GitHunt

MUHAMMAD AKMAL

MUHAMMADAKMAL137

Languages

Jupyter Notebook100%

Loading contributions...

Top Repositories

IMDB-Dataset-Classification-using-Pre-trained-Word-Embedding-with-GloVec-6B

In this project, I worked with a small corpus consisting of simple sentences. I tokenized the words using n-grams from the NLTK library and performed word-level and character-level one-hot encoding. Additionally, I utilized the Keras Tokenizer to tokenize the sentences and implemented word embedding using the Embedding layer. For sentiment analysis

2Jupyter Notebook
Pytorch-Training-Pipeline

This code builds a Pipeline training model in PyTorch to classify breast cancer whether positive or negative. It preprocesses the data using standard scaling and label encoding, then trains the model using manual weight updates and binary cross-entropy loss. Finally, it evaluates the model on the test set and prints the accuracy.

1Jupyter Notebook
Pytorch_Training_Pipeline_Using_Dataset_And_Dataloader_Class.ipynb

Binary classification of breast cancer using PyTorch. Used StandardScaler, LabelEncoder, Dataset, DataLoader, custom nn.Module model, BCELoss, and SGD. Focused on implementing a complete training pipeline, not optimizing accuracy.

1Jupyter Notebook
Fashion-MNIST-Classifier-with-PyTorch

This repository contains code to train and evaluate a neural network model on a subset of the Fashion MNIST dataset using PyTorch. The model achieves remarkable accuracy after 100 epochs of training.

1Jupyter Notebook
Optuna-based-Hyperparameter-Optimization-for-Machine-Learning-Models-Static-and-Dynamic-Tuning

This Optuna-based hyperparameter optimization study performs both static and dynamic tuning of hyperparameters for machine learning models (SVM, RandomForest, and GradientBoosting) to maximize accuracy. It tracks and analyzes model performance, displays the best trial results, and compares the average performance of each classifier.

1Jupyter Notebook
CNN-Model-for-Fashion-MNIST-Classification

This project demonstrates the implementation of a Convolutional Neural Network (CNN) using PyTorch, designed to classify fashion items from the Fashion MNIST dataset. The model was trained using GPU acceleration to speed up computation.

1Jupyter Notebook

Repositories

18
MU
MUHAMMADAKMAL137/xiyanghu.github.ioFork

No description provided.

00Updated 5 months ago
MU
MUHAMMADAKMAL137/Pytorch-Training-Pipeline

This code builds a Pipeline training model in PyTorch to classify breast cancer whether positive or negative. It preprocesses the data using standard scaling and label encoding, then trains the model using manual weight updates and binary cross-entropy loss. Finally, it evaluates the model on the test set and prints the accuracy.

Jupyter Notebook10Updated 11 months ago
MU
MUHAMMADAKMAL137/Pytorch_Training_Pipeline_Using_Dataset_And_Dataloader_Class.ipynb

Binary classification of breast cancer using PyTorch. Used StandardScaler, LabelEncoder, Dataset, DataLoader, custom nn.Module model, BCELoss, and SGD. Focused on implementing a complete training pipeline, not optimizing accuracy.

Jupyter Notebook10Updated 11 months ago
ai-healthcarebcelossesbinary-classificationbreast-cancerclassificationdatasetdeep-learninglabelencodermachine-learingnn-modulepreprocessingpytorchsigmoid-functionstandardscaler
MU
MUHAMMADAKMAL137/Fashion-MNIST-Classifier-with-PyTorch

This repository contains code to train and evaluate a neural network model on a subset of the Fashion MNIST dataset using PyTorch. The model achieves remarkable accuracy after 100 epochs of training.

Jupyter Notebook10Updated 11 months ago
accuracyartificial-neural-networkscrossentropylossdataloaderdataset-classdataset-normalizationevaluationfashion-mnist-datasetimage-classificationimage-processingneural-networkpytorchsgd-optimizertraining
MU
MUHAMMADAKMAL137/Optuna-based-Hyperparameter-Optimization-for-Machine-Learning-Models-Static-and-Dynamic-Tuning

This Optuna-based hyperparameter optimization study performs both static and dynamic tuning of hyperparameters for machine learning models (SVM, RandomForest, and GradientBoosting) to maximize accuracy. It tracks and analyzes model performance, displays the best trial results, and compares the average performance of each classifier.

Jupyter Notebook10Updated 11 months ago
dynamic-hypersphere-algorithmgradient-boosting-classifiermachine-learning-algorithmsobjective-function-optimizationoptunarandom-forest-classifiersvm-classifier
MU
MUHAMMADAKMAL137/CNN-Model-for-Fashion-MNIST-Classification

This project demonstrates the implementation of a Convolutional Neural Network (CNN) using PyTorch, designed to classify fashion items from the Fashion MNIST dataset. The model was trained using GPU acceleration to speed up computation.

