Stat. 654 Quiz keras

Author

Your Name Here

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

Clone the TFPlayground Github repository into your R Project folder.

To clone the repository you can use RStudio

File > New Project > Version Control > Git

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

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

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

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

Load the required libraries

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.2.1     ✔ readr     2.2.0
✔ forcats   1.0.1     ✔ stringr   1.6.0
✔ ggplot2   4.0.2     ✔ tibble    3.3.1
✔ lubridate 1.9.5     ✔ tidyr     1.3.2
✔ purrr     1.2.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(tidymodels)

── Attaching packages ────────────────────────────────────── tidymodels 1.4.1 ──
✔ broom        1.0.12     ✔ rsample      1.3.2 
✔ dials        1.4.2      ✔ tailor       0.1.0 
✔ infer        1.1.0      ✔ tune         2.0.1 
✔ modeldata    1.5.1      ✔ workflows    1.3.0 
✔ parsnip      1.5.0      ✔ workflowsets 1.1.1 
✔ recipes      1.3.2      ✔ yardstick    1.4.0 
── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
✖ scales::discard() masks purrr::discard()
✖ dplyr::filter()   masks stats::filter()
✖ recipes::fixed()  masks stringr::fixed()
✖ dplyr::lag()      masks stats::lag()
✖ yardstick::spec() masks readr::spec()
✖ recipes::step()   masks stats::step()

library(readr)
library(janitor)


Attaching package: 'janitor'

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

    chisq.test, fisher.test

library(forcats)
library(keras3)


Attaching package: 'keras3'

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

    get_weights

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

    generate

Load the data

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

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

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

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

head(input)

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

Split the data into training and testing sets

n <- nrow(input)

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

train <- input_parts |>
  training()

test <- input_parts |>
  testing()

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

[1] 160  40

Visualize the data

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

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

Using keras and tensorflow

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

Do not forget to remove the ID variable pid.

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

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

dim(x_train)

[1] 160   2

dim(x_test)

[1] 40  2

dim(y_train)

[1] 160   2

dim(y_test)

[1] 40  2

Set Architecture

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

keras activation

model <- keras_model_sequential()
model |>  
  layer_dense(units = 8, activation = 'relu', input_shape = 2) |> 
  layer_dense(units = 3, activation = 'relu') |> 
  layer_dense(units = 2, activation = 'softmax')
model |> summary()

Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                      ┃ Output Shape             ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ dense (Dense)                     │ (None, 8)                │            24 │
├───────────────────────────────────┼──────────────────────────┼───────────────┤
│ dense_1 (Dense)                   │ (None, 3)                │            27 │
├───────────────────────────────────┼──────────────────────────┼───────────────┤
│ dense_2 (Dense)                   │ (None, 2)                │             8 │
└───────────────────────────────────┴──────────────────────────┴───────────────┘
 Total params: 59 (236.00 B)
 Trainable params: 59 (236.00 B)
 Non-trainable params: 0 (0.00 B)

