The upcoming Cherenkov Telescope Array (CTA) will dramatically improve the point-source sensitivity compared to the current Imaging Atmospheric Cherenkov Telescopes (IACTs). One of the key science projects of CTA will be a survey of the whole Galactic plane (GPS) using both southern and northern observatories, specifically focusing on the inner galactic region. We extend a deep learning-based image segmentation software pipeline (autosource-id) developed on Fermi-LAT data to detect and classify extended sources for the simulated CTA GPS. Using updated instrument response functions for CTA (Prod5), we test this pipeline on simulated gamma-ray sources lying in the inner galactic region (specifically $0^\circ < l < 20^\circ$, $\left|b\right| < 4^{\circ}$) for energies ranging from 30 GeV to 100 TeV. Dividing the source extensions ranging from $0.03^{\circ}$ to $1^{\circ}$ in three different classes, we find that using a simple and light convolutional neural network achieves $97\%$ global accuracy in separating the extended sources from the point-like sources. The neural net architecture including other data pre-processing codes is available online.