batchnormalization

This Problem is based on a Image Data set consisting of different types of weeds, to detect them in crops and fields. I have used Deep Learning Model called CNN(Convolutional Neural Networks) with Dropout, Batch Normalization, ReduceLearning rate on plateau, Early stoppig rounds, and Transposd Convolutional Neural Networks.

𝗖𝘂𝘀𝘁𝗼𝗺-𝗩𝗚𝗚𝟭𝟲 | 𝗣𝘆𝗧𝗼𝗿𝗰𝗵 | 𝗖𝗡𝗡, 𝗕𝗮𝘁𝗰𝗵𝗡𝗼𝗿𝗺, 𝗥𝗲𝗟𝗨, 𝗠𝗮𝘅𝗣𝗼𝗼𝗹, 𝗗𝗿𝗼𝗽𝗼𝘂𝘁, 𝗠𝗡𝗜𝗦𝗧

Code to fold batch norm layer of a DNN model in pytorch

Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning. TL;DR: Fine-tuning only the batch norm affine parameters leads to similar performance as to fine-tuning all of the model parameters

MNIST Digit Prediction using Batch Normalization, Group Normalization, Layer Normalization and L1-L2 Regularizations

PyTorch module FLOPS counter

Cats vs dogs classification using deep learning. Data augmentation and convolutional neural networks.

Built a GAN using TensorFlow to generate handwritten digits from the MNIST dataset. Implemented a custom generator, discriminator, training loop, loss functions, and checkpointing, with image generation and GIF animation to visualize model progress across epochs.

This project aims to develop an advanced DL model using CNN to accurately detect and classify brain tumors from MRI scans.

Step-by-step image classification using Keras—evolving a basic CNN with Batch Norm, Data Augmentation, and Transfer Learning.

Charts and Fake image (OCR on Charts)

Keras Convolutianl Networks

Skin cancer can be broadly classified into two major categories: Melanoma (Malignant) and non-melanoma (Benign). Melanoma is one of the deadliest kinds of cancer. However, the detection of this cancer at an early stage can help in improving the chances of survival.

Fundamentals of Artificial Intelligence and Deep Learning Frameworks

Neural networks

Image classifiaction done on cifar 10 using deep learning (CNN)

LeNet-5 to ResNet-50 implemented from scratch in PyTorch — batch normalization ablation study, residual block comparison, trained on FashionMNIST with 90.37% accuracy

Brain Tumor Detection using EfficientNetB3-based Deep Learning model. The project leverages transfer learning on MRI brain scan images to classify and detect brain tumors with high accuracy. Includes full workflow: data preprocessing, image augmentation, model building, evaluation, and deployment.

Deep learning Simple models