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

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

Train the Artificial Neural Network

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

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

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

Epoch 1/400
7/7 - 2s - 344ms/step - accuracy: 0.4609 - loss: 0.6715 - val_accuracy: 0.6875 - val_loss: 0.6351
Epoch 2/400
7/7 - 0s - 9ms/step - accuracy: 0.5625 - loss: 0.6670 - val_accuracy: 0.6875 - val_loss: 0.6311
Epoch 3/400
7/7 - 0s - 8ms/step - accuracy: 0.5703 - loss: 0.6640 - val_accuracy: 0.6875 - val_loss: 0.6285
Epoch 4/400
7/7 - 0s - 8ms/step - accuracy: 0.5859 - loss: 0.6611 - val_accuracy: 0.7188 - val_loss: 0.6253
Epoch 5/400
7/7 - 0s - 9ms/step - accuracy: 0.6094 - loss: 0.6586 - val_accuracy: 0.7188 - val_loss: 0.6226
Epoch 6/400
7/7 - 0s - 8ms/step - accuracy: 0.6250 - loss: 0.6563 - val_accuracy: 0.7188 - val_loss: 0.6188
Epoch 7/400
7/7 - 0s - 8ms/step - accuracy: 0.6406 - loss: 0.6540 - val_accuracy: 0.7188 - val_loss: 0.6148
Epoch 8/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6517 - val_accuracy: 0.7500 - val_loss: 0.6110
Epoch 9/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6491 - val_accuracy: 0.7500 - val_loss: 0.6065
Epoch 10/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6464 - val_accuracy: 0.7500 - val_loss: 0.6010
Epoch 11/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6437 - val_accuracy: 0.7500 - val_loss: 0.5965
Epoch 12/400
7/7 - 0s - 9ms/step - accuracy: 0.6562 - loss: 0.6409 - val_accuracy: 0.7500 - val_loss: 0.5909
Epoch 13/400
7/7 - 0s - 9ms/step - accuracy: 0.6484 - loss: 0.6383 - val_accuracy: 0.7500 - val_loss: 0.5860
Epoch 14/400
7/7 - 0s - 9ms/step - accuracy: 0.6562 - loss: 0.6356 - val_accuracy: 0.7500 - val_loss: 0.5814
Epoch 15/400
7/7 - 0s - 9ms/step - accuracy: 0.6562 - loss: 0.6332 - val_accuracy: 0.7500 - val_loss: 0.5769
Epoch 16/400
7/7 - 0s - 9ms/step - accuracy: 0.6562 - loss: 0.6306 - val_accuracy: 0.7500 - val_loss: 0.5727
Epoch 17/400
7/7 - 0s - 9ms/step - accuracy: 0.6719 - loss: 0.6279 - val_accuracy: 0.7500 - val_loss: 0.5675
Epoch 18/400
7/7 - 0s - 9ms/step - accuracy: 0.6719 - loss: 0.6252 - val_accuracy: 0.7500 - val_loss: 0.5627
Epoch 19/400
7/7 - 0s - 9ms/step - accuracy: 0.6719 - loss: 0.6227 - val_accuracy: 0.7500 - val_loss: 0.5590
Epoch 20/400
7/7 - 0s - 8ms/step - accuracy: 0.6797 - loss: 0.6203 - val_accuracy: 0.7500 - val_loss: 0.5545
Epoch 21/400
7/7 - 0s - 9ms/step - accuracy: 0.6797 - loss: 0.6180 - val_accuracy: 0.7500 - val_loss: 0.5499
Epoch 22/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.6158 - val_accuracy: 0.7500 - val_loss: 0.5466
Epoch 23/400
7/7 - 0s - 9ms/step - accuracy: 0.6797 - loss: 0.6137 - val_accuracy: 0.7500 - val_loss: 0.5433
Epoch 24/400
7/7 - 0s - 8ms/step - accuracy: 0.6953 - loss: 0.6118 - val_accuracy: 0.7500 - val_loss: 0.5402
Epoch 25/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.6098 - val_accuracy: 0.7500 - val_loss: 0.5354
Epoch 26/400
7/7 - 0s - 9ms/step - accuracy: 0.6875 - loss: 0.6078 - val_accuracy: 0.7500 - val_loss: 0.5330
Epoch 27/400
7/7 - 0s - 8ms/step - accuracy: 0.6953 - loss: 0.6058 - val_accuracy: 0.7500 - val_loss: 0.5289
Epoch 28/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.6039 - val_accuracy: 0.7500 - val_loss: 0.5253
Epoch 29/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.6022 - val_accuracy: 0.7500 - val_loss: 0.5230
Epoch 30/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.6003 - val_accuracy: 0.7500 - val_loss: 0.5193
Epoch 31/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.5986 - val_accuracy: 0.7500 - val_loss: 0.5158
Epoch 32/400
7/7 - 0s - 8ms/step - accuracy: 0.6953 - loss: 0.5971 - val_accuracy: 0.7500 - val_loss: 0.5137
Epoch 33/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.5952 - val_accuracy: 0.7500 - val_loss: 0.5116
Epoch 34/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.5938 - val_accuracy: 0.7500 - val_loss: 0.5090
Epoch 35/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.5924 - val_accuracy: 0.7500 - val_loss: 0.5061
Epoch 36/400
7/7 - 0s - 8ms/step - accuracy: 0.6953 - loss: 0.5909 - val_accuracy: 0.7500 - val_loss: 0.5030
Epoch 37/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.5895 - val_accuracy: 0.7500 - val_loss: 0.5007
Epoch 38/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.5880 - val_accuracy: 0.7500 - val_loss: 0.4986
Epoch 39/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5869 - val_accuracy: 0.7500 - val_loss: 0.4973
Epoch 40/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5856 - val_accuracy: 0.7500 - val_loss: 0.4948
Epoch 41/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5844 - val_accuracy: 0.7500 - val_loss: 0.4932
Epoch 42/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5832 - val_accuracy: 0.7500 - val_loss: 0.4910
Epoch 43/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5819 - val_accuracy: 0.7500 - val_loss: 0.4884
Epoch 44/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5807 - val_accuracy: 0.7500 - val_loss: 0.4858
Epoch 45/400
7/7 - 0s - 8ms/step - accuracy: 0.6953 - loss: 0.5794 - val_accuracy: 0.7500 - val_loss: 0.4844
Epoch 46/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5784 - val_accuracy: 0.7500 - val_loss: 0.4821
Epoch 47/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5774 - val_accuracy: 0.7500 - val_loss: 0.4808
Epoch 48/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5764 - val_accuracy: 0.7500 - val_loss: 0.4786
Epoch 49/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5756 - val_accuracy: 0.7500 - val_loss: 0.4776
Epoch 50/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5746 - val_accuracy: 0.7500 - val_loss: 0.4764
Epoch 51/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5736 - val_accuracy: 0.7500 - val_loss: 0.4757
Epoch 52/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5729 - val_accuracy: 0.7500 - val_loss: 0.4745
Epoch 53/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5723 - val_accuracy: 0.7500 - val_loss: 0.4725
Epoch 54/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5711 - val_accuracy: 0.7500 - val_loss: 0.4725
Epoch 55/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5704 - val_accuracy: 0.7500 - val_loss: 0.4708
Epoch 56/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5696 - val_accuracy: 0.7500 - val_loss: 0.4697
Epoch 57/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5687 - val_accuracy: 0.7500 - val_loss: 0.4685
Epoch 58/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5681 - val_accuracy: 0.7500 - val_loss: 0.4675
Epoch 59/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5674 - val_accuracy: 0.7500 - val_loss: 0.4665
Epoch 60/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5668 - val_accuracy: 0.7500 - val_loss: 0.4651
Epoch 61/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5658 - val_accuracy: 0.7500 - val_loss: 0.4641
Epoch 62/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5655 - val_accuracy: 0.7500 - val_loss: 0.4633
Epoch 63/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5646 - val_accuracy: 0.7500 - val_loss: 0.4625
Epoch 64/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5641 - val_accuracy: 0.7500 - val_loss: 0.4612
Epoch 65/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5633 - val_accuracy: 0.7500 - val_loss: 0.4606
Epoch 66/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5629 - val_accuracy: 0.7500 - val_loss: 0.4595
Epoch 67/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5623 - val_accuracy: 0.7500 - val_loss: 0.4596
Epoch 68/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5617 - val_accuracy: 0.7500 - val_loss: 0.4587
