Closed manishh12 closed 1 month ago
Our team will soon review your PR. Thanks @manishh12 :)
@abhisheks008 Due to resource constraints, including limited GPU allocation, frequent runtime disconnects across multiple accounts, and the substantial size of the dataset, I could only implement two models: CNN and BiLSTM. Additionally, I was only able to train these models for a limited number of epochs.
@abhisheks008 Due to resource constraints, including limited GPU allocation, frequent runtime disconnects across multiple accounts, and the substantial size of the dataset, I could only implement two models: CNN and BiLSTM. Additionally, I was only able to train these models for a limited number of epochs.
Any other approach for this project?
@abhisheks008 Due to resource constraints, including limited GPU allocation, frequent runtime disconnects across multiple accounts, and the substantial size of the dataset, I could only implement two models: CNN and BiLSTM. Additionally, I was only able to train these models for a limited number of epochs.
Any other approach for this project?
Yes, there are algorithms that I know of, but they are machine learning algorithms like support vector machine (SVM) or multinomial naive Bayes. If you want, I can implement one of these algorithms.
Go ahead with those models @manishh12
Go ahead with those models @manishh12
@abhisheks008 I've implemented the MNB model and updated the readme. Please review it.
@manishh12 the project folder name should be Website Classification
, no underscore will be there.
@manishh12 the project folder name should be
Website Classification
, no underscore will be there.
@abhisheks008 Kindly Review it.
@manishh12
Images are not visible.
Images are not visible.
@abhisheks008 Sorry, I forgot to update the link after renaming. It's now displaying correctly. Please review it.
Pull Request for DL-Simplified 💡
Issue Title : Website Classification
JWOC Participant
) GSSOC'24Closes: #606 #627
Describe the add-ons or changes you've made 📃
The aim is to classify URLs into predefined categories such as adult content, arts, business, computers, games, health, home, kids, news, recreation, reference, science, shopping, society, or sports. The project involves preprocessing the dataset, visualizing the distribution of categories, training the models, and evaluating their performance.
Implemented the CNN model architecture, including embedding, convolutional, max pooling, flatten, dropout, and dense layers. Trained the CNN model using the provided dataset and evaluated its performance.
Plotted the training and validation loss values as well as the training and validation accuracy values for the CNN model.
Defined the BiLSTM model architecture, consisting of embedding, bidirectional LSTM, and dense layers.
Compiled and trained the BiLSTM model on the dataset.
Generated plots showing the accuracy and loss curves for the BiLSTM model.
The modifications include adding detailed descriptions of the CNN and BiLSTM model architectures, training the models, evaluating their performance, and visualizing the training progress through loss and accuracy plots. Additionally, explanations were provided for training the models for fewer epochs due to resource constraints, which may affect the achieved accuracy.
What sort of change have you made:
How Has This Been Tested? ⚙️
Describe how it has been tested Describe how have you verified the changes made
Checklist: ☑️