

Project 'VGG16_1FC.Exp11.AonB.100p.masked.run_2':
[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: 1096 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
3        0               Asteromphalus.labId_6835    50          50           0
9        1                 Chaetoceros.labId_6813    65          65           0
5        2 Fragilariopsis kerguelensis.labId_8356   334         334           0
4        3     Fragilariopsis rhombica.labId_8362    45          45           0
7        4                   Nitzschia.labId_6758    60          60           0
10       5             Pseudonitzschia.labId_8364   138         138           0
2        6                Rhizosolenia.labId_6776   122         122           0
6        7           Silicoflagellate.labId_10255   141         141           0
1        8     Thalassiosira gracilis.labId_10366    70          70           0
8        9  Thalassiosira lentiginosa.labId_10369    71          71           0
11      NA                                    Sum  1096        1096           0

Validation: 280 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
3        0               Asteromphalus.labId_6835    13          13           0
6        1                 Chaetoceros.labId_6813    17          17           0
7        2 Fragilariopsis kerguelensis.labId_8356    84          84           0
9        3     Fragilariopsis rhombica.labId_8362    12          12           0
8        4                   Nitzschia.labId_6758    16          16           0
10       5             Pseudonitzschia.labId_8364    35          35           0
1        6                Rhizosolenia.labId_6776    31          31           0
5        7           Silicoflagellate.labId_10255    36          36           0
4        8     Thalassiosira gracilis.labId_10366    18          18           0
2        9  Thalassiosira lentiginosa.labId_10369    18          18           0
11      NA                                    Sum   280         280           0

Test: 1943 samples:
   ClassId                              ClassName Count Count.ANT31 Count.PS103
3        0               Asteromphalus.labId_6835   160           0         160
4        1                 Chaetoceros.labId_6813   352           0         352
9        2 Fragilariopsis kerguelensis.labId_8356   242           0         242
5        3     Fragilariopsis rhombica.labId_8362   215           0         215
10       4                   Nitzschia.labId_6758    42           0          42
1        5             Pseudonitzschia.labId_8364   347           0         347
2        6                Rhizosolenia.labId_6776    74           0          74
6        7           Silicoflagellate.labId_10255   165           0         165
8        8     Thalassiosira gracilis.labId_10366   124           0         124
7        9  Thalassiosira lentiginosa.labId_10369   222           0         222
11      NA                                    Sum  1943           0        1943

Compiling Model:

Starting Training:
Epochs: 50
Batch size: 32


Evaluating trained model for project 'VGG16_1FC.Exp11.AonB.100p.masked.run_2':


Model evaluation:
$confusionMatrix
Confusion Matrix and Statistics

          Reference
Prediction   0   1   2   3   4   5   6   7   8   9
         0 159   0   0   0   0   0   0   0   0   0
         1   0 332   0   0   0   0   0   0   0   0
         2   0   0 242  14   2   3   0   0   0   0
         3   0   9   0 201   0   0   0   0   0   0
         4   0   0   0   0  39   3   0   0   0   0
         5   1   1   0   0   1 341   6   0   0   0
         6   0   3   0   0   0   0  68   0   0   0
         7   0   6   0   0   0   0   0 165   0   0
         8   0   0   0   0   0   0   0   0 123   0
         9   0   1   0   0   0   0   0   0   1 222

Overall Statistics
                                          
               Accuracy : 0.9738          
                 95% CI : (0.9656, 0.9804)
    No Information Rate : 0.1812          
    P-Value [Acc > NIR] : < 2.2e-16       
                                          
                  Kappa : 0.97            
                                          
 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   1.0000   0.9272   0.9571  0.92857   0.9743  0.95775  0.96491  1.00000   0.9911
Recall                0.99375   0.9432   1.0000   0.9349  0.92857   0.9827  0.91892  1.00000  0.99194   1.0000
F1                    0.99687   0.9708   0.9622   0.9459  0.92857   0.9785  0.93793  0.98214  0.99595   0.9955
Prevalence            0.08235   0.1812   0.1245   0.1107  0.02162   0.1786  0.03809  0.08492  0.06382   0.1143
Detection Rate        0.08183   0.1709   0.1245   0.1034  0.02007   0.1755  0.03500  0.08492  0.06330   0.1143
Detection Prevalence  0.08183   0.1709   0.1343   0.1081  0.02162   0.1801  0.03654  0.08801  0.06330   0.1153
Balanced Accuracy     0.99687   0.9716   0.9944   0.9648  0.96350   0.9885  0.95866  0.99831  0.99597   0.9994

$statistics
   class                              className  TP FP FN precision    recall        F1
1      0               Asteromphalus.labId_6835 159  0  1 1.0000000 0.9937500 0.9968652
2      1                 Chaetoceros.labId_6813 332  0 20 1.0000000 0.9431818 0.9707602
3      2 Fragilariopsis kerguelensis.labId_8356 242 19  0 0.9272031 1.0000000 0.9622266
4      3     Fragilariopsis rhombica.labId_8362 201  9 14 0.9571429 0.9348837 0.9458824
5      4                   Nitzschia.labId_6758  39  3  3 0.9285714 0.9285714 0.9285714
6      5             Pseudonitzschia.labId_8364 341  9  6 0.9742857 0.9827089 0.9784792
7      6                Rhizosolenia.labId_6776  68  3  6 0.9577465 0.9189189 0.9379310
8      7           Silicoflagellate.labId_10255 165  6  0 0.9649123 1.0000000 0.9821429
9      8     Thalassiosira gracilis.labId_10366 123  0  1 1.0000000 0.9919355 0.9959514
10     9  Thalassiosira lentiginosa.labId_10369 222  2  0 0.9910714 1.0000000 0.9955157

$macro
$macro$precision
[1] 0.9700933

$macro$recall
[1] 0.969395

$macro$F1
[1] 0.9694326

$macro$F1.Sokolova_Lapalme
[1] 0.9697441


$micro
$micro$precision
[1] 0.9737519

$micro$recall
[1] 0.9737519

$micro$F1
[1] 0.9737519