Epoch 69/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5610 - val_accuracy: 0.7500 - val_loss: 0.4580
Epoch 70/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5605 - val_accuracy: 0.7500 - val_loss: 0.4574
Epoch 71/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5599 - val_accuracy: 0.7500 - val_loss: 0.4571
Epoch 72/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5594 - val_accuracy: 0.7500 - val_loss: 0.4564
Epoch 73/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5588 - val_accuracy: 0.7500 - val_loss: 0.4561
Epoch 74/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5582 - val_accuracy: 0.7500 - val_loss: 0.4555
Epoch 75/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5577 - val_accuracy: 0.7500 - val_loss: 0.4544
Epoch 76/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5571 - val_accuracy: 0.7500 - val_loss: 0.4540
Epoch 77/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5566 - val_accuracy: 0.7500 - val_loss: 0.4537
Epoch 78/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5561 - val_accuracy: 0.7500 - val_loss: 0.4527
Epoch 79/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5555 - val_accuracy: 0.7500 - val_loss: 0.4524
Epoch 80/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5552 - val_accuracy: 0.7500 - val_loss: 0.4513
Epoch 81/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5548 - val_accuracy: 0.7500 - val_loss: 0.4517
Epoch 82/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5543 - val_accuracy: 0.7500 - val_loss: 0.4511
Epoch 83/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5539 - val_accuracy: 0.7500 - val_loss: 0.4510
Epoch 84/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5536 - val_accuracy: 0.7500 - val_loss: 0.4503
Epoch 85/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5532 - val_accuracy: 0.7500 - val_loss: 0.4501
Epoch 86/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5530 - val_accuracy: 0.7500 - val_loss: 0.4497
Epoch 87/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5524 - val_accuracy: 0.7500 - val_loss: 0.4493
Epoch 88/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5520 - val_accuracy: 0.7500 - val_loss: 0.4483
Epoch 89/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5516 - val_accuracy: 0.7500 - val_loss: 0.4479
Epoch 90/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5514 - val_accuracy: 0.7500 - val_loss: 0.4477
Epoch 91/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5514 - val_accuracy: 0.7500 - val_loss: 0.4468
Epoch 92/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5508 - val_accuracy: 0.7500 - val_loss: 0.4471
Epoch 93/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5503 - val_accuracy: 0.7500 - val_loss: 0.4467
Epoch 94/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5501 - val_accuracy: 0.7500 - val_loss: 0.4462
Epoch 95/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5499 - val_accuracy: 0.7500 - val_loss: 0.4459
Epoch 96/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5497 - val_accuracy: 0.7500 - val_loss: 0.4458
Epoch 97/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5494 - val_accuracy: 0.7500 - val_loss: 0.4450
Epoch 98/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5492 - val_accuracy: 0.7500 - val_loss: 0.4448
Epoch 99/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5488 - val_accuracy: 0.7500 - val_loss: 0.4446
Epoch 100/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5487 - val_accuracy: 0.7500 - val_loss: 0.4447
Epoch 101/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5483 - val_accuracy: 0.7500 - val_loss: 0.4445
Epoch 102/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5479 - val_accuracy: 0.7500 - val_loss: 0.4442
Epoch 103/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5479 - val_accuracy: 0.7500 - val_loss: 0.4441
Epoch 104/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5474 - val_accuracy: 0.7500 - val_loss: 0.4443
Epoch 105/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5471 - val_accuracy: 0.7500 - val_loss: 0.4443
Epoch 106/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5468 - val_accuracy: 0.7500 - val_loss: 0.4440
Epoch 107/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5469 - val_accuracy: 0.7500 - val_loss: 0.4434
Epoch 108/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5465 - val_accuracy: 0.7500 - val_loss: 0.4433
Epoch 109/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5463 - val_accuracy: 0.7500 - val_loss: 0.4433
Epoch 110/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5461 - val_accuracy: 0.7500 - val_loss: 0.4435
Epoch 111/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5459 - val_accuracy: 0.7500 - val_loss: 0.4430
Epoch 112/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5458 - val_accuracy: 0.7500 - val_loss: 0.4430
Epoch 113/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5457 - val_accuracy: 0.7500 - val_loss: 0.4428
Epoch 114/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5453 - val_accuracy: 0.7500 - val_loss: 0.4424
Epoch 115/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5451 - val_accuracy: 0.7500 - val_loss: 0.4422
Epoch 116/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5450 - val_accuracy: 0.7500 - val_loss: 0.4428
Epoch 117/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5448 - val_accuracy: 0.7500 - val_loss: 0.4431
Epoch 118/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5444 - val_accuracy: 0.7500 - val_loss: 0.4429
Epoch 119/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5442 - val_accuracy: 0.7500 - val_loss: 0.4428
Epoch 120/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5444 - val_accuracy: 0.7500 - val_loss: 0.4425
Epoch 121/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5438 - val_accuracy: 0.7500 - val_loss: 0.4421
Epoch 122/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5439 - val_accuracy: 0.7500 - val_loss: 0.4425
Epoch 123/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5436 - val_accuracy: 0.7500 - val_loss: 0.4422
Epoch 124/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5435 - val_accuracy: 0.7500 - val_loss: 0.4417
Epoch 125/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5433 - val_accuracy: 0.7500 - val_loss: 0.4414
Epoch 126/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5432 - val_accuracy: 0.7500 - val_loss: 0.4416
Epoch 127/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5430 - val_accuracy: 0.7500 - val_loss: 0.4414
Epoch 128/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5428 - val_accuracy: 0.7500 - val_loss: 0.4413
Epoch 129/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5428 - val_accuracy: 0.7500 - val_loss: 0.4415
Epoch 130/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5426 - val_accuracy: 0.7500 - val_loss: 0.4417
Epoch 131/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5423 - val_accuracy: 0.7500 - val_loss: 0.4415
Epoch 132/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5421 - val_accuracy: 0.7500 - val_loss: 0.4410
Epoch 133/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5424 - val_accuracy: 0.7500 - val_loss: 0.4415
Epoch 134/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5417 - val_accuracy: 0.7500 - val_loss: 0.4414
Epoch 135/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5417 - val_accuracy: 0.7500 - val_loss: 0.4419
Epoch 136/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5415 - val_accuracy: 0.7500 - val_loss: 0.4412
Epoch 137/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5414 - val_accuracy: 0.7500 - val_loss: 0.4406
Epoch 138/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5416 - val_accuracy: 0.7500 - val_loss: 0.4408
