Implementing Image Classification with ResNet-18 on Custom Datasets in PyTorch
Assume your data is structured as folows:
data/
├── dog/
│ ├── dog001.jpg
│ └── dog002.jpg
└── cat/
├── cat001.jpg
└── cat002.jpg
First, import necessary modules and prepare the dataset:
import torch
import torchvision
from torchvision import transforms
import torch.nn as nn
import torch.optim as optim
base_path = './data'
prepro ...
Posted on Tue, 20 Oct 2026 16:53:11 +0000 by salasilm
Deepfake Detection Competition Baseline
This document outlines a baseline approach for the Inclusion Global Multimedia Deepfake Detection competition. The competition tasks participants with classifying images to detect deepfakes, using the Area Under the ROC Curve (AUC) as the primary evaluation metric. If AUC scores are tied, True Positive Rate at a False Positive Rate of 1E-3 (TPR ...
Posted on Tue, 29 Sep 2026 16:51:38 +0000 by MicahCarrick
Fine-Tuning ResNet for Hotdog Image Classification Using Transfer Learning
Steps
Below we introduce fine‑tuning, a common technique in transfer learning. As illustrated in the following diagram, fine‑tuning consists of four steps.
Pre‑train a neural network model (the source model) on a source dataset, e.g., ImageNet.
Create a new neural network (the target model). It replicates all model design and parameters from t ...
Posted on Fri, 12 Jun 2026 17:03:14 +0000 by aniket_dj