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
── 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
── 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
<- 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 |> 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
<- nrow (input)<- input |> initial_split (prop = 0.8 )<- input_parts |> training ()<- input_parts |> testing ()list (train, test) |> map_int (nrow)
Visualize the data
|> ggplot (aes (x = x1, y = x2, color = factor (label))) + geom_point ()
|> 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.
<- train |> select (- pid, - label) |> select (x1, x2) |> as.matrix ()<- train |> select (label) |> as.matrix () |> as.numeric () <- test |> select (- pid, - label) |> select (x1, x2) |> as.matrix ()<- test |> select (label) |> as.matrix () |> as.numeric () dim (x_train)
Set Architecture
With the data in place, we now set the architecture of our neural network.
keras activation
<- keras_model_sequential ()|> layer_dense (units = 8 , activation = 'relu' , input_shape = 2 ) |> layer_dense (units = 3 , activation = 'relu' ) |> layer_dense (units = 1 , activation = 'sigmoid' )|> summary ()
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type) ┃ Output Shape ┃ Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ dense (Dense) │ (None, 8) │ 24 │
├───────────────────────────────────┼──────────────────────────┼───────────────┤
│ dense_1 (Dense) │ (None, 3) │ 27 │
├───────────────────────────────────┼──────────────────────────┼───────────────┤
│ dense_2 (Dense) │ (None, 1) │ 4 │
└───────────────────────────────────┴──────────────────────────┴───────────────┘
Total params: 55 (220.00 B)
Trainable params: 55 (220.00 B)
Non-trainable params: 0 (0.00 B)
Next, the architecture set in the model needs to be compiled.
|> 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 .
<- model |> fit (x = x_train, y = y_train,epochs = 400 ,batch_size = 20 ,validation_split = 0.2
Epoch 1/400
7/7 - 2s - 310ms/step - accuracy: 0.5469 - loss: 0.8674 - val_accuracy: 0.6562 - val_loss: 0.7700
Epoch 2/400
7/7 - 0s - 9ms/step - accuracy: 0.5625 - loss: 0.8227 - val_accuracy: 0.6562 - val_loss: 0.7467
Epoch 3/400
7/7 - 0s - 9ms/step - accuracy: 0.5781 - loss: 0.7924 - val_accuracy: 0.6562 - val_loss: 0.7282
Epoch 4/400
7/7 - 0s - 9ms/step - accuracy: 0.6016 - loss: 0.7664 - val_accuracy: 0.6562 - val_loss: 0.7117
Epoch 5/400
7/7 - 0s - 9ms/step - accuracy: 0.6094 - loss: 0.7430 - val_accuracy: 0.6562 - val_loss: 0.6961
Epoch 6/400
7/7 - 0s - 9ms/step - accuracy: 0.6094 - loss: 0.7193 - val_accuracy: 0.6562 - val_loss: 0.6805
Epoch 7/400
7/7 - 0s - 9ms/step - accuracy: 0.6250 - loss: 0.6989 - val_accuracy: 0.6875 - val_loss: 0.6675
Epoch 8/400
7/7 - 0s - 9ms/step - accuracy: 0.6328 - loss: 0.6825 - val_accuracy: 0.6875 - val_loss: 0.6538
Epoch 9/400
7/7 - 0s - 9ms/step - accuracy: 0.6328 - loss: 0.6660 - val_accuracy: 0.6875 - val_loss: 0.6413
Epoch 10/400
7/7 - 0s - 9ms/step - accuracy: 0.6328 - loss: 0.6500 - val_accuracy: 0.6875 - val_loss: 0.6292
Epoch 11/400
7/7 - 0s - 9ms/step - accuracy: 0.6328 - loss: 0.6363 - val_accuracy: 0.6875 - val_loss: 0.6188
Epoch 12/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6250 - val_accuracy: 0.6875 - val_loss: 0.6094
Epoch 13/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6157 - val_accuracy: 0.6562 - val_loss: 0.6004
Epoch 14/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6080 - val_accuracy: 0.6562 - val_loss: 0.5921
Epoch 15/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.6004 - val_accuracy: 0.6562 - val_loss: 0.5872
Epoch 16/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.5943 - val_accuracy: 0.6875 - val_loss: 0.5830
Epoch 17/400
7/7 - 0s - 8ms/step - accuracy: 0.6484 - loss: 0.5893 - val_accuracy: 0.6875 - val_loss: 0.5780
Epoch 18/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.5845 - val_accuracy: 0.6875 - val_loss: 0.5731
Epoch 19/400
7/7 - 0s - 8ms/step - accuracy: 0.6406 - loss: 0.5805 - val_accuracy: 0.6875 - val_loss: 0.5697
Epoch 20/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.5770 - val_accuracy: 0.6875 - val_loss: 0.5672
Epoch 21/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.5732 - val_accuracy: 0.6875 - val_loss: 0.5628
Epoch 22/400
7/7 - 0s - 9ms/step - accuracy: 0.6406 - loss: 0.5695 - val_accuracy: 0.6875 - val_loss: 0.5595
Epoch 23/400
7/7 - 0s - 10ms/step - accuracy: 0.6406 - loss: 0.5654 - val_accuracy: 0.6875 - val_loss: 0.5564
Epoch 24/400
7/7 - 0s - 8ms/step - accuracy: 0.6328 - loss: 0.5620 - val_accuracy: 0.6875 - val_loss: 0.5524
Epoch 25/400
7/7 - 0s - 8ms/step - accuracy: 0.6328 - loss: 0.5583 - val_accuracy: 0.6875 - val_loss: 0.5488
Epoch 26/400
7/7 - 0s - 8ms/step - accuracy: 0.6406 - loss: 0.5550 - val_accuracy: 0.6875 - val_loss: 0.5445
Epoch 27/400
7/7 - 0s - 8ms/step - accuracy: 0.6484 - loss: 0.5511 - val_accuracy: 0.6875 - val_loss: 0.5396
Epoch 28/400
7/7 - 0s - 9ms/step - accuracy: 0.6562 - loss: 0.5474 - val_accuracy: 0.6875 - val_loss: 0.5347
Epoch 29/400
7/7 - 0s - 9ms/step - accuracy: 0.6562 - loss: 0.5437 - val_accuracy: 0.6875 - val_loss: 0.5307
Epoch 30/400
7/7 - 0s - 9ms/step - accuracy: 0.6562 - loss: 0.5404 - val_accuracy: 0.6875 - val_loss: 0.5255
Epoch 31/400
7/7 - 0s - 9ms/step - accuracy: 0.6641 - loss: 0.5366 - val_accuracy: 0.6875 - val_loss: 0.5235
Epoch 32/400
7/7 - 0s - 8ms/step - accuracy: 0.6641 - loss: 0.5334 - val_accuracy: 0.6875 - val_loss: 0.5199
Epoch 33/400
7/7 - 0s - 9ms/step - accuracy: 0.6641 - loss: 0.5295 - val_accuracy: 0.6875 - val_loss: 0.5156
Epoch 34/400
7/7 - 0s - 8ms/step - accuracy: 0.6641 - loss: 0.5256 - val_accuracy: 0.7188 - val_loss: 0.5094
Epoch 35/400
7/7 - 0s - 9ms/step - accuracy: 0.6641 - loss: 0.5216 - val_accuracy: 0.7188 - val_loss: 0.5035
