Machine-Learning-Collection VS pytorch-accelerated

def compute_mean_std(dataloader): ''' We assume that the images of the dataloader have the same height and width source: https://github.com/aladdinpersson/Machine-Learning-Collection/blob/master/ML/Pytorch/Basics/pytorch_std_mean.py ''' # var[X] = E[X**2] - E[X]**2 channels_sum, channels_sqrd_sum, num_batches = 0, 0, 0 for batch_images, labels in tqdm(dataloader): # (B,H,W,C) batch_images = batch_images.permute(0,3,4,2,1) channels_sum += torch.mean(batch_images, dim=[0, 1, 2, 3]) channels_sqrd_sum += torch.mean(batch_images ** 2, dim=[0, 1, 2,3]) num_batches += 1 mean = channels_sum / num_batches std = (channels_sqrd_sum / num_batches - mean ** 2) ** 0.5 return mean, std compute_mean_std(dataloader)

I then found Aladdin Persson implementation (which he described in YouTube video). He said that original paper used Dropout, because BatchNorm was not invented at the time, and he wants to use BatchNorm instead. I thought there is no critical difference between these two, and decided to stick up with paper for the sake of learning to implement such things.

I am trying to train a model for NMT on a custom dataset. I found this great tutorial on youtube along with the accompanying repo, but it uses an old version of PyTorch and torchtext. More recent versions of torchtext have removed the Field and BucketIterator classes. I looked for more recent tutorials. The closest thing I could find was this medium post (again with the accompanying code) which worked with a custom dataset for text classification. I tried to replicate the code with my problem and got this far:

with the source code here: Machine-Learning-Collection/ML/Pytorch/GANs/CycleGAN at master · aladdinpersson/Machine-Learning-Collection · GitHub

seq2seq_attention

I followed a tutorial to do a pix2pix GAN network here: https://www.youtube.com/watch?v=SuddDSqGRzg, and the github.

Aladdin Persson

Hello everyone. I am all set up and ready to go. I downloaded the code below (btw, I don't fully understand what it does, lol) and ran it a few times.

Code: https://github.com/aladdinpersson/Machine-Learning-Collection/tree/master/ML/Pytorch/object_detection/YOLOv3

I would love to know your thoughts on PyTorch Lightning vs. other, even more lightweight libraries, if you have the time. PL strikes me as being less idiosyncratic than FastAI, but I'm still not sure whether it would be better in engineering work to go even more lightweight (when I'm not just writing the code myself) -- something that offers up just optimizations and a trainer, a la MosaicML's [Composer](https://github.com/mosaicml/composer) or Chris Hughes's [pytorch-accelerated](https://github.com/Chris-hughes10/pytorch-accelerated) .