

Project 'VGG16_1FC.Exp03.AonA.100p.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: 816 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
10       0               Asteromphalus.labId_6835    37          37           0
5        1                 Chaetoceros.labId_6813    48          48           0
1        2 Fragilariopsis kerguelensis.labId_8356   250         250           0
9        3     Fragilariopsis rhombica.labId_8362    33          33           0
6        4                   Nitzschia.labId_6758    45          45           0
4        5             Pseudonitzschia.labId_8364   103         103           0
8        6                Rhizosolenia.labId_6776    91          91           0
2        7           Silicoflagellate.labId_10255   105         105           0
7        8     Thalassiosira gracilis.labId_10366    52          52           0
3        9  Thalassiosira lentiginosa.labId_10369    52          52           0
11      NA                                    Sum   816         816           0

Validation: 211 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
6        0               Asteromphalus.labId_6835    10          10           0
5        1                 Chaetoceros.labId_6813    13          13           0
1        2 Fragilariopsis kerguelensis.labId_8356    63          63           0
9        3     Fragilariopsis rhombica.labId_8362     9           9           0
4        4                   Nitzschia.labId_6758    12          12           0
3        5             Pseudonitzschia.labId_8364    26          26           0
8        6                Rhizosolenia.labId_6776    23          23           0
2        7           Silicoflagellate.labId_10255    27          27           0
10       8     Thalassiosira gracilis.labId_10366    14          14           0
7        9  Thalassiosira lentiginosa.labId_10369    14          14           0
11      NA                                    Sum   211         211           0

Test: 349 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
7        0               Asteromphalus.labId_6835    16          16           0
8        1                 Chaetoceros.labId_6813    21          21           0
2        2 Fragilariopsis kerguelensis.labId_8356   105         105           0
9        3     Fragilariopsis rhombica.labId_8362    15          15           0
5        4                   Nitzschia.labId_6758    19          19           0
1        5             Pseudonitzschia.labId_8364    44          44           0
6        6                Rhizosolenia.labId_6776    39          39           0
3        7           Silicoflagellate.labId_10255    45          45           0
10       8     Thalassiosira gracilis.labId_10366    22          22           0
4        9  Thalassiosira lentiginosa.labId_10369    23          23           0
11      NA                                    Sum   349         349           0

Compiling Model:

Starting Training:
Epochs: 50
Batch size: 32


Evaluating trained model for project 'VGG16_1FC.Exp03.AonA.100p.masked.fold_1':


Model evaluation:
$confusionMatrix
Confusion Matrix and Statistics

          Reference
Prediction   0   1   2   3   4   5   6   7   8   9
         0  15   0   0   0   0   0   0   0   0   0
         1   1  20   0   0   0   0   1   0   0   0
         2   0   0 104   0   3   0   0   0   0   0
         3   0   0   1  15   0   0   0   0   0   0
         4   0   0   0   0  16   0   0   0   0   0
         5   0   1   0   0   0  44   0   0   0   0
         6   0   0   0   0   0   0  38   0   0   0
         7   0   0   0   0   0   0   0  45   0   0
         8   0   0   0   0   0   0   0   0  22   0
         9   0   0   0   0   0   0   0   0   0  23

Overall Statistics
                                          
               Accuracy : 0.9799          
                 95% CI : (0.9591, 0.9919)
    No Information Rate : 0.3009          
    P-Value [Acc > NIR] : < 2.2e-16       
                                          
                  Kappa : 0.9762          
                                          
 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  0.90909   0.9720  0.93750  1.00000   0.9778   1.0000   1.0000  1.00000   1.0000
Recall                0.93750  0.95238   0.9905  1.00000  0.84211   1.0000   0.9744   1.0000  1.00000   1.0000
F1                    0.96774  0.93023   0.9811  0.96774  0.91429   0.9888   0.9870   1.0000  1.00000   1.0000
Prevalence            0.04585  0.06017   0.3009  0.04298  0.05444   0.1261   0.1117   0.1289  0.06304   0.0659
Detection Rate        0.04298  0.05731   0.2980  0.04298  0.04585   0.1261   0.1089   0.1289  0.06304   0.0659
Detection Prevalence  0.04298  0.06304   0.3066  0.04585  0.04585   0.1289   0.1089   0.1289  0.06304   0.0659
Balanced Accuracy     0.96875  0.97314   0.9891  0.99850  0.92105   0.9984   0.9872   1.0000  1.00000   1.0000

$statistics
   class                              className  TP FP FN precision    recall        F1
1      0               Asteromphalus.labId_6835  15  0  1 1.0000000 0.9375000 0.9677419
2      1                 Chaetoceros.labId_6813  20  2  1 0.9090909 0.9523810 0.9302326
3      2 Fragilariopsis kerguelensis.labId_8356 104  3  1 0.9719626 0.9904762 0.9811321
4      3     Fragilariopsis rhombica.labId_8362  15  1  0 0.9375000 1.0000000 0.9677419
5      4                   Nitzschia.labId_6758  16  0  3 1.0000000 0.8421053 0.9142857
6      5             Pseudonitzschia.labId_8364  44  1  0 0.9777778 1.0000000 0.9887640
7      6                Rhizosolenia.labId_6776  38  0  1 1.0000000 0.9743590 0.9870130
8      7           Silicoflagellate.labId_10255  45  0  0 1.0000000 1.0000000 1.0000000
9      8     Thalassiosira gracilis.labId_10366  22  0  0 1.0000000 1.0000000 1.0000000
10     9  Thalassiosira lentiginosa.labId_10369  23  0  0 1.0000000 1.0000000 1.0000000

$macro
$macro$precision
[1] 0.9796331

$macro$recall
[1] 0.9696821

$macro$F1
[1] 0.9736911

$macro$F1.Sokolova_Lapalme
[1] 0.9746322


$micro
$micro$precision
[1] 0.9799427

$micro$recall
[1] 0.9799427

$micro$F1
[1] 0.9799427


