0.9219 - val_loss: 0.3451 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 241/400
7/7 - 0s - loss: 0.2539 - accuracy: 0.9219 - val_loss: 0.3449 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 242/400
7/7 - 0s - loss: 0.2531 - accuracy: 0.9219 - val_loss: 0.3444 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 243/400
7/7 - 0s - loss: 0.2523 - accuracy: 0.9219 - val_loss: 0.3447 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 244/400
7/7 - 0s - loss: 0.2520 - accuracy: 0.9219 - val_loss: 0.3437 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 245/400
7/7 - 0s - loss: 0.2517 - accuracy: 0.9219 - val_loss: 0.3432 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 246/400
7/7 - 0s - loss: 0.2507 - accuracy: 0.9219 - val_loss: 0.3425 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 247/400
7/7 - 0s - loss: 0.2505 - accuracy: 0.9219 - val_loss: 0.3423 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 248/400
7/7 - 0s - loss: 0.2499 - accuracy: 0.9219 - val_loss: 0.3419 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 249/400
7/7 - 0s - loss: 0.2491 - accuracy: 0.9219 - val_loss: 0.3413 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 250/400
7/7 - 0s - loss: 0.2487 - accuracy: 0.9219 - val_loss: 0.3414 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 251/400
7/7 - 0s - loss: 0.2482 - accuracy: 0.9219 - val_loss: 0.3408 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 252/400
7/7 - 0s - loss: 0.2476 - accuracy: 0.9219 - val_loss: 0.3400 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 253/400
7/7 - 0s - loss: 0.2471 - accuracy: 0.9219 - val_loss: 0.3392 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 254/400
7/7 - 0s - loss: 0.2466 - accuracy: 0.9219 - val_loss: 0.3386 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 255/400
7/7 - 0s - loss: 0.2463 - accuracy: 0.9219 - val_loss: 0.3385 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 256/400
7/7 - 0s - loss: 0.2459 - accuracy: 0.9219 - val_loss: 0.3383 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 257/400
7/7 - 0s - loss: 0.2451 - accuracy: 0.9219 - val_loss: 0.3370 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 258/400
7/7 - 0s - loss: 0.2445 - accuracy: 0.9219 - val_loss: 0.3362 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 259/400
7/7 - 0s - loss: 0.2443 - accuracy: 0.9219 - val_loss: 0.3359 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 260/400
7/7 - 0s - loss: 0.2439 - accuracy: 0.9219 - val_loss: 0.3357 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 261/400
7/7 - 0s - loss: 0.2432 - accuracy: 0.9219 - val_loss: 0.3350 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 262/400
7/7 - 0s - loss: 0.2428 - accuracy: 0.9219 - val_loss: 0.3348 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 263/400
7/7 - 0s - loss: 0.2422 - accuracy: 0.9219 - val_loss: 0.3354 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 264/400
7/7 - 0s - loss: 0.2419 - accuracy: 0.9219 - val_loss: 0.3352 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 265/400
7/7 - 0s - loss: 0.2413 - accuracy: 0.9219 - val_loss: 0.3343 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 266/400
7/7 - 0s - loss: 0.2408 - accuracy: 0.9219 - val_loss: 0.3345 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 267/400
7/7 - 0s - loss: 0.2403 - accuracy: 0.9219 - val_loss: 0.3336 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 268/400
7/7 - 0s - loss: 0.2400 - accuracy: 0.9219 - val_loss: 0.3337 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 269/400
7/7 - 0s - loss: 0.2395 - accuracy: 0.9219 - val_loss: 0.3335 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 270/400
7/7 - 0s - loss: 0.2391 - accuracy: 0.9219 - val_loss: 0.3325 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 271/400
7/7 - 0s - loss: 0.2384 - accuracy: 0.9219 - val_loss: 0.3320 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 272/400
7/7 - 0s - loss: 0.2383 - accuracy: 0.9219 - val_loss: 0.3314 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 273/400
