

Project 'VGG16_1FC.Exp07.AonA.10p.masked.fold_1':
[1] "Model type 'VGG16_1FC' sucessfully initialized:"
$model
Model
Model: "sequential"
____________________________________________________________________________________________________________________________________________________________________
Layer (type)                                                             Output Shape                                                      Param #                  
====================================================================================================================================================================
vgg16 (Model)                                                            (None, 7, 7, 512)                                                 14714688                 
____________________________________________________________________________________________________________________________________________________________________
flatten (Flatten)                                                        (None, 25088)                                                     0                        
____________________________________________________________________________________________________________________________________________________________________
fc1 (Dense)                                                              (None, 256)                                                       6422784                  
____________________________________________________________________________________________________________________________________________________________________
Predictions (Dense)                                                      (None, 10)                                                        2570                     
====================================================================================================================================================================
Total params: 21,140,042
Trainable params: 6,425,354
Non-trainable params: 14,714,688
____________________________________________________________________________________________________________________________________________________________________



$classes
                                     name id
1                Asteromphalus.labId_6835  0
2                  Chaetoceros.labId_6813  1
3  Fragilariopsis kerguelensis.labId_8356  2
4      Fragilariopsis rhombica.labId_8362  3
5                    Nitzschia.labId_6758  4
6              Pseudonitzschia.labId_8364  5
7                 Rhizosolenia.labId_6776  6
8            Silicoflagellate.labId_10255  7
9      Thalassiosira gracilis.labId_10366  8
10  Thalassiosira lentiginosa.labId_10369  9

$inputShape
[1] 224 224

$optimizer
<tensorflow.python.keras.optimizers.Adam>

$callbacksList
list()

Data:
Classes: 10

Training: 73 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
7        0               Asteromphalus.labId_6835     3           3           0
10       1                 Chaetoceros.labId_6813     4           4           0
2        2 Fragilariopsis kerguelensis.labId_8356    24          24           0
6        3     Fragilariopsis rhombica.labId_8362     3           3           0
8        4                   Nitzschia.labId_6758     4           4           0
5        5             Pseudonitzschia.labId_8364     9           9           0
3        6                Rhizosolenia.labId_6776     8           8           0
4        7           Silicoflagellate.labId_10255    10          10           0
9        8     Thalassiosira gracilis.labId_10366     4           4           0
1        9  Thalassiosira lentiginosa.labId_10369     4           4           0
11      NA                                    Sum    73          73           0

Validation: 26 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
1        0               Asteromphalus.labId_6835     1           1           0
7        1                 Chaetoceros.labId_6813     2           2           0
5        2 Fragilariopsis kerguelensis.labId_8356     7           7           0
10       3     Fragilariopsis rhombica.labId_8362     1           1           0
3        4                   Nitzschia.labId_6758     2           2           0
2        5             Pseudonitzschia.labId_8364     3           3           0
8        6                Rhizosolenia.labId_6776     3           3           0
6        7           Silicoflagellate.labId_10255     3           3           0
4        8     Thalassiosira gracilis.labId_10366     2           2           0
9        9  Thalassiosira lentiginosa.labId_10369     2           2           0
11      NA                                    Sum    26          26           0

Test: 39 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
8        0               Asteromphalus.labId_6835     2           2           0
9        1                 Chaetoceros.labId_6813     2           2           0
2        2 Fragilariopsis kerguelensis.labId_8356    11          11           0
3        3     Fragilariopsis rhombica.labId_8362     2           2           0
1        4                   Nitzschia.labId_6758     2           2           0
7        5             Pseudonitzschia.labId_8364     5           5           0
5        6                Rhizosolenia.labId_6776     4           4           0
4        7           Silicoflagellate.labId_10255     5           5           0
6        8     Thalassiosira gracilis.labId_10366     3           3           0
10       9  Thalassiosira lentiginosa.labId_10369     3           3           0
11      NA                                    Sum    39          39           0

