

Project 'VGG16_1FC.Exp02.BonB.100p.unmasked.fold_4':
[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: 1160 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
8        0               Asteromphalus.labId_6835    96           0          96
4        1                 Chaetoceros.labId_6813   211           0         211
5        2 Fragilariopsis kerguelensis.labId_8356   144           0         144
1        3     Fragilariopsis rhombica.labId_8362   128           0         128
10       4                   Nitzschia.labId_6758    24           0          24
2        5             Pseudonitzschia.labId_8364   208           0         208
9        6                Rhizosolenia.labId_6776    44           0          44
7        7           Silicoflagellate.labId_10255    99           0          99
3        8     Thalassiosira gracilis.labId_10366    74           0          74
6        9  Thalassiosira lentiginosa.labId_10369   132           0         132
11      NA                                    Sum  1160           0        1160

Validation: 295 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
4        0               Asteromphalus.labId_6835    24           0          24
3        1                 Chaetoceros.labId_6813    53           0          53
2        2 Fragilariopsis kerguelensis.labId_8356    37           0          37
1        3     Fragilariopsis rhombica.labId_8362    33           0          33
9        4                   Nitzschia.labId_6758     7           0           7
5        5             Pseudonitzschia.labId_8364    52           0          52
6        6                Rhizosolenia.labId_6776    11           0          11
10       7           Silicoflagellate.labId_10255    25           0          25
7        8     Thalassiosira gracilis.labId_10366    19           0          19
8        9  Thalassiosira lentiginosa.labId_10369    34           0          34
11      NA                                    Sum   295           0         295

Test: 488 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
5        0               Asteromphalus.labId_6835    40           0          40
4        1                 Chaetoceros.labId_6813    88           0          88
2        2 Fragilariopsis kerguelensis.labId_8356    61           0          61
7        3     Fragilariopsis rhombica.labId_8362    54           0          54
10       4                   Nitzschia.labId_6758    11           0          11
8        5             Pseudonitzschia.labId_8364    87           0          87
9        6                Rhizosolenia.labId_6776    19           0          19
6        7           Silicoflagellate.labId_10255    41           0          41
1        8     Thalassiosira gracilis.labId_10366    31           0          31
3        9  Thalassiosira lentiginosa.labId_10369    56           0          56
11      NA                                    Sum   488           0         488

Compiling Model:

Starting Training:
Epochs: 50
Batch size: 32


Evaluating trained model for project 'VGG16_1FC.Exp02.BonB.100p.unmasked.fold_4':


Model evaluation:
$confusionMatrix
Confusion Matrix and Statistics

          Reference
Prediction  0  1  2  3  4  5  6  7  8  9
         0 39  0  0  0  0  0  0  0  0  0
         1  0 88  0  0  1  1  0  0  0  0
         2  0  0 59  0  0  0  0  0  0  0
         3  0  0  2 54  0  0  0  0  0  0
         4  0  0  0  0 10  0  0  0  0  0
         5  1  0  0  0  0 86  0  0  0  0
         6  0  0  0  0  0  0 19  0  0  0
         7  0  0  0  0  0  0  0 41  0  0
         8  0  0  0  0  0  0  0  0 30  0
         9  0  0  0  0  0  0  0  0  1 56

Overall Statistics
                                          
               Accuracy : 0.9877          
                 95% CI : (0.9734, 0.9955)
    No Information Rate : 0.1803          
    P-Value [Acc > NIR] : < 2.2e-16       
                                          
                  Kappa : 0.9859          
                                          
 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   0.9778   1.0000   0.9643  1.00000   0.9885  1.00000  1.00000  1.00000   0.9825
Recall                0.97500   1.0000   0.9672   1.0000  0.90909   0.9885  1.00000  1.00000  0.96774   1.0000
F1                    0.98734   0.9888   0.9833   0.9818  0.95238   0.9885  1.00000  1.00000  0.98361   0.9912
Prevalence            0.08197   0.1803   0.1250   0.1107  0.02254   0.1783  0.03893  0.08402  0.06352   0.1148
Detection Rate        0.07992   0.1803   0.1209   0.1107  0.02049   0.1762  0.03893  0.08402  0.06148   0.1148
Detection Prevalence  0.07992   0.1844   0.1209   0.1148  0.02049   0.1783  0.03893  0.08402  0.06148   0.1168
Balanced Accuracy     0.98750   0.9975   0.9836   0.9977  0.95455   0.9930  1.00000  1.00000  0.98387   0.9988

$statistics
   class                              className TP FP FN precision    recall        F1
1      0               Asteromphalus.labId_6835 39  0  1 1.0000000 0.9750000 0.9873418
2      1                 Chaetoceros.labId_6813 88  2  0 0.9777778 1.0000000 0.9887640
3      2 Fragilariopsis kerguelensis.labId_8356 59  0  2 1.0000000 0.9672131 0.9833333
4      3     Fragilariopsis rhombica.labId_8362 54  2  0 0.9642857 1.0000000 0.9818182
5      4                   Nitzschia.labId_6758 10  0  1 1.0000000 0.9090909 0.9523810
6      5             Pseudonitzschia.labId_8364 86  1  1 0.9885057 0.9885057 0.9885057
7      6                Rhizosolenia.labId_6776 19  0  0 1.0000000 1.0000000 1.0000000
8      7           Silicoflagellate.labId_10255 41  0  0 1.0000000 1.0000000 1.0000000
9      8     Thalassiosira gracilis.labId_10366 30  0  1 1.0000000 0.9677419 0.9836066
10     9  Thalassiosira lentiginosa.labId_10369 56  1  0 0.9824561 1.0000000 0.9911504

$macro
$macro$precision
[1] 0.9913025

$macro$recall
[1] 0.9807552

$macro$F1
[1] 0.9856901

$macro$F1.Sokolova_Lapalme
[1] 0.9860006


$micro
$micro$precision
[1] 0.9877049

$micro$recall
[1] 0.9877049

$micro$F1
[1] 0.9877049