7/7 - 0s - loss: 0.2375 - accuracy: 0.9219 - val_loss: 0.3306 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 274/400
7/7 - 0s - loss: 0.2372 - accuracy: 0.9219 - val_loss: 0.3302 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 275/400
7/7 - 0s - loss: 0.2368 - accuracy: 0.9219 - val_loss: 0.3297 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 276/400
7/7 - 0s - loss: 0.2362 - accuracy: 0.9219 - val_loss: 0.3286 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 277/400
7/7 - 0s - loss: 0.2356 - accuracy: 0.9219 - val_loss: 0.3282 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 278/400
7/7 - 0s - loss: 0.2353 - accuracy: 0.9219 - val_loss: 0.3279 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 279/400
7/7 - 0s - loss: 0.2346 - accuracy: 0.9219 - val_loss: 0.3280 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 280/400
7/7 - 0s - loss: 0.2342 - accuracy: 0.9219 - val_loss: 0.3275 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 281/400
7/7 - 0s - loss: 0.2337 - accuracy: 0.9219 - val_loss: 0.3262 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 282/400
7/7 - 0s - loss: 0.2332 - accuracy: 0.9219 - val_loss: 0.3257 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 283/400
7/7 - 0s - loss: 0.2327 - accuracy: 0.9219 - val_loss: 0.3250 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 284/400
7/7 - 0s - loss: 0.2325 - accuracy: 0.9219 - val_loss: 0.3254 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 285/400
7/7 - 0s - loss: 0.2319 - accuracy: 0.9219 - val_loss: 0.3248 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 286/400
7/7 - 0s - loss: 0.2315 - accuracy: 0.9219 - val_loss: 0.3249 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 287/400
7/7 - 0s - loss: 0.2312 - accuracy: 0.9297 - val_loss: 0.3239 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 288/400
7/7 - 0s - loss: 0.2305 - accuracy: 0.9297 - val_loss: 0.3235 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 289/400
7/7 - 0s - loss: 0.2302 - accuracy: 0.9297 - val_loss: 0.3236 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 290/400
7/7 - 0s - loss: 0.2300 - accuracy: 0.9297 - val_loss: 0.3234 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 291/400
7/7 - 0s - loss: 0.2293 - accuracy: 0.9297 - val_loss: 0.3226 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 292/400
7/7 - 0s - loss: 0.2290 - accuracy: 0.9297 - val_loss: 0.3225 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 293/400
7/7 - 0s - loss: 0.2286 - accuracy: 0.9297 - val_loss: 0.3221 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 294/400
7/7 - 0s - loss: 0.2281 - accuracy: 0.9297 - val_loss: 0.3222 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 295/400
7/7 - 0s - loss: 0.2279 - accuracy: 0.9297 - val_loss: 0.3216 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 296/400
7/7 - 0s - loss: 0.2273 - accuracy: 0.9297 - val_loss: 0.3212 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 297/400
7/7 - 0s - loss: 0.2270 - accuracy: 0.9297 - val_loss: 0.3211 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 298/400
7/7 - 0s - loss: 0.2270 - accuracy: 0.9297 - val_loss: 0.3205 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 299/400
7/7 - 0s - loss: 0.2262 - accuracy: 0.9297 - val_loss: 0.3209 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 300/400
7/7 - 0s - loss: 0.2258 - accuracy: 0.9297 - val_loss: 0.3208 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 301/400
7/7 - 0s - loss: 0.2257 - accuracy: 0.9297 - val_loss: 0.3199 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 302/400
7/7 - 0s - loss: 0.2252 - accuracy: 0.9297 - val_loss: 0.3193 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 303/400
7/7 - 0s - loss: 0.2250 - accuracy: 0.9297 - val_loss: 0.3184 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 304/400
7/7 - 0s - loss: 0.2246 - accuracy: 0.9297 - val_loss: 0.3177 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 305/400
7/7 - 0s - loss: 0.2241 - accuracy: 0.9297 - val_loss: 0.3171 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 306/400
