s444427/Sztuczna_Inteligencja_2020
2
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

Add report

Browse Source
This commit is contained in:
s450026 2020-05-26 21:23:50 +02:00
parent 1202ad849d
commit 16002209bf
4 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

0
Podprojekt-CNN-Maksymilian-Kierski.md Normal file
View File

1
src/SubprojectMaksymilianKierski/Data/LogsIMG/accuracy.svg Normal file
View File

File diff suppressed because one or more lines are too long
Side by Side

After

Width:  |  Height:  |  Size: 30 KiB

1
src/SubprojectMaksymilianKierski/Data/LogsIMG/loss.svg Normal file
View File

File diff suppressed because one or more lines are too long
Side by Side

After

Width:  |  Height:  |  Size: 29 KiB

10
src/SubprojectMaksymilianKierski/PlateRecognition.py
View File

@ -9,7 +9,7 @@ import pickle
# For creating model # For creating model
import tensorflow as tf import tensorflow as tf
from tensorflow.keras.models import Sequential # to use sequential model from tensorflow.keras.models import Sequential # to use sequential model
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, \ from tensorflow.keras.layers import Dense, Activation, Flatten, Conv2D, \
MaxPooling2D # elements which we need to creat our layers MaxPooling2D # elements which we need to creat our layers
# For analysing model # For analysing model
@ -34,8 +34,8 @@ y = [] # label set
layer size | conv layer | Dense layer | layer size | conv layer | Dense layer |
64 | 1 | 0 | loss: 0.0443 - accuracy: 0.9942 - val_loss: 0.3614 - val_accuracy: 0.7692 64 | 1 | 0 | loss: 0.0443 - accuracy: 0.9942 - val_loss: 0.3614 - val_accuracy: 0.7692
64 | 2 | 0 | loss: 0.0931 - accuracy: 0.9625 - val_loss: 0.4772 - val_accuracy: 0.8462 64 | 2 | 0 | loss: 0.0931 - accuracy: 0.9625 - val_loss: 0.4772 - val_accuracy: 0.8462
64 | 3 | 0 | loss: 0.2491 - accuracy: 0.9020 - val_loss: 0.3762 - val_accuracy: 0.7949 64 | 3 | 0 | loss: 0.2491 - accuracy: 0.9020 - val_loss: 0.3762 - val_accuracy: 0.7949 ->
64 | 1 | 1 | loss: 0.0531 - accuracy: 0.9971 - val_loss: 0.4176 - val_accuracy: 0.8205 -> 64 | 1 | 1 | loss: 0.0531 - accuracy: 0.9971 - val_loss: 0.4176 - val_accuracy: 0.8205
64 | 2 | 1 | loss: 0.0644 - accuracy: 0.9798 - val_loss: 0.5606 - val_accuracy: 0.8462 64 | 2 | 1 | loss: 0.0644 - accuracy: 0.9798 - val_loss: 0.5606 - val_accuracy: 0.8462
64 | 3 | 1 | loss: 0.1126 - accuracy: 0.9625 - val_loss: 0.5916 - val_accuracy: 0.8205 64 | 3 | 1 | loss: 0.1126 - accuracy: 0.9625 - val_loss: 0.5916 - val_accuracy: 0.8205
''' '''
@ -103,9 +103,7 @@ def creat_model():
model = Sequential() # initialize our model as a Sequential model model = Sequential() # initialize our model as a Sequential model
model.add(Conv2D(64, (3, 3), model.add(Conv2D(64, (3, 3), input_shape=X.shape[1:])) # first convolution layer 64 neurons (filters cuz it a convolutional layer), checking 3px on 3px, of 50px 50px grey img
input_shape=X.shape[
1:])) # first convolution layer 64 neurons (filters cuz it a convolutional layer), checking 3px on 3px, of 50px 50px grey img
model.add(Activation('relu')) # relu activation function model.add(Activation('relu')) # relu activation function
model.add(MaxPooling2D(pool_size=(2, 2))) # max pooling on 2px on 2px conv2 layer to get the max value model.add(MaxPooling2D(pool_size=(2, 2))) # max pooling on 2px on 2px conv2 layer to get the max value