Epoch 139/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5413 - val_accuracy: 0.7500 - val_loss: 0.4406
Epoch 140/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5411 - val_accuracy: 0.7500 - val_loss: 0.4408
Epoch 141/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5410 - val_accuracy: 0.7500 - val_loss: 0.4406
Epoch 142/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5408 - val_accuracy: 0.7500 - val_loss: 0.4406
Epoch 143/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5407 - val_accuracy: 0.7500 - val_loss: 0.4404
Epoch 144/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5406 - val_accuracy: 0.7500 - val_loss: 0.4408
Epoch 145/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5405 - val_accuracy: 0.7500 - val_loss: 0.4405
Epoch 146/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5404 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 147/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5404 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 148/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5401 - val_accuracy: 0.7500 - val_loss: 0.4401
Epoch 149/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5401 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 150/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5398 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 151/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5398 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 152/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5396 - val_accuracy: 0.7500 - val_loss: 0.4401
Epoch 153/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5396 - val_accuracy: 0.7500 - val_loss: 0.4400
Epoch 154/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5393 - val_accuracy: 0.7500 - val_loss: 0.4401
Epoch 155/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5391 - val_accuracy: 0.7500 - val_loss: 0.4402
Epoch 156/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5390 - val_accuracy: 0.7500 - val_loss: 0.4401
Epoch 157/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5392 - val_accuracy: 0.7500 - val_loss: 0.4402
Epoch 158/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5390 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 159/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5387 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 160/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5386 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 161/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5385 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 162/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5386 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 163/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5383 - val_accuracy: 0.7500 - val_loss: 0.4402
Epoch 164/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5381 - val_accuracy: 0.7500 - val_loss: 0.4402
Epoch 165/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5381 - val_accuracy: 0.7500 - val_loss: 0.4404
Epoch 166/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5378 - val_accuracy: 0.7500 - val_loss: 0.4405
Epoch 167/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5379 - val_accuracy: 0.7500 - val_loss: 0.4400
Epoch 168/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5378 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 169/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5377 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 170/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5376 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 171/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5375 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 172/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5377 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 173/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5374 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 174/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5373 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 175/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5373 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 176/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5372 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 177/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5369 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 178/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5370 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 179/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5368 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 180/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5370 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 181/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5365 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 182/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5370 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 183/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5364 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 184/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5365 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 185/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5363 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 186/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5364 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 187/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5365 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 188/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5360 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 189/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5360 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 190/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5359 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 191/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5358 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 192/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5358 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 193/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5358 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 194/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5356 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 195/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5357 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 196/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5355 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 197/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5356 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 198/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5356 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 199/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5355 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 200/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5353 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 201/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5352 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 202/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5350 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 203/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5350 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 204/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5349 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 205/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5353 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 206/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5349 