7/7 - 0s - loss: 0.2240 - accuracy: 0.9297 - val_loss: 0.3168 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 307/400
7/7 - 0s - loss: 0.2232 - accuracy: 0.9297 - val_loss: 0.3163 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 308/400
7/7 - 0s - loss: 0.2230 - accuracy: 0.9297 - val_loss: 0.3158 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 309/400
7/7 - 0s - loss: 0.2226 - accuracy: 0.9297 - val_loss: 0.3147 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 310/400
7/7 - 0s - loss: 0.2221 - accuracy: 0.9297 - val_loss: 0.3149 - val_accuracy: 0.9062 - 31ms/epoch - 4ms/step
Epoch 311/400
7/7 - 0s - loss: 0.2218 - accuracy: 0.9297 - val_loss: 0.3151 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 312/400
7/7 - 0s - loss: 0.2217 - accuracy: 0.9297 - val_loss: 0.3152 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 313/400
7/7 - 0s - loss: 0.2210 - accuracy: 0.9297 - val_loss: 0.3149 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 314/400
7/7 - 0s - loss: 0.2207 - accuracy: 0.9297 - val_loss: 0.3145 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 315/400
7/7 - 0s - loss: 0.2205 - accuracy: 0.9297 - val_loss: 0.3142 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 316/400
7/7 - 0s - loss: 0.2199 - accuracy: 0.9297 - val_loss: 0.3137 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 317/400
7/7 - 0s - loss: 0.2196 - accuracy: 0.9297 - val_loss: 0.3129 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 318/400
7/7 - 0s - loss: 0.2192 - accuracy: 0.9297 - val_loss: 0.3125 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 319/400
7/7 - 0s - loss: 0.2186 - accuracy: 0.9297 - val_loss: 0.3127 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 320/400
7/7 - 0s - loss: 0.2183 - accuracy: 0.9297 - val_loss: 0.3119 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 321/400
7/7 - 0s - loss: 0.2180 - accuracy: 0.9297 - val_loss: 0.3121 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 322/400
7/7 - 0s - loss: 0.2174 - accuracy: 0.9297 - val_loss: 0.3115 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 323/400
7/7 - 0s - loss: 0.2172 - accuracy: 0.9297 - val_loss: 0.3106 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 324/400
7/7 - 0s - loss: 0.2172 - accuracy: 0.9297 - val_loss: 0.3105 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 325/400
7/7 - 0s - loss: 0.2165 - accuracy: 0.9297 - val_loss: 0.3100 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 326/400
7/7 - 0s - loss: 0.2160 - accuracy: 0.9297 - val_loss: 0.3099 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 327/400
7/7 - 0s - loss: 0.2160 - accuracy: 0.9297 - val_loss: 0.3100 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 328/400
7/7 - 0s - loss: 0.2154 - accuracy: 0.9297 - val_loss: 0.3091 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 329/400
7/7 - 0s - loss: 0.2150 - accuracy: 0.9297 - val_loss: 0.3090 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 330/400
7/7 - 0s - loss: 0.2147 - accuracy: 0.9297 - val_loss: 0.3081 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 331/400
7/7 - 0s - loss: 0.2144 - accuracy: 0.9297 - val_loss: 0.3078 - val_accuracy: 0.9062 - 38ms/epoch - 5ms/step
Epoch 332/400
7/7 - 0s - loss: 0.2141 - accuracy: 0.9297 - val_loss: 0.3067 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 333/400
7/7 - 0s - loss: 0.2137 - accuracy: 0.9297 - val_loss: 0.3065 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 334/400
7/7 - 0s - loss: 0.2132 - accuracy: 0.9297 - val_loss: 0.3072 - val_accuracy: 0.9062 - 41ms/epoch - 6ms/step
Epoch 335/400
7/7 - 0s - loss: 0.2129 - accuracy: 0.9297 - val_loss: 0.3070 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 336/400
7/7 - 0s - loss: 0.2124 - accuracy: 0.9297 - val_loss: 0.3061 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 337/400
7/7 - 0s - loss: 0.2124 - accuracy: 0.9297 - val_loss: 0.3058 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 338/400