Epoch 36/400
7/7 - 0s - 9ms/step - accuracy: 0.6875 - loss: 0.5183 - val_accuracy: 0.7500 - val_loss: 0.4985
Epoch 37/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.5144 - val_accuracy: 0.7500 - val_loss: 0.4933
Epoch 38/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5102 - val_accuracy: 0.7500 - val_loss: 0.4884
Epoch 39/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.5067 - val_accuracy: 0.7500 - val_loss: 0.4838
Epoch 40/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.5028 - val_accuracy: 0.7500 - val_loss: 0.4793
Epoch 41/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.4990 - val_accuracy: 0.7500 - val_loss: 0.4741
Epoch 42/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.4953 - val_accuracy: 0.7812 - val_loss: 0.4692
Epoch 43/400
7/7 - 0s - 8ms/step - accuracy: 0.7109 - loss: 0.4918 - val_accuracy: 0.7812 - val_loss: 0.4642
Epoch 44/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.4881 - val_accuracy: 0.7812 - val_loss: 0.4607
Epoch 45/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.4840 - val_accuracy: 0.7812 - val_loss: 0.4568
Epoch 46/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.4807 - val_accuracy: 0.7812 - val_loss: 0.4520
Epoch 47/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.4768 - val_accuracy: 0.7812 - val_loss: 0.4477
Epoch 48/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.4730 - val_accuracy: 0.8125 - val_loss: 0.4413
Epoch 49/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.4692 - val_accuracy: 0.8125 - val_loss: 0.4379
Epoch 50/400
7/7 - 0s - 8ms/step - accuracy: 0.7031 - loss: 0.4654 - val_accuracy: 0.8125 - val_loss: 0.4330
Epoch 51/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.4618 - val_accuracy: 0.8125 - val_loss: 0.4296
Epoch 52/400
7/7 - 0s - 9ms/step - accuracy: 0.7031 - loss: 0.4582 - val_accuracy: 0.8125 - val_loss: 0.4240
Epoch 53/400
7/7 - 0s - 9ms/step - accuracy: 0.6953 - loss: 0.4545 - val_accuracy: 0.8125 - val_loss: 0.4211
Epoch 54/400
7/7 - 0s - 9ms/step - accuracy: 0.7109 - loss: 0.4506 - val_accuracy: 0.8125 - val_loss: 0.4187
Epoch 55/400
7/7 - 0s - 9ms/step - accuracy: 0.7266 - loss: 0.4471 - val_accuracy: 0.8125 - val_loss: 0.4140
Epoch 56/400
7/7 - 0s - 8ms/step - accuracy: 0.7344 - loss: 0.4435 - val_accuracy: 0.8125 - val_loss: 0.4107
Epoch 57/400
7/7 - 0s - 8ms/step - accuracy: 0.7344 - loss: 0.4397 - val_accuracy: 0.8125 - val_loss: 0.4065
Epoch 58/400
7/7 - 0s - 8ms/step - accuracy: 0.7422 - loss: 0.4362 - val_accuracy: 0.8125 - val_loss: 0.4030
Epoch 59/400
7/7 - 0s - 9ms/step - accuracy: 0.7422 - loss: 0.4324 - val_accuracy: 0.8125 - val_loss: 0.3989
Epoch 60/400
7/7 - 0s - 9ms/step - accuracy: 0.7578 - loss: 0.4284 - val_accuracy: 0.8125 - val_loss: 0.3950
Epoch 61/400
7/7 - 0s - 8ms/step - accuracy: 0.7656 - loss: 0.4249 - val_accuracy: 0.8125 - val_loss: 0.3900
Epoch 62/400
7/7 - 0s - 9ms/step - accuracy: 0.7734 - loss: 0.4212 - val_accuracy: 0.8125 - val_loss: 0.3858
Epoch 63/400
7/7 - 0s - 9ms/step - accuracy: 0.7734 - loss: 0.4173 - val_accuracy: 0.8125 - val_loss: 0.3813
Epoch 64/400
7/7 - 0s - 8ms/step - accuracy: 0.7812 - loss: 0.4133 - val_accuracy: 0.8438 - val_loss: 0.3784
Epoch 65/400
7/7 - 0s - 8ms/step - accuracy: 0.7812 - loss: 0.4093 - val_accuracy: 0.8438 - val_loss: 0.3752
Epoch 66/400
7/7 - 0s - 8ms/step - accuracy: 0.7812 - loss: 0.4060 - val_accuracy: 0.8438 - val_loss: 0.3740
Epoch 67/400
7/7 - 0s - 8ms/step - accuracy: 0.8125 - loss: 0.4022 - val_accuracy: 0.8438 - val_loss: 0.3699
Epoch 68/400
7/7 - 0s - 8ms/step - accuracy: 0.8125 - loss: 0.3986 - val_accuracy: 0.8438 - val_loss: 0.3678
Epoch 69/400
7/7 - 0s - 9ms/step - accuracy: 0.8125 - loss: 0.3956 - val_accuracy: 0.8438 - val_loss: 0.3642
Epoch 70/400
7/7 - 0s - 9ms/step - accuracy: 0.8125 - loss: 0.3921 - val_accuracy: 0.8750 - val_loss: 0.3610
Epoch 71/400
7/7 - 0s - 9ms/step - accuracy: 0.8203 - loss: 0.3886 - val_accuracy: 0.8750 - val_loss: 0.3589
Epoch 72/400
7/7 - 0s - 9ms/step - accuracy: 0.8281 - loss: 0.3853 - val_accuracy: 0.8750 - val_loss: 0.3555
Epoch 73/400
7/7 - 0s - 9ms/step - accuracy: 0.8281 - loss: 0.3820 - val_accuracy: 0.8750 - val_loss: 0.3536
Epoch 74/400
7/7 - 0s - 9ms/step - accuracy: 0.8281 - loss: 0.3788 - val_accuracy: 0.8750 - val_loss: 0.3493
Epoch 75/400
7/7 - 0s - 9ms/step - accuracy: 0.8359 - loss: 0.3752 - val_accuracy: 0.8750 - val_loss: 0.3453
Epoch 76/400
7/7 - 0s - 9ms/step - accuracy: 0.8438 - loss: 0.3721 - val_accuracy: 0.8750 - val_loss: 0.3420
Epoch 77/400
7/7 - 0s - 9ms/step - accuracy: 0.8438 - loss: 0.3692 - val_accuracy: 0.8750 - val_loss: 0.3378
Epoch 78/400
7/7 - 0s - 9ms/step - accuracy: 0.8516 - loss: 0.3659 - val_accuracy: 0.8750 - val_loss: 0.3353
Epoch 79/400
7/7 - 0s - 9ms/step - accuracy: 0.8516 - loss: 0.3627 - val_accuracy: 0.9062 - val_loss: 0.3318
Epoch 80/400
7/7 - 0s - 9ms/step - accuracy: 0.8516 - loss: 0.3599 - val_accuracy: 0.9062 - val_loss: 0.3294
Epoch 81/400
7/7 - 0s - 9ms/step - accuracy: 0.8516 - loss: 0.3567 - val_accuracy: 0.9062 - val_loss: 0.3242
Epoch 82/400
7/7 - 0s - 9ms/step - accuracy: 0.8516 - loss: 0.3535 - val_accuracy: 0.9062 - val_loss: 0.3226
Epoch 83/400
7/7 - 0s - 9ms/step - accuracy: 0.8594 - loss: 0.3507 - val_accuracy: 0.9062 - val_loss: 0.3202
Epoch 84/400
7/7 - 0s - 8ms/step - accuracy: 0.8828 - loss: 0.3477 - val_accuracy: 0.9062 - val_loss: 0.3163
Epoch 85/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3445 - val_accuracy: 0.9062 - val_loss: 0.3123
Epoch 86/400
7/7 - 0s - 9ms/step - accuracy: 0.8828 - loss: 0.3413 - val_accuracy: 0.9062 - val_loss: 0.3095
Epoch 87/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3383 - val_accuracy: 0.9062 - val_loss: 0.3072
