I'm implementing a UNet neural network but I'm having some issues while importing libraries. I found a solution for a couple of them, but I still have a problem with these two imports:

`from tensorflow.keras.optimizers import Adam
#Import "tensorflow.keras.optimizers" could not be resolved(reportMissingImports)

from tensorflow.keras.preprocessing.image import ImageDataGenerator
#Import "tensorflow.keras.preprocessing.image" could not be resolved(reportMissingImports)
`

Any idea?i've tryed some changes but it's still not working

data/k-means.xlsx missing in tutorial71

Does anyone have any idea what could be causing such results?

Predict on the 4th columns

Confusion matrix (I have 8 class) :

i try with another dataset, it always crashed in:

#XGBOOST
import xgboost as xgb
model = xgb.XGBClassifier(tree_method='gpu_hist', gpu_id=0)
model.fit(X_for_training, y_train) #For sklearn no one hot encoding <---- (this part)

i already try with local PC too, there's bug:

AttributeError: 'bool' object has no atribute 'all'

could someone solve my problem please. many thanks

Sir, inspired by your tutorial and other references I tried with HOCR output, but 3 things is pulling me back from final output.

1. Removal of black scattered dust between text
2. Extra thickness of font , it needs to be thinned
3. HOCR output is not generating from multiple TIFF images, i was able to generate as single page wise.
   How do you suggest me on this.

`# Python program to extract text from all the images in a folder

storing the text in corresponding files in a different folder

This is for hocr output, but there is error of getting only 1 page

from PIL import Image
import pytesseract as pt
import os
pt.pytesseract.tesseract_cmd = r'C:\Users\admin\AppData\Local\Programs\Tesseract-OCR\tesseract.exe'

def main():
# path for the folder for getting the raw images
path ="D:\input"

# path for the folder for getting the output
tempPath ="D:\\output\"

# iterating the images inside the folder
for imageName in os.listdir(path):
		
	inputPath = os.path.join(path, imageName)
	img = Image.open(inputPath)

#config =('--oem 3--psm 6')

	# applying ocr using pytesseract for python

#custom_config = r'--oem 3 --psm 6'
#text=pt.image_to_string(img, config=custom_config)

	text = pt.image_to_pdf_or_hocr(img, extension = 'hocr', config = (r'--oem 3 --psm 6'), lang ="eng")

	# for removing the .jpg from the imagePath
	#imagePath = imagePath[0:-4]

	fullTempPath = os.path.join(tempPath, 'time_'+imageName+".hocr")
	print(text)

	# saving the text for every image in a separate .txt file
	file1 = open(fullTempPath, "wb")
	file1.write(text)
	file1.close()

if name == 'main':
main()

`

Hi,
Thank you for sharing this code.

I have two (reference and tested) images of different sizes (H*W). The PSNR and RMSE in the code did not work with different shapes.

Is there a way to assess the two images with different shapes?

Thank you in advanced