s481825/AI_PROJECT
4
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

neural_network #25

Merged
s481834 merged 12 commits from neural_network into refactor 2024-06-04 13:23:20 +02:00
Conversation 0 Commits 12 Files Changed 14 +15 -5
3 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit de0740d34b - Show all commits

12
Image.py
View File

@ -56,14 +56,24 @@ class Image:
def return_gasStation(self): def return_gasStation(self):
return self.gasStation_image return self.gasStation_image
# losowanie zdjęcia z testowego datasetu bez powtórzeń
imagePathList = []
def getRandomImageFromDataBase(): def getRandomImageFromDataBase():
label = random.choice(neuralnetwork.labels) label = random.choice(neuralnetwork.labels)
folderPath = f"dataset/test/{label}" folderPath = f"dataset/test/{label}"
files = os.listdir(folderPath) files = os.listdir(folderPath)
random_image = random.choice(files) random_image = random.choice(files)
imgPath = os.path.join(folderPath, random_image) imgPath = os.path.join(folderPath, random_image)
while imgPath in imagePathList:
label = random.choice(neuralnetwork.labels)
folderPath = f"dataset/test/{label}"
files = os.listdir(folderPath)
random_image = random.choice(files)
imgPath = os.path.join(folderPath, random_image)
imagePathList.append(imgPath)
image = pygame.image.load(imgPath) image = pygame.image.load(imgPath)
image=pygame.transform.scale(image,(dCon.CUBE_SIZE,dCon.CUBE_SIZE)) image=pygame.transform.scale(image,(dCon.CUBE_SIZE,dCon.CUBE_SIZE))
return image, label, imgPath return image, label, imgPath

2
Tractor.py
View File

@ -198,7 +198,7 @@ class Tractor:
for j in range(initPos[0], dCon.NUM_X): for j in range(initPos[0], dCon.NUM_X):
if self.slot.imagePath != None: if self.slot.imagePath != None:
predictedLabel = nn.predictLabel(self.slot.imagePath, model) predictedLabel = nn.predictLabel(self.slot.imagePath, model)
print(str("Coords: ({:02d}, {:02d})").format(self.slot.x_axis, self.slot.y_axis), "real: ", self.slot.label, "predicted: ", predictedLabel, "correct" if (self.slot.label == predictedLabel) else "incorrect") print(str("Coords: ({:02d}, {:02d})").format(self.slot.x_axis, self.slot.y_axis), "real:", self.slot.label, "predicted:", predictedLabel, "correct" if (self.slot.label == predictedLabel) else "incorrect", 'nawożę za pomocą:', nn.fertilizer[predictedLabel])
self.move_forward(pole, False) self.move_forward(pole, False)
if i % 2 == 0 and i != dCon.NUM_Y - 1: if i % 2 == 0 and i != dCon.NUM_Y - 1:
self.turn_right() self.turn_right()

4
neuralnetwork.py
View File

@ -9,8 +9,8 @@ from PIL import Image
import random import random
imageSize = (128, 128) imageSize = (128, 128)
labels = ['beetroot', 'potato', 'carrot'] labels = ['beetroot', 'carrot', 'potato'] # musi być w kolejności alfabetycznej
labels.sort() fertilizer = {labels[0]: 'kompost', labels[1]: 'saletra amonowa', labels[2]: 'superfosfat'}
torch.manual_seed(42) torch.manual_seed(42)