Epoch 88/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3351 - val_accuracy: 0.9062 - val_loss: 0.3048
Epoch 89/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3324 - val_accuracy: 0.9062 - val_loss: 0.3005
Epoch 90/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3292 - val_accuracy: 0.9062 - val_loss: 0.2990
Epoch 91/400
7/7 - 0s - 9ms/step - accuracy: 0.8906 - loss: 0.3267 - val_accuracy: 0.9062 - val_loss: 0.2966
Epoch 92/400
7/7 - 0s - 8ms/step - accuracy: 0.8906 - loss: 0.3238 - val_accuracy: 0.9062 - val_loss: 0.2946
Epoch 93/400
7/7 - 0s - 9ms/step - accuracy: 0.8984 - loss: 0.3210 - val_accuracy: 0.9062 - val_loss: 0.2921
Epoch 94/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.3182 - val_accuracy: 0.9062 - val_loss: 0.2882
Epoch 95/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.3155 - val_accuracy: 0.9375 - val_loss: 0.2848
Epoch 96/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.3124 - val_accuracy: 0.9375 - val_loss: 0.2818
Epoch 97/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.3099 - val_accuracy: 0.9375 - val_loss: 0.2779
Epoch 98/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.3078 - val_accuracy: 0.9375 - val_loss: 0.2757
Epoch 99/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.3051 - val_accuracy: 0.9375 - val_loss: 0.2721
Epoch 100/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.3030 - val_accuracy: 0.9375 - val_loss: 0.2722
Epoch 101/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.3009 - val_accuracy: 0.9375 - val_loss: 0.2711
Epoch 102/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.2989 - val_accuracy: 0.9375 - val_loss: 0.2669
Epoch 103/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.2966 - val_accuracy: 0.9375 - val_loss: 0.2651
Epoch 104/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.2944 - val_accuracy: 0.9375 - val_loss: 0.2619
Epoch 105/400
7/7 - 0s - 8ms/step - accuracy: 0.9062 - loss: 0.2925 - val_accuracy: 0.9375 - val_loss: 0.2596
Epoch 106/400
7/7 - 0s - 9ms/step - accuracy: 0.9062 - loss: 0.2901 - val_accuracy: 0.9375 - val_loss: 0.2562
Epoch 107/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2878 - val_accuracy: 0.9375 - val_loss: 0.2552
Epoch 108/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2855 - val_accuracy: 0.9375 - val_loss: 0.2539
Epoch 109/400
7/7 - 0s - 8ms/step - accuracy: 0.9141 - loss: 0.2835 - val_accuracy: 0.9375 - val_loss: 0.2513
Epoch 110/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2812 - val_accuracy: 0.9375 - val_loss: 0.2511
Epoch 111/400
7/7 - 0s - 10ms/step - accuracy: 0.9141 - loss: 0.2791 - val_accuracy: 0.9375 - val_loss: 0.2471
Epoch 112/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2771 - val_accuracy: 0.9375 - val_loss: 0.2454
Epoch 113/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2753 - val_accuracy: 0.9375 - val_loss: 0.2417
Epoch 114/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2730 - val_accuracy: 0.9375 - val_loss: 0.2398
Epoch 115/400
7/7 - 0s - 9ms/step - accuracy: 0.9141 - loss: 0.2714 - val_accuracy: 0.9375 - val_loss: 0.2381
Epoch 116/400
7/7 - 0s - 8ms/step - accuracy: 0.9141 - loss: 0.2691 - val_accuracy: 0.9375 - val_loss: 0.2369
Epoch 117/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.2671 - val_accuracy: 0.9375 - val_loss: 0.2358
Epoch 118/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.2654 - val_accuracy: 0.9375 - val_loss: 0.2348
Epoch 119/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.2632 - val_accuracy: 0.9375 - val_loss: 0.2330
Epoch 120/400
7/7 - 0s - 8ms/step - accuracy: 0.9219 - loss: 0.2613 - val_accuracy: 0.9375 - val_loss: 0.2305
Epoch 121/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.2595 - val_accuracy: 0.9375 - val_loss: 0.2288
Epoch 122/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.2581 - val_accuracy: 0.9375 - val_loss: 0.2253
Epoch 123/400
7/7 - 0s - 9ms/step - accuracy: 0.9219 - loss: 0.2564 - val_accuracy: 0.9375 - val_loss: 0.2247
Epoch 124/400
7/7 - 0s - 8ms/step - accuracy: 0.9297 - loss: 0.2547 - val_accuracy: 0.9375 - val_loss: 0.2241
Epoch 125/400
7/7 - 0s - 9ms/step - accuracy: 0.9531 - loss: 0.2530 - val_accuracy: 0.9375 - val_loss: 0.2216
Epoch 126/400
7/7 - 0s - 8ms/step - accuracy: 0.9531 - loss: 0.2515 - val_accuracy: 0.9375 - val_loss: 0.2206
Epoch 127/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2498 - val_accuracy: 0.9375 - val_loss: 0.2183
Epoch 128/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2479 - val_accuracy: 0.9688 - val_loss: 0.2174
Epoch 129/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2461 - val_accuracy: 0.9688 - val_loss: 0.2162
Epoch 130/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2448 - val_accuracy: 0.9688 - val_loss: 0.2131
Epoch 131/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2435 - val_accuracy: 0.9688 - val_loss: 0.2113
Epoch 132/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2415 - val_accuracy: 0.9688 - val_loss: 0.2112
Epoch 133/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2401 - val_accuracy: 0.9688 - val_loss: 0.2116
Epoch 134/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2387 - val_accuracy: 0.9688 - val_loss: 0.2099
Epoch 135/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2369 - val_accuracy: 0.9688 - val_loss: 0.2081
Epoch 136/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2354 - val_accuracy: 0.9688 - val_loss: 0.2080
Epoch 137/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2334 - val_accuracy: 0.9688 - val_loss: 0.2066
Epoch 138/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2322 - val_accuracy: 0.9688 - val_loss: 0.2075
Epoch 139/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2308 - val_accuracy: 0.9688 - val_loss: 0.2040
Epoch 140/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2292 - val_accuracy: 0.9688 - val_loss: 0.2037
