Image Classification Using Pytorch and Convolutional Neural Network

Подписаться 37 тыс.

Просмотров 19 тыс.

50% 1

This video provides a comprehensive guide on creating an image classification model using PyTorch and Convolutional Neural Networks (CNNs). We dive into the world of deep learning, focusing on the development of a custom dataset to train and evaluate our model. Whether you're a beginner looking to get started with image classification or an enthusiast seeking to enhance your PyTorch and CNN skills, this video is the perfect resource for you.
Github: github.com/Aar...
For queries: You can comment in comment section or you can mail me at aarohisingla1987@gmail.com
#imageclassification #computervision #pytorch #cnn #convolutionalneuralnetworks #convolutionalneuralnetwork

Опубликовано:

29 сен 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 90

@jmxt3 9 месяцев назад

Great video, thanks

@CodeWithAarohi 9 месяцев назад

Glad you liked it!

@yasharazadvatan6673 21 день назад

Hi, thank you for sharing this great content. I have a question; in 19th minute of the video, you create a model and load the trained model. also you create new_model variable. in 20th minute of the video, you write output = model(input_batch) I get confused, where we use new_model?

@karthickkuduva9819 3 месяца назад

Mam i tried with my own cnn model including dropout and batch normalization. And i achieved accuracy of 64% and model predicted output label correctly with image. 64% of accuracy is not bad. How to increase accuracy mam ?.

@CodeWithAarohi 3 месяца назад

1- Increase the amount and diversity of your training data. 2- Increase the number of layers (both convolutional and fully connected layers) to capture more complex patterns. 3- Experiment with different hyperparameters like learning rate, optimizers. 4- Use pre-trained models (e.g., VGG, ResNet, Inception) and fine-tune them on your dataset.

@karthickkuduva9819 3 месяца назад

@@CodeWithAarohi thanks for your guidance mam

@НиколайНовичков-е1э 11 месяцев назад

Thank you!

@CodeWithAarohi 11 месяцев назад

Welcome!

@Mehrdadkh87 11 месяцев назад

Yea

@mohamedragab8644 4 месяца назад

Where is the dataset

@CodeWithAarohi 4 месяца назад

universe.roboflow.com/enrico-garaiman/flowers-y6mda/dataset/7

@mohamedragab8644 4 месяца назад

@@CodeWithAarohi Thank you ❤️

@NabeelBaig-p1y 11 месяцев назад

Where is Dataset?

@NabeelBaig-p1y 11 месяцев назад

Where is Dataset directory?

@adelilyasgoffa2717 11 месяцев назад

Thank you, I sent you a mail you didn't answer me,I need your advice please 🙏 , thank you

@CodeWithAarohi 11 месяцев назад

Let me check

@Sunil-ez1hx 11 месяцев назад

Hello Ma’am Your AI and Data Science content is consistently impressive! Thanks for making complex concepts so accessible. Keep up the great work! 🚀 #ArtificialIntelligence #DataScience #ImpressiveContent 👏👍

@CodeWithAarohi 11 месяцев назад

My pleasure 😊

@felipemunoz6561 10 месяцев назад

where i can find that dataset?, i just found of CNN in his github :(

@CodeWithAarohi 10 месяцев назад

universe.roboflow.com/enrico-garaiman/flowers-y6mda/dataset/7

@MS-yy2dh Месяц назад

Thank for the video. Can I ask - how do you crate the directory structure with just daisies and dandelions in separate folders? The file I have downloaded (from the link you give) has daisy, dandelion, rose, sunflower and tulip, all together.

@CodeWithAarohi Месяц назад

delete rest of the folders

@SagarLekhak 8 месяцев назад

How can someone explain such complex concepts in a very simple way? I adore you.

@CodeWithAarohi 8 месяцев назад

Glad my video is helpful 🙂

@ravindrakarande59 9 месяцев назад

Please share the dataset used in this video

@mainhoontom2176 11 месяцев назад

Very nice Aarohi Mam. Thanks for making complex stuff simple.

