Jebb

We're on the same page on this one. I didn't notice this thread existed and created my own. nevertheless I'm referencing my thread for merge later. My thread #153

Or I'm being dumb realizing VGG was built and compiled only for 3 channels? 😂😂😂

I guess I'll just resort to converting images to grayscale literally. Then fill in inputs as RGB; this way I have uniform inputs. Can't wait to see the outcome. Leaving...

Tweaked iterator to override `load_img` to load images as grayscale. Then verified changes by printing shape of loaded data. Reverted the rest of the changes back to original. Currently training...

Training was completed. Although working, I'm not getting my desired results. I noticed color still was a heavy factor for prediction. currently looking for ways for the model to disregard...

It seems so. I'm really going super slow at the moment. The sampling process easily exhausts my resources. I only have 16GB ram. I'm still researching the feasibility of VGG...

I also wish to ask what's the most ideal number of image per class? I have more than 10 classes. each having a mix of 40~50 images. Not quite enough...

Interesting! I'll give that a shot after I exhaust myself on VGG. Thankfully Keras made things easier with the applied networks. Thanks Akarsh!

When you say "50 triplets per query image" does that mean increasing the num_pos_images and num_neg_images in tripletSampler.py? such that parameters look like the following: `python tripletSampler.py --input_directory data --output_directory...

That's noted. Thanks Akarsh! I'll be updating soon.