Epoch 141/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2281 - val_accuracy: 0.9688 - val_loss: 0.2019
Epoch 142/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2269 - val_accuracy: 0.9688 - val_loss: 0.2005
Epoch 143/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2255 - val_accuracy: 0.9688 - val_loss: 0.1991
Epoch 144/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2238 - val_accuracy: 0.9688 - val_loss: 0.1962
Epoch 145/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2226 - val_accuracy: 0.9688 - val_loss: 0.1938
Epoch 146/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2216 - val_accuracy: 0.9688 - val_loss: 0.1954
Epoch 147/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2199 - val_accuracy: 0.9688 - val_loss: 0.1949
Epoch 148/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2189 - val_accuracy: 0.9688 - val_loss: 0.1942
Epoch 149/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2178 - val_accuracy: 0.9688 - val_loss: 0.1936
Epoch 150/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2161 - val_accuracy: 0.9688 - val_loss: 0.1904
Epoch 151/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2152 - val_accuracy: 0.9688 - val_loss: 0.1902
Epoch 152/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2137 - val_accuracy: 0.9688 - val_loss: 0.1892
Epoch 153/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2130 - val_accuracy: 0.9688 - val_loss: 0.1878
Epoch 154/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2113 - val_accuracy: 0.9688 - val_loss: 0.1884
Epoch 155/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2102 - val_accuracy: 0.9688 - val_loss: 0.1870
Epoch 156/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2090 - val_accuracy: 0.9688 - val_loss: 0.1835
Epoch 157/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2075 - val_accuracy: 0.9688 - val_loss: 0.1829
Epoch 158/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2067 - val_accuracy: 0.9688 - val_loss: 0.1804
Epoch 159/400
7/7 - 0s - 8ms/step - accuracy: 0.9609 - loss: 0.2054 - val_accuracy: 0.9688 - val_loss: 0.1797
Epoch 160/400
7/7 - 0s - 9ms/step - accuracy: 0.9609 - loss: 0.2047 - val_accuracy: 0.9688 - val_loss: 0.1809
Epoch 161/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.2034 - val_accuracy: 0.9688 - val_loss: 0.1788
Epoch 162/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.2023 - val_accuracy: 0.9688 - val_loss: 0.1797
Epoch 163/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.2015 - val_accuracy: 0.9688 - val_loss: 0.1780
Epoch 164/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.2008 - val_accuracy: 0.9688 - val_loss: 0.1775
Epoch 165/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1994 - val_accuracy: 0.9688 - val_loss: 0.1752
Epoch 166/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1990 - val_accuracy: 0.9688 - val_loss: 0.1740
Epoch 167/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1977 - val_accuracy: 0.9688 - val_loss: 0.1739
Epoch 168/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1970 - val_accuracy: 0.9688 - val_loss: 0.1727
Epoch 169/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1961 - val_accuracy: 0.9688 - val_loss: 0.1722
Epoch 170/400
7/7 - 0s - 8ms/step - accuracy: 0.9688 - loss: 0.1954 - val_accuracy: 0.9688 - val_loss: 0.1706
Epoch 171/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1941 - val_accuracy: 0.9688 - val_loss: 0.1702
Epoch 172/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1934 - val_accuracy: 0.9688 - val_loss: 0.1695
Epoch 173/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1923 - val_accuracy: 0.9688 - val_loss: 0.1718
Epoch 174/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1913 - val_accuracy: 0.9688 - val_loss: 0.1693
Epoch 175/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1905 - val_accuracy: 0.9688 - val_loss: 0.1685
Epoch 176/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1898 - val_accuracy: 0.9688 - val_loss: 0.1697
Epoch 177/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1885 - val_accuracy: 0.9688 - val_loss: 0.1682
Epoch 178/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1879 - val_accuracy: 0.9375 - val_loss: 0.1694
Epoch 179/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1873 - val_accuracy: 0.9688 - val_loss: 0.1667
Epoch 180/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1864 - val_accuracy: 0.9688 - val_loss: 0.1649
Epoch 181/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1857 - val_accuracy: 0.9688 - val_loss: 0.1649
Epoch 182/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1845 - val_accuracy: 0.9688 - val_loss: 0.1636
Epoch 183/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1835 - val_accuracy: 0.9688 - val_loss: 0.1620
Epoch 184/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1828 - val_accuracy: 0.9688 - val_loss: 0.1613
Epoch 185/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1823 - val_accuracy: 0.9688 - val_loss: 0.1585
Epoch 186/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1812 - val_accuracy: 0.9688 - val_loss: 0.1592
Epoch 187/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1803 - val_accuracy: 0.9688 - val_loss: 0.1574
Epoch 188/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1798 - val_accuracy: 0.9688 - val_loss: 0.1561
Epoch 189/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1788 - val_accuracy: 0.9688 - val_loss: 0.1580
Epoch 190/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1779 - val_accuracy: 0.9375 - val_loss: 0.1587
Epoch 191/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1779 - val_accuracy: 0.9375 - val_loss: 0.1581
Epoch 192/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1768 - val_accuracy: 0.9375 - val_loss: 0.1585