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 207/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5350 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 208/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5347 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 209/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5348 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 210/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5349 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 211/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5347 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 212/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5346 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 213/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5344 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 214/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5345 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 215/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5345 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 216/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5342 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 217/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5343 - val_accuracy: 0.7500 - val_loss: 0.4385
Epoch 218/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5342 - val_accuracy: 0.7500 - val_loss: 0.4384
Epoch 219/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5342 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 220/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5340 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 221/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5340 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 222/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5340 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 223/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5339 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 224/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5341 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 225/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5337 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 226/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5338 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 227/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5337 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 228/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5336 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 229/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5335 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 230/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5333 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 231/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5337 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 232/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5334 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 233/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5334 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 234/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5333 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 235/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5331 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 236/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5330 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 237/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5330 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 238/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5329 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 239/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5329 - val_accuracy: 0.7500 - val_loss: 0.4402
Epoch 240/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5330 - val_accuracy: 0.7500 - val_loss: 0.4401
Epoch 241/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5329 - val_accuracy: 0.7500 - val_loss: 0.4400
Epoch 242/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5331 - val_accuracy: 0.7500 - val_loss: 0.4401
Epoch 243/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5328 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 244/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5328 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 245/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5328 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 246/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5326 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 247/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5325 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 248/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5323 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 249/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5326 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 250/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5323 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 251/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5325 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 252/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5320 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 253/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5321 - val_accuracy: 0.7500 - val_loss: 0.4400
Epoch 254/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5320 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 255/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5321 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 256/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5323 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 257/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5320 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 258/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5318 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 259/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5323 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 260/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5318 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 261/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5318 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 262/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5316 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 263/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5318 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 264/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5317 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 265/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5316 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 266/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5314 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 267/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5317 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 268/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5315 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 269/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5313 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 270/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5314 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 271/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5315 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 272/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5312 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 