Train Neural Network by loading your images |TensorFlow, CNN, Keras tutorial

Very helpfull tutorial. I have some questions though. Shouldnt all the images of the dataset be the same dimensions before we use them? how can i create a confusion matrix?

How to create bounding box with this tutorial sir? Dont use tensorflow model deeplearning. Use our coding

Bro can you tell me to use folder name as an output without using if condition

dont know how testing folder become test folder? and do i have to copy images in all three folders? please ans

this tutorial is really good. thank you so much

Thank you very much sir, you explained step by step. but I have problem in last step. how to accept sub directory path and select both folder data set. please reply me. Thank you.

The best video ever for a person who studies deep learning and cnn ❤😍🔥

Thanks

please do tutorial of this with tarfile. i have tar file image dataset and having trouble opening it

My assignment requires me to show a plant image to camera and it should say which type of image it is out of 4 classes, how can i modify this code?

thanks bro huge help

Thanks a lot for the amazing video. I tried it out for healthy and diseased plants, it looks like it wrongly identified few. Should i put them back in training folder and re-run everything again? Please suggest.

Hi what's the content of other 2 folders? The same pictures for train folder?

Hi
The accuracy of the sample code is not acceptable if you check it with real images!
With this number of images and these layers, the code cannot recognize happy faces.
We need more images, some preprocessing, combining other image processing techniques to receive better result, and again with all these extra efforts, the accuracy could not be high!
Please do not show 100% accuracy as the result for more followers.
Most of people do not check code with real samples to see the accuracy, and based on the accurate result that you show, they evaluate the ability of CCN better than reality, and they do not spend time to read deeply and learn essential elements related to image processing.
because of that, we face many research papers that claim the suggested algorithm is like a wizard.
But in practice, it is a trash.

Hi, excellent tut, but I want to ask a stupid question, do I need to train or test the network using the same person's face photo? thanks

always the low quality videos that are the best out there

Very useful and great job, thanks you so much

what if I have 4 classes? do I replicate the code?

Thx, this is what i looking for.

Thank you so much for this video. Cannot appreciate enough!

Sir I am getting problem in the last cell while I am running the model for testing dataset it is throwing error what should I do?

Hi sir plz explain how you did load image in juipoter sir i need your number plz give me i want more information about AI

Amazing !! True life saviour. I was looking for exactly the same.

I don't know Image processing but my project guide has forced me take building boundary refinement for remote sensing images has major project. I can anyone familiar with this guide me to complete my project.

Supperb 👍

can you share us the github repo or something please

Getting error logits and label must be same shape

How to learn machine learning.
1. watch theory lecture from ocw or other college website
2. Read blogs and understand maths.
3. Watch Indian guy doing demo with simple explanations.

Pls bro I want source code of this project pls send me

I get 'PermissionError: [Errno 13] Permission denied' when I try to test the model with the data in my test directory. How can I rectify it?

thanks, this helped me!

When i code it in google collab there is an error, why is this happen sir?
it said:
AttributeError: module 'keras.preprocessing.image' has no attribute 'img_to_array'
(error while showing image)

Amazing job! Thank you so much for that

In model fit i am getting an error

Thank you for the amazing tutorial!
May I ask something? why we have to rescale the RGB image from 0-255 to 0-1?
thanks for anyones's answer

I need documentation of this project does anyone have it.!

While running cell 27 we get an error saying no permission to file
CODE:file = open("Computer-vision/basedata/testing", "r")
file.close()
dir_path = 'Computer-vision/basedata/testing'

for i in os.listdir(dir_path):
img = image.load_img(dir_path+'/'+ i,target_size=(200,200))
plt.imshow(img)
plt.show()

X = image.img_to_array(img)
X = np.expand_dims(X,axis =0)
images = np.vstack([X])
val = model.predit(images)
if val == 0:
print("apple")
else:
print("carrot")

PermissionError: [Errno 13] Permission denied: 'Computer-vision/basedata/testing/apple'

i have named test as tesing file how can i fix this

I have my 3 files saved in a Project folder on my desktop and the path I insert (very beginning step) does not work.
What am I doing wrong? I am working in google collab and Project file is on my computer.

great tutorial, could you kindly show how to display the results with a confusion matrix?

Thanks.

Exactly what I was looking for. Wonderful video and well explained. Thank You ❤️❤️❤️

Thank You bro. After building 3 models I forgot the most basic thing, prediction on single random image file. Your video solved my issue. Much love from my side.

Sir How to calculate its total accuracy of training data and testing data

Thank you so much

suggestion: improve your video quality.

InvalidArgumentError: Graph execution error: in model_fit line.. how to resolve?

In second code i am getting error sir

Hy, how hours do we need to trean a model like that? Thanks