7/7 - 0s - loss: 0.2118 - accuracy: 0.9297 - val_loss: 0.3050 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 339/400
7/7 - 0s - loss: 0.2116 - accuracy: 0.9297 - val_loss: 0.3055 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 340/400
7/7 - 0s - loss: 0.2110 - accuracy: 0.9297 - val_loss: 0.3052 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 341/400
7/7 - 0s - loss: 0.2109 - accuracy: 0.9297 - val_loss: 0.3049 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 342/400
7/7 - 0s - loss: 0.2103 - accuracy: 0.9297 - val_loss: 0.3041 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 343/400
7/7 - 0s - loss: 0.2100 - accuracy: 0.9297 - val_loss: 0.3032 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 344/400
7/7 - 0s - loss: 0.2096 - accuracy: 0.9297 - val_loss: 0.3033 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 345/400
7/7 - 0s - loss: 0.2092 - accuracy: 0.9297 - val_loss: 0.3033 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 346/400
7/7 - 0s - loss: 0.2092 - accuracy: 0.9297 - val_loss: 0.3033 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 347/400
7/7 - 0s - loss: 0.2086 - accuracy: 0.9297 - val_loss: 0.3027 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 348/400
7/7 - 0s - loss: 0.2082 - accuracy: 0.9297 - val_loss: 0.3030 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 349/400
7/7 - 0s - loss: 0.2076 - accuracy: 0.9297 - val_loss: 0.3024 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 350/400
7/7 - 0s - loss: 0.2075 - accuracy: 0.9297 - val_loss: 0.3023 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 351/400
7/7 - 0s - loss: 0.2071 - accuracy: 0.9297 - val_loss: 0.3027 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 352/400
7/7 - 0s - loss: 0.2066 - accuracy: 0.9297 - val_loss: 0.3021 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 353/400
7/7 - 0s - loss: 0.2063 - accuracy: 0.9297 - val_loss: 0.3018 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 354/400
7/7 - 0s - loss: 0.2061 - accuracy: 0.9297 - val_loss: 0.3019 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 355/400
7/7 - 0s - loss: 0.2056 - accuracy: 0.9297 - val_loss: 0.3010 - val_accuracy: 0.9062 - 38ms/epoch - 5ms/step
Epoch 356/400
7/7 - 0s - loss: 0.2056 - accuracy: 0.9297 - val_loss: 0.3012 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 357/400
7/7 - 0s - loss: 0.2053 - accuracy: 0.9297 - val_loss: 0.3007 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 358/400
7/7 - 0s - loss: 0.2049 - accuracy: 0.9297 - val_loss: 0.3001 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 359/400
7/7 - 0s - loss: 0.2046 - accuracy: 0.9297 - val_loss: 0.2990 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 360/400
7/7 - 0s - loss: 0.2043 - accuracy: 0.9297 - val_loss: 0.2995 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 361/400
7/7 - 0s - loss: 0.2041 - accuracy: 0.9297 - val_loss: 0.2989 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 362/400
7/7 - 0s - loss: 0.2038 - accuracy: 0.9297 - val_loss: 0.2995 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 363/400
7/7 - 0s - loss: 0.2033 - accuracy: 0.9375 - val_loss: 0.2996 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 364/400
7/7 - 0s - loss: 0.2031 - accuracy: 0.9297 - val_loss: 0.2985 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 365/400
7/7 - 0s - loss: 0.2028 - accuracy: 0.9297 - val_loss: 0.2973 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 366/400
7/7 - 0s - loss: 0.2025 - accuracy: 0.9297 - val_loss: 0.2974 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 367/400
7/7 - 0s - loss: 0.2022 - accuracy: 0.9297 - val_loss: 0.2969 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 368/400
7/7 - 0s - loss: 0.2020 - accuracy: 0.9297 - val_loss: 0.2963 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 369/400
7/7 - 0s - loss: 0.2016 - accuracy: 0.9297 - val_loss: 0.2963 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 370/400
7/7 - 0s - loss: 0.2014 - accuracy: 0.9297 - val_loss: 0.2957 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 371/400