273/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5312 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 274/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5314 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 275/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5312 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 276/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5313 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 277/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5315 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 278/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5308 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 279/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5311 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 280/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5311 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 281/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5310 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 282/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5309 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 283/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5307 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 284/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5308 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 285/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5308 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 286/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5307 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 287/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5306 - val_accuracy: 0.7500 - val_loss: 0.4386
Epoch 288/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5307 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 289/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5306 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 290/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5307 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 291/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5307 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 292/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5303 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 293/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5302 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 294/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5305 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 295/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5304 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 296/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5303 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 297/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5304 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 298/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5302 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 299/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5302 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 300/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5303 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 301/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5301 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 302/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5302 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 303/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5300 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 304/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5301 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 305/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5299 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 306/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5299 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 307/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5297 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 308/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5300 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 309/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5299 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 310/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5297 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 311/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5296 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 312/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5298 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 313/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5296 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 314/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5298 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 315/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5296 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 316/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5295 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 317/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5297 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 318/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5295 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 319/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5295 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 320/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5294 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 321/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5293 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 322/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5292 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 323/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5293 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 324/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5293 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 325/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5292 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 326/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5291 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 327/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5293 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 328/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5296 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 329/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5291 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 330/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5288 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 331/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5293 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 332/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5287 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 333/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5292 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 334/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5289 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 335/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5288 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 336/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5287 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 337/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5288 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 338/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5287 - val_accuracy: 0.7500 - val_loss: 0.4402
Epoch 339/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5285 - val_accuracy: 0.7500 - val_loss: 0.4399