@CodeWithAarohi 11 месяцев назад

Most welcome 😊

@harshawithhonor6992 7 месяцев назад

Hello ma'am, could you please provide the source from where I could get the image files to run this project. Also, do you have any citations (references) for this project.

@deepakchaudhary3149 7 месяцев назад

mam if image is of .npy file extension then how to load it?

@saranshtiwari8543 3 месяца назад

x = np.load("x.npy")

@soravsingla8782 11 месяцев назад

Really knowledgeable video & explained in a Very well manner. Thank you

@CodeWithAarohi 11 месяцев назад

Glad it was helpful!

@arnavthakur5409 11 месяцев назад

Keep sharing such an amazing knowledgeable content in form of very easy to learn videos.

@CodeWithAarohi 11 месяцев назад

Thank you, I will

@utkarshtripathi9118 11 месяцев назад

Ossm video well explained

@CodeWithAarohi 11 месяцев назад

Thank you so much

@rainlarh5306 9 месяцев назад

Hi Arohi! Thanks for sharing the knowledge:) I have a qns to clarify but I'm not sure whether would you be able to see my comments. How will the the code understand or how was the datasets being seperated into inputs and labels while running the training loop as shown in your video?

@CodeWithAarohi 9 месяцев назад

This line is responsible for reading labels and images: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}

@Arceus948 6 месяцев назад

hey, i m working on an image classifcation project but i m confused what should be the order of preprocessing the images. is my below order of image prepprocessing correct?? step - 1 -> Resizing to 64x64 (Both Train & Validation dataset) step - 2 ->Splitting dataset into train and validation step - 3 ->Augmentation (Only Train data) step - 4 ->Normalization (Both Train & Validation dataset)

@CodeWithAarohi 6 месяцев назад

Correct

@TekkenGamer7 4 месяца назад

Can I use flatten() instead of Randomhorizontal()

@Sunil-ez1hx 11 месяцев назад

Simple awesome . Thank you

@CodeWithAarohi 11 месяцев назад

Glad you liked it!

@ashimasingla103 10 месяцев назад

Hello Aarohi Your channel is very knowledgeable & helpful for all Artificial Intelligence/ Data Scientist Professionals. Stay blessed & keep sharing such a good content. Your channel really needs more likes & share so to reach maximum AI professionals who can encash from it

@CodeWithAarohi 10 месяцев назад

So nice of you

@josephmyalla3611 13 дней назад

Great, Short and Clear

@CodeWithAarohi 9 дней назад

Thanks!

@arnavthakur5409 11 месяцев назад

Thank you mam for sharing

@CodeWithAarohi 11 месяцев назад

Thanks for liking

@soravsingla8782 11 месяцев назад

Hi Aarohi, your content is excellent and your channel is one of the best Artificial Intelligence channel but still not getting that much of likes which your channel deserves. Hope you succeed #AI #ArtificialIntelligence #DataScience #EducationalContent

@CodeWithAarohi 11 месяцев назад

Thank you so much for your kind words and support! It means a lot to me. 😊🙏

@shanikananayakkara4451 11 месяцев назад

Thank you very much for the amazing knowledge sharing. If you can, please explain how we can use deep unfolding networks for image classification optimisation using a code.

@CodeWithAarohi 11 месяцев назад

Sure I will

@omerkaya2320 11 месяцев назад

Thank you very much. Please make a video that contains an end to end computer vision project even if the project is basic.

@CodeWithAarohi 11 месяцев назад

Sure!

@Sunil-ez1hx 11 месяцев назад

Code with Aarohi is best platform to learn Artificial Intelligence & Data Science #BestChannel #CodeWithAarohi

@arnavthakur5409 11 месяцев назад

Keep sharing such an amazing knowledgeable content in form of very easy to learn videos.