Jupyter Notebook10Updated 10 months ago
cnn-classificationdeep-learningfashion-mnist-datasetpipelinepytorch
MU
MUHAMMADAKMAL137/Fashion-MNIST-Classification-with-Transfer-Learning-using-Pre-trained-VGG16

This project uses transfer learning with a pre-trained VGG16 model to classify Fashion MNIST images. The convolutional layers are frozen, and a custom classifier is added. The model is fine-tuned using the Adam optimizer and CrossEntropyLoss, with training and evaluation loops running on GPU for efficient processing.

Jupyter Notebook10Updated 10 months ago
cnn-classificationdeep-learningfashion-mnist-datasetgpupretrained-modelstransfer-learningvgg16
MU
MUHAMMADAKMAL137/FashionMNIST-Classification-Using-Transfer-Learning-with-Pretrained-AlexNet

This project applies transfer learning using a pretrained AlexNet model to classify FashionMNIST images. The model was fine-tuned and trained on GPU after necessary preprocessing. It achieved 93.16% accuracy on the test set and 95.87% on the training set.

Jupyter Notebook10Updated 10 months ago
accuracyalexnet-pytorchdeep-neural-networksfashion-mnist-datasetgpupreprocessingpretrained-modelspytor
MU
MUHAMMADAKMAL137/Question-Answering-System-Using-PyTorch-and-Recurrent-Neural-Networks-RNN-

A simple QA model using RNNs to predict answers from custom question-answer pairs. Includes text preprocessing, vocabulary building, and PyTorch training. Ideal for NLP beginners and chatbot development. 🚀 #PyTorch #NLP #RNN #AI

Jupyter Notebook10Updated 10 months ago
deep-learningnatural-language-processingneural-question-answeringnlp-with-pytorchpytorch-rnntext-processing-using-pytorchvocabulary-building
MU
MUHAMMADAKMAL137/GPU-Accelerated-Next-Word-Prediction-Using-LSTM-and-PyTorch

This repository implements a GPU-accelerated next-word prediction model using PyTorch and LSTM. It includes data preprocessing with NLTK, vocabulary creation, training on tokenized text, and generating text predictions, starting from a given input phrase.

Jupyter Notebook10Updated 10 months ago
aideep-learningembeddinggpu-accelerated-nlplanguage-modellstm-neural-networksnatural-language-processingnext-word-predictionnlppredictive-textpytorchrnnsequence-modelingtext-generationtokenization
MU
MUHAMMADAKMAL137/IMDB-Dataset-Classification-using-Pre-trained-Word-Embedding-with-GloVec-6B

In this project, I worked with a small corpus consisting of simple sentences. I tokenized the words using n-grams from the NLTK library and performed word-level and character-level one-hot encoding. Additionally, I utilized the Keras Tokenizer to tokenize the sentences and implemented word embedding using the Embedding layer. For sentiment analysis

Jupyter Notebook20Updated 2 years ago
character-levelcharacter-level-language-modelcorpusngramsone-hot-encodingpre-trained-glove-6bpre-trained-word-embeddingseq2seqword-embeddingsword-levelword-level-language-model
MU
MUHAMMADAKMAL137/-Visualizing-convnet-filters-and-eatmaps-of-class-activation

We utilized the VGG16 model for filter visualization, class activation heatmaps, and the Grad-CAM algorithm. We implemented functions to fetch and manipulate Numpy output values, generate filter visualizations, and create grids of filter response patterns. Through these techniques, we gained insights into the model's learned patter

Jupyter Notebook10Updated 2 years ago
MU
MUHAMMADAKMAL137/CatandDogsWithAugmentation

CatandDogsWithAugmentation

Jupyter Notebook10Updated 2 years ago
MU
MUHAMMADAKMAL137/CNN-in-Five-Steps

No description provided.

Jupyter Notebook10Updated 2 years ago
MU
MUHAMMADAKMAL137/MNIST-Practice

No description provided.

Jupyter Notebook10Updated 2 years ago
MU
MUHAMMADAKMAL137/TensorAndVariable

No description provided.

Jupyter Notebook10Updated 2 years ago
MU
MUHAMMADAKMAL137/Layer-weight-creation-in-build-input_shape-

No description provided.

Jupyter Notebook10Updated 2 years ago
MU
MUHAMMADAKMAL137/Classification-of-MNIST-dataset-with-CNN

No description provided.

Jupyter Notebook10Updated 2 years ago

Gists

Recent Activity