Epoch 193/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1758 - val_accuracy: 0.9375 - val_loss: 0.1565
Epoch 194/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1749 - val_accuracy: 0.9688 - val_loss: 0.1548
Epoch 195/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1748 - val_accuracy: 0.9375 - val_loss: 0.1565
Epoch 196/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1737 - val_accuracy: 0.9375 - val_loss: 0.1560
Epoch 197/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1729 - val_accuracy: 0.9375 - val_loss: 0.1534
Epoch 198/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1723 - val_accuracy: 0.9375 - val_loss: 0.1525
Epoch 199/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1713 - val_accuracy: 0.9375 - val_loss: 0.1512
Epoch 200/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1709 - val_accuracy: 0.9688 - val_loss: 0.1492
Epoch 201/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1700 - val_accuracy: 0.9375 - val_loss: 0.1491
Epoch 202/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1690 - val_accuracy: 0.9688 - val_loss: 0.1468
Epoch 203/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1685 - val_accuracy: 0.9688 - val_loss: 0.1467
Epoch 204/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1677 - val_accuracy: 0.9688 - val_loss: 0.1456
Epoch 205/400
7/7 - 0s - 8ms/step - accuracy: 0.9688 - loss: 0.1669 - val_accuracy: 0.9688 - val_loss: 0.1452
Epoch 206/400
7/7 - 0s - 8ms/step - accuracy: 0.9688 - loss: 0.1662 - val_accuracy: 0.9375 - val_loss: 0.1465
Epoch 207/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1656 - val_accuracy: 0.9688 - val_loss: 0.1442
Epoch 208/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1650 - val_accuracy: 0.9688 - val_loss: 0.1428
Epoch 209/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1641 - val_accuracy: 0.9688 - val_loss: 0.1429
Epoch 210/400
7/7 - 0s - 8ms/step - accuracy: 0.9688 - loss: 0.1637 - val_accuracy: 0.9375 - val_loss: 0.1429
Epoch 211/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1632 - val_accuracy: 0.9375 - val_loss: 0.1446
Epoch 212/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1622 - val_accuracy: 0.9375 - val_loss: 0.1429
Epoch 213/400
7/7 - 0s - 8ms/step - accuracy: 0.9688 - loss: 0.1618 - val_accuracy: 0.9375 - val_loss: 0.1417
Epoch 214/400
7/7 - 0s - 8ms/step - accuracy: 0.9688 - loss: 0.1608 - val_accuracy: 0.9375 - val_loss: 0.1416
Epoch 215/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1609 - val_accuracy: 0.9375 - val_loss: 0.1434
Epoch 216/400
7/7 - 0s - 10ms/step - accuracy: 0.9688 - loss: 0.1597 - val_accuracy: 0.9375 - val_loss: 0.1430
Epoch 217/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1594 - val_accuracy: 0.9375 - val_loss: 0.1421
Epoch 218/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1586 - val_accuracy: 0.9375 - val_loss: 0.1405
Epoch 219/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1578 - val_accuracy: 0.9375 - val_loss: 0.1394
Epoch 220/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1574 - val_accuracy: 0.9375 - val_loss: 0.1400
Epoch 221/400
7/7 - 0s - 9ms/step - accuracy: 0.9688 - loss: 0.1570 - val_accuracy: 0.9375 - val_loss: 0.1408
Epoch 222/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1561 - val_accuracy: 0.9375 - val_loss: 0.1380
Epoch 223/400
7/7 - 0s - 8ms/step - accuracy: 0.9688 - loss: 0.1556 - val_accuracy: 0.9375 - val_loss: 0.1396
Epoch 224/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1549 - val_accuracy: 0.9375 - val_loss: 0.1399
Epoch 225/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1541 - val_accuracy: 0.9375 - val_loss: 0.1381
Epoch 226/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1539 - val_accuracy: 0.9375 - val_loss: 0.1353
Epoch 227/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1531 - val_accuracy: 0.9375 - val_loss: 0.1359
Epoch 228/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1524 - val_accuracy: 0.9375 - val_loss: 0.1337
Epoch 229/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1519 - val_accuracy: 0.9375 - val_loss: 0.1338
Epoch 230/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1519 - val_accuracy: 0.9375 - val_loss: 0.1338
Epoch 231/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1510 - val_accuracy: 0.9375 - val_loss: 0.1333
Epoch 232/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1499 - val_accuracy: 0.9375 - val_loss: 0.1329
Epoch 233/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1504 - val_accuracy: 0.9375 - val_loss: 0.1348
Epoch 234/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1490 - val_accuracy: 0.9375 - val_loss: 0.1334
Epoch 235/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1490 - val_accuracy: 0.9375 - val_loss: 0.1323
Epoch 236/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1479 - val_accuracy: 0.9375 - val_loss: 0.1310
Epoch 237/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1481 - val_accuracy: 0.9375 - val_loss: 0.1281
Epoch 238/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1468 - val_accuracy: 0.9375 - val_loss: 0.1279
Epoch 239/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1469 - val_accuracy: 0.9375 - val_loss: 0.1264
Epoch 240/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1461 - val_accuracy: 0.9375 - val_loss: 0.1268
Epoch 241/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1459 - val_accuracy: 0.9375 - val_loss: 0.1254
Epoch 242/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1450 - val_accuracy: 0.9375 - val_loss: 0.1271
Epoch 243/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1445 - val_accuracy: 0.9375 - val_loss: 0.1273
Epoch 244/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1442 - val_accuracy: 0.9375 - val_loss: 0.1275
