

Project 'VGG16_1FC.Exp13.AonB.10p.unmasked.run_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: 106 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
7        0               Asteromphalus.labId_6835     4           4           0
8        1                 Chaetoceros.labId_6813     6           6           0
3        2 Fragilariopsis kerguelensis.labId_8356    33          33           0
10       3     Fragilariopsis rhombica.labId_8362     4           4           0
5        4                   Nitzschia.labId_6758     6           6           0
4        5             Pseudonitzschia.labId_8364    13          13           0
2        6                Rhizosolenia.labId_6776    12          12           0
6        7           Silicoflagellate.labId_10255    14          14           0
9        8     Thalassiosira gracilis.labId_10366     7           7           0
1        9  Thalassiosira lentiginosa.labId_10369     7           7           0
11      NA                                    Sum   106         106           0

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

Test: 193 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
7        0               Asteromphalus.labId_6835    16           0          16
2        1                 Chaetoceros.labId_6813    35           0          35
3        2 Fragilariopsis kerguelensis.labId_8356    24           0          24
8        3     Fragilariopsis rhombica.labId_8362    22           0          22
10       4                   Nitzschia.labId_6758     4           0           4
5        5             Pseudonitzschia.labId_8364    35           0          35
6        6                Rhizosolenia.labId_6776     7           0           7
4        7           Silicoflagellate.labId_10255    16           0          16
1        8     Thalassiosira gracilis.labId_10366    12           0          12
9        9  Thalassiosira lentiginosa.labId_10369    22           0          22
11      NA                                    Sum   193           0         193

Compiling Model:

Starting Training:
Epochs: 50
Batch size: 8


Evaluating trained model for project 'VGG16_1FC.Exp13.AonB.10p.unmasked.run_4':


Model evaluation:
$confusionMatrix
Confusion Matrix and Statistics

          Reference
Prediction  0  1  2  3  4  5  6  7  8  9
         0  9  0  0  0  0  0  0  0  0  0
         1  3 23  0  0  0  2  0  1  0  0
         2  0  2 24  5  1  2  0  0  0  0
         3  1  4  0 17  0  0  0  0  0  0
         4  0  1  0  0  3  4  1  0  0  0
         5  1  2  0  0  0 25  1  0  0  0
         6  0  2  0  0  0  2  5  0  0  0
         7  0  1  0  0  0  0  0 15  0  0
         8  0  0  0  0  0  0  0  0 12  0
         9  2  0  0  0  0  0  0  0  0 22

Overall Statistics
                                          
               Accuracy : 0.8031          
                 95% CI : (0.7399, 0.8567)
    No Information Rate : 0.1813          
    P-Value [Acc > NIR] : < 2.2e-16       
                                          
                  Kappa : 0.776           
                                          
 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   0.7931   0.7059  0.77273  0.33333   0.8621  0.55556  0.93750  1.00000   0.9167
Recall                0.56250   0.6571   1.0000  0.77273  0.75000   0.7143  0.71429  0.93750  1.00000   1.0000
F1                    0.72000   0.7188   0.8276  0.77273  0.46154   0.7813  0.62500  0.93750  1.00000   0.9565
Prevalence            0.08290   0.1813   0.1244  0.11399  0.02073   0.1813  0.03627  0.08290  0.06218   0.1140
Detection Rate        0.04663   0.1192   0.1244  0.08808  0.01554   0.1295  0.02591  0.07772  0.06218   0.1140
Detection Prevalence  0.04663   0.1503   0.1762  0.11399  0.04663   0.1503  0.04663  0.08290  0.06218   0.1244
Balanced Accuracy     0.78125   0.8096   0.9704  0.87174  0.85913   0.8445  0.84639  0.96593  1.00000   0.9942

$statistics
   class                              className TP FP FN precision    recall        F1
1      0               Asteromphalus.labId_6835  9  0  7 1.0000000 0.5625000 0.7200000
2      1                 Chaetoceros.labId_6813 23  6 12 0.7931034 0.6571429 0.7187500
3      2 Fragilariopsis kerguelensis.labId_8356 24 10  0 0.7058824 1.0000000 0.8275862
4      3     Fragilariopsis rhombica.labId_8362 17  5  5 0.7727273 0.7727273 0.7727273
5      4                   Nitzschia.labId_6758  3  6  1 0.3333333 0.7500000 0.4615385
6      5             Pseudonitzschia.labId_8364 25  4 10 0.8620690 0.7142857 0.7812500
7      6                Rhizosolenia.labId_6776  5  4  2 0.5555556 0.7142857 0.6250000
8      7           Silicoflagellate.labId_10255 15  1  1 0.9375000 0.9375000 0.9375000
9      8     Thalassiosira gracilis.labId_10366 12  0  0 1.0000000 1.0000000 1.0000000
10     9  Thalassiosira lentiginosa.labId_10369 22  2  0 0.9166667 1.0000000 0.9565217

$macro
$macro$precision
[1] 0.7876838

$macro$recall
[1] 0.8108442

$macro$F1
[1] 0.7800874

$macro$F1.Sokolova_Lapalme
[1] 0.7990962


$micro
$micro$precision
[1] 0.8031088

$micro$recall
[1] 0.8031088

$micro$F1
[1] 0.8031088


