Issue in training - Githubissues

breadbread1984 / LAPGAN-pt

this project implements algorithm LAPGAN for high resolution image generation introduced in paper Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks.

3 stars 0 forks source link

Issue in training #1

Open Krishnapixels opened 9 months ago

Krishnapixels commented 9 months ago

I tried running this code. I am not able to train. This is the error I am receiving---

WARNING:root:Pytorch Functional was renamed to Pytorch Symbolic! WARNING:root:Please import pytorch_symbolic instead! Seed set to 1234 Traceback (most recent call last): File "/content/LAPGAN-pt/train.py", line 39, in main(); File "/content/LAPGAN-pt/train.py", line 16, in main parser = pl.Trainer.add_argparse_args(parser); AttributeError: type object 'Trainer' has no attribute 'add_argparse_args'

sjmikler commented 9 months ago

Install older version of pytorch_lightning. Maybe 1.9.4.

Krishnapixels commented 9 months ago

Thank you. But now it seems to have problem with the data format.