Epoch 245/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1439 - val_accuracy: 0.9375 - val_loss: 0.1278
Epoch 246/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1434 - val_accuracy: 0.9375 - val_loss: 0.1270
Epoch 247/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1429 - val_accuracy: 0.9375 - val_loss: 0.1285
Epoch 248/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1421 - val_accuracy: 0.9375 - val_loss: 0.1278
Epoch 249/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1418 - val_accuracy: 0.9375 - val_loss: 0.1262
Epoch 250/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1411 - val_accuracy: 0.9375 - val_loss: 0.1257
Epoch 251/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1410 - val_accuracy: 0.9375 - val_loss: 0.1229
Epoch 252/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1402 - val_accuracy: 0.9688 - val_loss: 0.1216
Epoch 253/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1399 - val_accuracy: 0.9375 - val_loss: 0.1217
Epoch 254/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1397 - val_accuracy: 0.9375 - val_loss: 0.1222
Epoch 255/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1392 - val_accuracy: 0.9375 - val_loss: 0.1227
Epoch 256/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1389 - val_accuracy: 0.9375 - val_loss: 0.1207
Epoch 257/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1380 - val_accuracy: 0.9375 - val_loss: 0.1208
Epoch 258/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1377 - val_accuracy: 0.9375 - val_loss: 0.1223
Epoch 259/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1375 - val_accuracy: 0.9375 - val_loss: 0.1218
Epoch 260/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1370 - val_accuracy: 0.9375 - val_loss: 0.1211
Epoch 261/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1359 - val_accuracy: 0.9375 - val_loss: 0.1202
Epoch 262/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1360 - val_accuracy: 0.9375 - val_loss: 0.1182
Epoch 263/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1358 - val_accuracy: 0.9688 - val_loss: 0.1161
Epoch 264/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1352 - val_accuracy: 0.9375 - val_loss: 0.1186
Epoch 265/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1344 - val_accuracy: 0.9375 - val_loss: 0.1207
Epoch 266/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1345 - val_accuracy: 0.9375 - val_loss: 0.1205
Epoch 267/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1334 - val_accuracy: 0.9375 - val_loss: 0.1194
Epoch 268/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1337 - val_accuracy: 0.9375 - val_loss: 0.1195
Epoch 269/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1328 - val_accuracy: 0.9375 - val_loss: 0.1186
Epoch 270/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1333 - val_accuracy: 0.9375 - val_loss: 0.1208
Epoch 271/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1320 - val_accuracy: 0.9375 - val_loss: 0.1186
Epoch 272/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1319 - val_accuracy: 0.9375 - val_loss: 0.1185
Epoch 273/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1315 - val_accuracy: 0.9375 - val_loss: 0.1191
Epoch 274/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1309 - val_accuracy: 0.9375 - val_loss: 0.1178
Epoch 275/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1307 - val_accuracy: 0.9375 - val_loss: 0.1175
Epoch 276/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1304 - val_accuracy: 0.9375 - val_loss: 0.1168
Epoch 277/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1302 - val_accuracy: 0.9375 - val_loss: 0.1192
Epoch 278/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1297 - val_accuracy: 0.9375 - val_loss: 0.1185
Epoch 279/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1289 - val_accuracy: 0.9375 - val_loss: 0.1162
Epoch 280/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1287 - val_accuracy: 0.9375 - val_loss: 0.1153
Epoch 281/400
7/7 - 0s - 10ms/step - accuracy: 0.9766 - loss: 0.1285 - val_accuracy: 0.9375 - val_loss: 0.1172
Epoch 282/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1278 - val_accuracy: 0.9375 - val_loss: 0.1132
Epoch 283/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1275 - val_accuracy: 0.9375 - val_loss: 0.1150
Epoch 284/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1275 - val_accuracy: 0.9375 - val_loss: 0.1137
Epoch 285/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1270 - val_accuracy: 0.9375 - val_loss: 0.1155
Epoch 286/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1266 - val_accuracy: 0.9688 - val_loss: 0.1128
Epoch 287/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1263 - val_accuracy: 0.9375 - val_loss: 0.1141
Epoch 288/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1256 - val_accuracy: 0.9375 - val_loss: 0.1150
Epoch 289/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1255 - val_accuracy: 0.9375 - val_loss: 0.1137
Epoch 290/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1257 - val_accuracy: 0.9375 - val_loss: 0.1129
Epoch 291/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1247 - val_accuracy: 0.9375 - val_loss: 0.1121
Epoch 292/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1241 - val_accuracy: 0.9375 - val_loss: 0.1116
Epoch 293/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1240 - val_accuracy: 0.9375 - val_loss: 0.1129
Epoch 294/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1237 - val_accuracy: 0.9688 - val_loss: 0.1091
Epoch 295/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1230 - val_accuracy: 0.9688 - val_loss: 0.1084
Epoch 296/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1229 - val_accuracy: 0.9688 - val_loss: 0.1080