Epoch 340/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5286 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 341/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5285 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 342/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5286 - val_accuracy: 0.7500 - val_loss: 0.4396
Epoch 343/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5286 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 344/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5286 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 345/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5286 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 346/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5283 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 347/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5284 - val_accuracy: 0.7500 - val_loss: 0.4386
Epoch 348/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5283 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 349/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5286 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 350/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5284 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 351/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5281 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 352/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5282 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 353/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5280 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 354/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5285 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 355/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5279 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 356/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5282 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 357/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5278 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 358/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5281 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 359/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5279 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 360/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5280 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 361/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5278 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 362/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5281 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 363/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.5278 - val_accuracy: 0.7500 - val_loss: 0.4389
Epoch 364/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5279 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 365/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5275 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 366/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5277 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 367/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5277 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 368/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5278 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 369/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5278 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 370/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.5276 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 371/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5274 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 372/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5273 - val_accuracy: 0.7500 - val_loss: 0.4390
Epoch 373/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5275 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 374/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5274 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 375/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5273 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 376/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5273 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 377/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5273 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 378/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5273 - val_accuracy: 0.7500 - val_loss: 0.4395
Epoch 379/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5271 - val_accuracy: 0.7500 - val_loss: 0.4391
Epoch 380/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5273 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 381/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5270 - val_accuracy: 0.7500 - val_loss: 0.4385
Epoch 382/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5268 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 383/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5268 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 384/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5270 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 385/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5271 - val_accuracy: 0.7500 - val_loss: 0.4383
Epoch 386/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5270 - val_accuracy: 0.7500 - val_loss: 0.4383
Epoch 387/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5269 - val_accuracy: 0.7500 - val_loss: 0.4386
Epoch 388/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5266 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 389/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5268 - val_accuracy: 0.7500 - val_loss: 0.4385
Epoch 390/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5264 - val_accuracy: 0.7500 - val_loss: 0.4387
Epoch 391/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5266 - val_accuracy: 0.7500 - val_loss: 0.4388
Epoch 392/400
7/7 - 0s - 8ms/step - accuracy: 0.7188 - loss: 0.5265 - val_accuracy: 0.7500 - val_loss: 0.4392
Epoch 393/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5264 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 394/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5263 - val_accuracy: 0.7500 - val_loss: 0.4393
Epoch 395/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5262 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 396/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5263 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 397/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5260 - val_accuracy: 0.7500 - val_loss: 0.4397
Epoch 398/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5260 - val_accuracy: 0.7500 - val_loss: 0.4398
Epoch 399/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5259 - val_accuracy: 0.7500 - val_loss: 0.4394
Epoch 400/400
7/7 - 0s - 9ms/step - accuracy: 0.7188 - loss: 0.5259 - val_accuracy: 0.7500 - val_loss: 0.4392

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 - 79ms/step - accuracy: 0.7250 - loss: 0.5082

print(perf)

$accuracy
[1] 0.725

$loss
[1] 0.508231

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

2/2 - 0s - 169ms/step - accuracy: 0.6250 - loss: 0.6073

print(perf)

$accuracy
[1] 0.625

$loss
[1] 0.6073383

Evaluate Network Performance

The final performance can be obtained like so.

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

5/5 - 0s - 6ms/step - accuracy: 0.7250 - loss: 0.5082

print(perf)

$accuracy
[1] 0.725

$loss
[1] 0.508231

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

2/2 - 0s - 12ms/step - accuracy: 0.6250 - loss: 0.6073

print(perf)

$accuracy
[1] 0.625

$loss
[1] 0.6073383