@CodeWithAarohi 11 месяцев назад

Thank you, I will

@shaikhyaqoob9386 5 месяцев назад

how can i get this dataset

@CodeWithAarohi 5 месяцев назад

universe.roboflow.com/search?q=flower%20classification

@karthickkuduva9819 4 месяца назад

thanks for such easy tutorial on image classification mam.... worth watching your channel

@CodeWithAarohi 4 месяца назад

Glad to hear that

@krishnazala8735 6 месяцев назад

can you provide dataset

@andreadotta73 9 месяцев назад

Hello, great video! I wanted to ask why you used model instead of new_model in the line output = model(input_batch)? new_model should have only 2 neurons in the last layer and therefore choose between two solutions, while model still has all the neurons. Am I correct or am I mistaken? Thanks!!

@CodeWithAarohi 8 месяцев назад

Check the cell below "Classification on unseen image". Therewe are loading a pre-trained ResNet-18 model and its saved weights from 'flower_classification_model.pth', then creates a new ResNet-18 model adjusted to classify 2 classes (daisy and dandelion). It copies only the first 2 output units' weights and biases from the loaded model to the final layer of the new model, effectively adapting the pre-trained model for a 2-class problem.

@andreadotta73 8 месяцев назад

Okay, thank you! So, load the model with 1000 final nodes and then load our model which has only 2 outputs. Next, we create a new model and copy only the first 2 weights and biases from the initial model. So, to understand, I could directly load the pre-trained model with the exact number of output units, then load my model and use that@@CodeWithAarohi

@JohnSmith-gu9gl 3 месяца назад

how did you come up with the values: [0.485, 0.456, 0.406] and [0.229, 0.224, 0.225] ?

@DBWorld 2 месяца назад

These values are taken for ImageNet dataset. You need to arrive with your own mean[R,B,G] and std[R,B,G] values for your kind of training dataset.

@JohnSmith-gu9gl 2 месяца назад

@@DBWorld thanks!

@Thejus_tv 28 дней назад

How can i find that? @DBWorld can you explain?

@Ai_Engineer 7 месяцев назад

where i can get the datasets

@CodeWithAarohi 7 месяцев назад

universe.roboflow.com/enrico-garaiman/flowers-y6mda/dataset/7

@commoncats5437 11 месяцев назад

good work.... do more in Gen ai and LLm's

@CodeWithAarohi 11 месяцев назад

Noted!

@imihhdude 7 месяцев назад

Can the code snippet apply to multiple labels

@CodeWithAarohi 7 месяцев назад

Yes

@imihhdude 7 месяцев назад

@@CodeWithAarohi thank you 🫶🏻

@luisaruquipac.381 3 месяца назад

Excellent content! Thank you

@CodeWithAarohi 3 месяца назад

Glad you liked it!

@CodeWithAarohi 3 месяца назад

Thank you!

@dibo1934 7 месяцев назад

very helpful video

@CodeWithAarohi 7 месяцев назад

Glad it was helpful!

@pifordtechnologiespvtltd5698 7 месяцев назад

Really amazing work

@CodeWithAarohi 7 месяцев назад

Thank you so much 😀

@soravsingla6574 11 месяцев назад

Very good video

@CodeWithAarohi 11 месяцев назад

Thanks

@gowthamggp4657 8 месяцев назад

Tq mam

@CodeWithAarohi 8 месяцев назад

welcome!

@nabeelbaig2292 11 месяцев назад

I have a quick question regarding this video, Aarohi. I watched your video and cloned your GitHub repository to train a dataset of approximately 100 bank cheque images. However, I encountered an issue with the model's performance. When I tested it with non-cheque images, it incorrectly classified them as cheques. On the other hand, it also misclassified bank cheque images as something other than cheques. Can you help me understand and address this problem?

@CodeWithAarohi 11 месяцев назад

Imbalanced data can lead to misclassification issues. If you have significantly more cheque images than non-cheque images (or vice versa), it can skew the model's performance. You might need to balance the dataset by oversampling the minority class or undersampling the majority class.