Epoch 297/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1223 - val_accuracy: 0.9688 - val_loss: 0.1068
Epoch 298/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1229 - val_accuracy: 0.9688 - val_loss: 0.1070
Epoch 299/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1218 - val_accuracy: 0.9375 - val_loss: 0.1092
Epoch 300/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1213 - val_accuracy: 0.9375 - val_loss: 0.1096
Epoch 301/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1212 - val_accuracy: 0.9688 - val_loss: 0.1083
Epoch 302/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1208 - val_accuracy: 0.9688 - val_loss: 0.1075
Epoch 303/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1208 - val_accuracy: 0.9688 - val_loss: 0.1075
Epoch 304/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1203 - val_accuracy: 0.9688 - val_loss: 0.1048
Epoch 305/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1196 - val_accuracy: 0.9375 - val_loss: 0.1076
Epoch 306/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1194 - val_accuracy: 0.9688 - val_loss: 0.1042
Epoch 307/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1189 - val_accuracy: 0.9688 - val_loss: 0.1039
Epoch 308/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1186 - val_accuracy: 0.9688 - val_loss: 0.1043
Epoch 309/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1188 - val_accuracy: 0.9375 - val_loss: 0.1060
Epoch 310/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1183 - val_accuracy: 0.9375 - val_loss: 0.1076
Epoch 311/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1180 - val_accuracy: 0.9375 - val_loss: 0.1091
Epoch 312/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1176 - val_accuracy: 0.9375 - val_loss: 0.1097
Epoch 313/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1176 - val_accuracy: 0.9375 - val_loss: 0.1055
Epoch 314/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1168 - val_accuracy: 0.9375 - val_loss: 0.1052
Epoch 315/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1168 - val_accuracy: 0.9375 - val_loss: 0.1045
Epoch 316/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1161 - val_accuracy: 0.9375 - val_loss: 0.1045
Epoch 317/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1163 - val_accuracy: 0.9688 - val_loss: 0.1019
Epoch 318/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1157 - val_accuracy: 0.9688 - val_loss: 0.1027
Epoch 319/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1153 - val_accuracy: 0.9375 - val_loss: 0.1042
Epoch 320/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1151 - val_accuracy: 0.9375 - val_loss: 0.1035
Epoch 321/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1153 - val_accuracy: 0.9375 - val_loss: 0.1036
Epoch 322/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1147 - val_accuracy: 0.9375 - val_loss: 0.1038
Epoch 323/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1141 - val_accuracy: 0.9375 - val_loss: 0.1053
Epoch 324/400
7/7 - 0s - 10ms/step - accuracy: 0.9766 - loss: 0.1140 - val_accuracy: 0.9375 - val_loss: 0.1029
Epoch 325/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1134 - val_accuracy: 0.9375 - val_loss: 0.1032
Epoch 326/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1135 - val_accuracy: 0.9375 - val_loss: 0.1028
Epoch 327/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1131 - val_accuracy: 0.9688 - val_loss: 0.0988
Epoch 328/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1129 - val_accuracy: 0.9688 - val_loss: 0.0990
Epoch 329/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1123 - val_accuracy: 0.9688 - val_loss: 0.0983
Epoch 330/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1118 - val_accuracy: 0.9688 - val_loss: 0.1014
Epoch 331/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1117 - val_accuracy: 0.9688 - val_loss: 0.1004
Epoch 332/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1121 - val_accuracy: 0.9688 - val_loss: 0.1002
Epoch 333/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1111 - val_accuracy: 0.9688 - val_loss: 0.0992
Epoch 334/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1109 - val_accuracy: 0.9688 - val_loss: 0.0977
Epoch 335/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1107 - val_accuracy: 0.9688 - val_loss: 0.0970
Epoch 336/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1103 - val_accuracy: 0.9688 - val_loss: 0.0974
Epoch 337/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1102 - val_accuracy: 0.9688 - val_loss: 0.0960
Epoch 338/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1098 - val_accuracy: 0.9688 - val_loss: 0.0965
Epoch 339/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1095 - val_accuracy: 0.9688 - val_loss: 0.0967
Epoch 340/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1091 - val_accuracy: 0.9688 - val_loss: 0.0971
Epoch 341/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1090 - val_accuracy: 0.9688 - val_loss: 0.0944
Epoch 342/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1089 - val_accuracy: 0.9688 - val_loss: 0.0949
Epoch 343/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1085 - val_accuracy: 0.9688 - val_loss: 0.0927
Epoch 344/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1083 - val_accuracy: 0.9688 - val_loss: 0.0938
Epoch 345/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1081 - val_accuracy: 0.9688 - val_loss: 0.0942
Epoch 346/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1079 - val_accuracy: 0.9688 - val_loss: 0.0944
Epoch 347/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1076 - val_accuracy: 0.9688 - val_loss: 0.0939
Epoch 348/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1075 - val_accuracy: 0.9688 - val_loss: 0.0943
Epoch 349/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1067 - val_accuracy: 0.9688 - val_loss: 0.0973
