

Project 'VGG16_1FC.Exp12.BonA.100p.masked.run_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: 1551 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
5        0               Asteromphalus.labId_6835   128           0         128
6        1                 Chaetoceros.labId_6813   281           0         281
1        2 Fragilariopsis kerguelensis.labId_8356   193           0         193
3        3     Fragilariopsis rhombica.labId_8362   172           0         172
10       4                   Nitzschia.labId_6758    33           0          33
4        5             Pseudonitzschia.labId_8364   277           0         277
7        6                Rhizosolenia.labId_6776    59           0          59
8        7           Silicoflagellate.labId_10255   132           0         132
9        8     Thalassiosira gracilis.labId_10366    99           0          99
2        9  Thalassiosira lentiginosa.labId_10369   177           0         177
11      NA                                    Sum  1551           0        1551

Validation: 392 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
2        0               Asteromphalus.labId_6835    32           0          32
6        1                 Chaetoceros.labId_6813    71           0          71
1        2 Fragilariopsis kerguelensis.labId_8356    49           0          49
7        3     Fragilariopsis rhombica.labId_8362    43           0          43
10       4                   Nitzschia.labId_6758     9           0           9
5        5             Pseudonitzschia.labId_8364    70           0          70
9        6                Rhizosolenia.labId_6776    15           0          15
3        7           Silicoflagellate.labId_10255    33           0          33
8        8     Thalassiosira gracilis.labId_10366    25           0          25
4        9  Thalassiosira lentiginosa.labId_10369    45           0          45
11      NA                                    Sum   392           0         392

Test: 1376 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
10       0               Asteromphalus.labId_6835    63          63           0
9        1                 Chaetoceros.labId_6813    82          82           0
1        2 Fragilariopsis kerguelensis.labId_8356   418         418           0
7        3     Fragilariopsis rhombica.labId_8362    57          57           0
8        4                   Nitzschia.labId_6758    76          76           0
2        5             Pseudonitzschia.labId_8364   173         173           0
4        6                Rhizosolenia.labId_6776   153         153           0
6        7           Silicoflagellate.labId_10255   177         177           0
5        8     Thalassiosira gracilis.labId_10366    88          88           0
3        9  Thalassiosira lentiginosa.labId_10369    89          89           0
11      NA                                    Sum  1376        1376           0

Compiling Model:

Starting Training:
Epochs: 50
Batch size: 32


Evaluating trained model for project 'VGG16_1FC.Exp12.BonA.100p.masked.run_1':


Model evaluation:
$confusionMatrix
Confusion Matrix and Statistics

          Reference
Prediction   0   1   2   3   4   5   6   7   8   9
         0  63   0   0   0   0   0   0   0   0   0
         1   0  74   0   0   1   0   1   0   0   0
         2   0   0 415   3   3   1   3   0   0   0
         3   0   0   3  53   1   0   0   0   0   0
         4   0   0   0   1  58   0   0   0   0   0
         5   0   2   0   0   8 171   1   0   0   0
         6   0   6   0   0   5   1 148   0   0   0
         7   0   0   0   0   0   0   0 177   0   0
         8   0   0   0   0   0   0   0   0  88   0
         9   0   0   0   0   0   0   0   0   0  89

Overall Statistics
                                          
               Accuracy : 0.9709          
                 95% CI : (0.9606, 0.9792)
    No Information Rate : 0.3038          
    P-Value [Acc > NIR] : < 2.2e-16       
                                          
                  Kappa : 0.9655          
                                          
 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  0.97368   0.9765  0.92982  0.98305   0.9396   0.9250   1.0000  1.00000  1.00000
Recall                1.00000  0.90244   0.9928  0.92982  0.76316   0.9884   0.9673   1.0000  1.00000  1.00000
F1                    1.00000  0.93671   0.9846  0.92982  0.85926   0.9634   0.9457   1.0000  1.00000  1.00000
Prevalence            0.04578  0.05959   0.3038  0.04142  0.05523   0.1257   0.1112   0.1286  0.06395  0.06468
Detection Rate        0.04578  0.05378   0.3016  0.03852  0.04215   0.1243   0.1076   0.1286  0.06395  0.06468
Detection Prevalence  0.04578  0.05523   0.3089  0.04142  0.04288   0.1323   0.1163   0.1286  0.06395  0.06468
Balanced Accuracy     1.00000  0.95045   0.9912  0.96340  0.88119   0.9896   0.9788   1.0000  1.00000  1.00000

$statistics
   class                              className  TP FP FN precision    recall        F1
1      0               Asteromphalus.labId_6835  63  0  0 1.0000000 1.0000000 1.0000000
2      1                 Chaetoceros.labId_6813  74  2  8 0.9736842 0.9024390 0.9367089
3      2 Fragilariopsis kerguelensis.labId_8356 415 10  3 0.9764706 0.9928230 0.9845789
4      3     Fragilariopsis rhombica.labId_8362  53  4  4 0.9298246 0.9298246 0.9298246
5      4                   Nitzschia.labId_6758  58  1 18 0.9830508 0.7631579 0.8592593
6      5             Pseudonitzschia.labId_8364 171 11  2 0.9395604 0.9884393 0.9633803
7      6                Rhizosolenia.labId_6776 148 12  5 0.9250000 0.9673203 0.9456869
8      7           Silicoflagellate.labId_10255 177  0  0 1.0000000 1.0000000 1.0000000
9      8     Thalassiosira gracilis.labId_10366  88  0  0 1.0000000 1.0000000 1.0000000
10     9  Thalassiosira lentiginosa.labId_10369  89  0  0 1.0000000 1.0000000 1.0000000

$macro
$macro$precision
[1] 0.9727591

$macro$recall
[1] 0.9544004

$macro$F1
[1] 0.9619439

$macro$F1.Sokolova_Lapalme
[1] 0.9634923


$micro
$micro$precision
[1] 0.9709302

$micro$recall
[1] 0.9709302

$micro$F1
[1] 0.9709302