Compiling Model:

Starting Training:
Epochs: 50
Batch size: 8


Evaluating trained model for project 'VGG16_1FC.Exp07.AonA.10p.masked.fold_1':


Model evaluation:
$confusionMatrix
Confusion Matrix and Statistics

          Reference
Prediction  0  1  2  3  4  5  6  7  8  9
         0  1  0  0  0  0  0  0  0  0  0
         1  1  2  0  0  1  0  0  0  0  0
         2  0  0 11  1  0  0  1  0  0  0
         3  0  0  0  1  0  0  0  0  0  0
         4  0  0  0  0  1  0  0  0  0  0
         5  0  0  0  0  0  5  0  0  0  0
         6  0  0  0  0  0  0  3  0  0  0
         7  0  0  0  0  0  0  0  5  0  0
         8  0  0  0  0  0  0  0  0  3  0
         9  0  0  0  0  0  0  0  0  0  3

Overall Statistics
                                          
               Accuracy : 0.8974          
                 95% CI : (0.7578, 0.9713)
    No Information Rate : 0.2821          
    P-Value [Acc > NIR] : 1.319e-15       
                                          
                  Kappa : 0.8785          
                                          
 Mcnemar's Test P-Value : NA              

Statistics by Class:

                     Class: 0 Class: 1 Class: 2 Class: 3 Class: 4 Class: 5 Class: 6 Class: 7 Class: 8 Class: 9
Precision             1.00000  0.50000   0.8462  1.00000  1.00000   1.0000  1.00000   1.0000  1.00000  1.00000
Recall                0.50000  1.00000   1.0000  0.50000  0.50000   1.0000  0.75000   1.0000  1.00000  1.00000
F1                    0.66667  0.66667   0.9167  0.66667  0.66667   1.0000  0.85714   1.0000  1.00000  1.00000
Prevalence            0.05128  0.05128   0.2821  0.05128  0.05128   0.1282  0.10256   0.1282  0.07692  0.07692
Detection Rate        0.02564  0.05128   0.2821  0.02564  0.02564   0.1282  0.07692   0.1282  0.07692  0.07692
Detection Prevalence  0.02564  0.10256   0.3333  0.02564  0.02564   0.1282  0.07692   0.1282  0.07692  0.07692
Balanced Accuracy     0.75000  0.97297   0.9643  0.75000  0.75000   1.0000  0.87500   1.0000  1.00000  1.00000

$statistics
   class                              className TP FP FN precision recall        F1
1      0               Asteromphalus.labId_6835  1  0  1 1.0000000   0.50 0.6666667
2      1                 Chaetoceros.labId_6813  2  2  0 0.5000000   1.00 0.6666667
3      2 Fragilariopsis kerguelensis.labId_8356 11  2  0 0.8461538   1.00 0.9166667
4      3     Fragilariopsis rhombica.labId_8362  1  0  1 1.0000000   0.50 0.6666667
5      4                   Nitzschia.labId_6758  1  0  1 1.0000000   0.50 0.6666667
6      5             Pseudonitzschia.labId_8364  5  0  0 1.0000000   1.00 1.0000000
7      6                Rhizosolenia.labId_6776  3  0  1 1.0000000   0.75 0.8571429
8      7           Silicoflagellate.labId_10255  5  0  0 1.0000000   1.00 1.0000000
9      8     Thalassiosira gracilis.labId_10366  3  0  0 1.0000000   1.00 1.0000000
10     9  Thalassiosira lentiginosa.labId_10369  3  0  0 1.0000000   1.00 1.0000000

$macro
$macro$precision
[1] 0.9346154

$macro$recall
[1] 0.825

$macro$F1
[1] 0.8440476

$macro$F1.Sokolova_Lapalme
[1] 0.8763934


$micro
$micro$precision
[1] 0.8974359

$micro$recall
[1] 0.8974359

$micro$F1
[1] 0.8974359