Epoch 350/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1070 - val_accuracy: 0.9688 - val_loss: 0.0963
Epoch 351/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1067 - val_accuracy: 0.9688 - val_loss: 0.0956
Epoch 352/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1060 - val_accuracy: 0.9688 - val_loss: 0.0941
Epoch 353/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1056 - val_accuracy: 0.9688 - val_loss: 0.0932
Epoch 354/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1056 - val_accuracy: 0.9688 - val_loss: 0.0949
Epoch 355/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1059 - val_accuracy: 0.9688 - val_loss: 0.0934
Epoch 356/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1054 - val_accuracy: 0.9688 - val_loss: 0.0936
Epoch 357/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1053 - val_accuracy: 0.9688 - val_loss: 0.0928
Epoch 358/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1044 - val_accuracy: 0.9688 - val_loss: 0.0907
Epoch 359/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1044 - val_accuracy: 0.9688 - val_loss: 0.0886
Epoch 360/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1044 - val_accuracy: 0.9688 - val_loss: 0.0893
Epoch 361/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1037 - val_accuracy: 0.9688 - val_loss: 0.0919
Epoch 362/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1037 - val_accuracy: 0.9688 - val_loss: 0.0912
Epoch 363/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1036 - val_accuracy: 0.9688 - val_loss: 0.0917
Epoch 364/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1034 - val_accuracy: 0.9688 - val_loss: 0.0915
Epoch 365/400
7/7 - 0s - 8ms/step - accuracy: 0.9766 - loss: 0.1033 - val_accuracy: 0.9688 - val_loss: 0.0915
Epoch 366/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1026 - val_accuracy: 0.9688 - val_loss: 0.0914
Epoch 367/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1024 - val_accuracy: 0.9688 - val_loss: 0.0919
Epoch 368/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1026 - val_accuracy: 0.9688 - val_loss: 0.0925
Epoch 369/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1021 - val_accuracy: 0.9688 - val_loss: 0.0923
Epoch 370/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1022 - val_accuracy: 0.9688 - val_loss: 0.0891
Epoch 371/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1016 - val_accuracy: 0.9688 - val_loss: 0.0899
Epoch 372/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1018 - val_accuracy: 0.9688 - val_loss: 0.0898
Epoch 373/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1012 - val_accuracy: 0.9688 - val_loss: 0.0903
Epoch 374/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1008 - val_accuracy: 0.9688 - val_loss: 0.0900
Epoch 375/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1007 - val_accuracy: 0.9688 - val_loss: 0.0920
Epoch 376/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1006 - val_accuracy: 0.9688 - val_loss: 0.0881
Epoch 377/400
7/7 - 0s - 10ms/step - accuracy: 0.9766 - loss: 0.1002 - val_accuracy: 0.9688 - val_loss: 0.0869
Epoch 378/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1002 - val_accuracy: 0.9688 - val_loss: 0.0871
Epoch 379/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0995 - val_accuracy: 0.9688 - val_loss: 0.0876
Epoch 380/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.1000 - val_accuracy: 0.9688 - val_loss: 0.0894
Epoch 381/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0998 - val_accuracy: 0.9688 - val_loss: 0.0883
Epoch 382/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0990 - val_accuracy: 0.9688 - val_loss: 0.0890
Epoch 383/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0994 - val_accuracy: 0.9688 - val_loss: 0.0911
Epoch 384/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0990 - val_accuracy: 0.9688 - val_loss: 0.0902
Epoch 385/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0988 - val_accuracy: 0.9688 - val_loss: 0.0899
Epoch 386/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0992 - val_accuracy: 0.9688 - val_loss: 0.0895
Epoch 387/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0985 - val_accuracy: 0.9688 - val_loss: 0.0904
Epoch 388/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0985 - val_accuracy: 0.9688 - val_loss: 0.0871
Epoch 389/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0979 - val_accuracy: 0.9688 - val_loss: 0.0857
Epoch 390/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0979 - val_accuracy: 0.9688 - val_loss: 0.0887
Epoch 391/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0978 - val_accuracy: 0.9688 - val_loss: 0.0881
Epoch 392/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0975 - val_accuracy: 0.9688 - val_loss: 0.0886
Epoch 393/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0980 - val_accuracy: 0.9688 - val_loss: 0.0874
Epoch 394/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0971 - val_accuracy: 0.9688 - val_loss: 0.0869
Epoch 395/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0977 - val_accuracy: 0.9688 - val_loss: 0.0864
Epoch 396/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0971 - val_accuracy: 0.9688 - val_loss: 0.0855
Epoch 397/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0969 - val_accuracy: 0.9688 - val_loss: 0.0848
Epoch 398/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0964 - val_accuracy: 0.9688 - val_loss: 0.0852
Epoch 399/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0965 - val_accuracy: 0.9688 - val_loss: 0.0826
Epoch 400/400
7/7 - 0s - 9ms/step - accuracy: 0.9766 - loss: 0.0961 - val_accuracy: 0.9688 - val_loss: 0.0801
plot (history) + ggtitle ("Training a neural network based classifier on the iris data set" ) + theme_bw ()