7/7 - 0s - loss: 0.2010 - accuracy: 0.9297 - val_loss: 0.2955 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 372/400
7/7 - 0s - loss: 0.2006 - accuracy: 0.9297 - val_loss: 0.2947 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 373/400
7/7 - 0s - loss: 0.2001 - accuracy: 0.9297 - val_loss: 0.2948 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 374/400
7/7 - 0s - loss: 0.2001 - accuracy: 0.9297 - val_loss: 0.2944 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 375/400
7/7 - 0s - loss: 0.1998 - accuracy: 0.9297 - val_loss: 0.2936 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 376/400
7/7 - 0s - loss: 0.1993 - accuracy: 0.9297 - val_loss: 0.2936 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 377/400
7/7 - 0s - loss: 0.1990 - accuracy: 0.9297 - val_loss: 0.2937 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 378/400
7/7 - 0s - loss: 0.1989 - accuracy: 0.9453 - val_loss: 0.2936 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 379/400
7/7 - 0s - loss: 0.1986 - accuracy: 0.9453 - val_loss: 0.2928 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 380/400
7/7 - 0s - loss: 0.1982 - accuracy: 0.9297 - val_loss: 0.2932 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 381/400
7/7 - 0s - loss: 0.1979 - accuracy: 0.9297 - val_loss: 0.2930 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 382/400
7/7 - 0s - loss: 0.1977 - accuracy: 0.9375 - val_loss: 0.2929 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 383/400
7/7 - 0s - loss: 0.1974 - accuracy: 0.9375 - val_loss: 0.2925 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 384/400
7/7 - 0s - loss: 0.1968 - accuracy: 0.9297 - val_loss: 0.2931 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 385/400
7/7 - 0s - loss: 0.1966 - accuracy: 0.9453 - val_loss: 0.2922 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 386/400
7/7 - 0s - loss: 0.1962 - accuracy: 0.9375 - val_loss: 0.2916 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 387/400
7/7 - 0s - loss: 0.1962 - accuracy: 0.9375 - val_loss: 0.2903 - val_accuracy: 0.9062 - 32ms/epoch - 5ms/step
Epoch 388/400
7/7 - 0s - loss: 0.1958 - accuracy: 0.9297 - val_loss: 0.2901 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 389/400
7/7 - 0s - loss: 0.1956 - accuracy: 0.9375 - val_loss: 0.2891 - val_accuracy: 0.9062 - 35ms/epoch - 5ms/step
Epoch 390/400
7/7 - 0s - loss: 0.1953 - accuracy: 0.9297 - val_loss: 0.2886 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 391/400
7/7 - 0s - loss: 0.1951 - accuracy: 0.9375 - val_loss: 0.2888 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 392/400
7/7 - 0s - loss: 0.1945 - accuracy: 0.9375 - val_loss: 0.2885 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 393/400
7/7 - 0s - loss: 0.1946 - accuracy: 0.9375 - val_loss: 0.2875 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 394/400
7/7 - 0s - loss: 0.1944 - accuracy: 0.9375 - val_loss: 0.2876 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 395/400
7/7 - 0s - loss: 0.1939 - accuracy: 0.9375 - val_loss: 0.2868 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 396/400
7/7 - 0s - loss: 0.1935 - accuracy: 0.9297 - val_loss: 0.2869 - val_accuracy: 0.9062 - 36ms/epoch - 5ms/step
Epoch 397/400
7/7 - 0s - loss: 0.1931 - accuracy: 0.9297 - val_loss: 0.2869 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 398/400
7/7 - 0s - loss: 0.1930 - accuracy: 0.9297 - val_loss: 0.2859 - val_accuracy: 0.9062 - 34ms/epoch - 5ms/step
Epoch 399/400
7/7 - 0s - loss: 0.1927 - accuracy: 0.9297 - val_loss: 0.2858 - val_accuracy: 0.9062 - 33ms/epoch - 5ms/step
Epoch 400/400
7/7 - 0s - loss: 0.1924 - accuracy: 0.9297 - val_loss: 0.2859 - val_accuracy: 0.9062 - 32ms/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: 0.2105 - accuracy: 0.9250 - 20ms/epoch - 4ms/step

print(perf)

     loss  accuracy 
0.2104692 0.9250000

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

2/2 - 0s - loss: 0.0947 - accuracy: 1.0000 - 16ms/epoch - 8ms/step

print(perf)

      loss   accuracy 
0.09473421 1.00000000