Convergence failure while training GAN for 128x128 images

Question

thanks for looking at this question!

I attempted to train a simple DCGAN to generate room designs from a dataset of 215 coloured images of size 128x128. My attempt can be summarised as below:

1. Generator: 5 deconvolution layers from (100x1) noise input to (128x128x1) grayscale image output
2. Discriminator: 4 convolution layers from (128x128x1) grayscale image input
3. Optimizer: Adam at learning rate of 0.002 for both Generator and Discriminator
4. Batch size: 21 images/batch
5. Epoch: 100 epochs with 10 batches/epoch

Results: 1. D-loss is close to 0, G-loss is close to 1. After which, I've cut down my discriminator by 2 convolution layers, reduce Adam learning rate to 0.00002, hoping that the discriminator doesn't overpower my generator.

2. Upon (1), D-loss and G-loss hovers around 0.5 - 1.0. However, the generated image still show noise images even after 100 epochs.

Questions:

1. Is there something wrong in terms of how I trained my GAN?

2. How should I modify my approach to successfully train the GAN?

Thank you so much everyone for your help, really looking forward!