File size: 3,182 Bytes
4bc9607 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
import os
import numpy as np
import torch
import torchvision
from PIL import Image
from pytorch_lightning.callbacks import Callback
from pytorch_lightning.utilities.distributed import rank_zero_only
class ImageLogger(Callback):
def __init__(self, batch_frequency=2000, max_images=4, clamp=True, increase_log_steps=True,
rescale=True, disabled=False, log_on_batch_idx=False, log_first_step=False,
log_images_kwargs=None):
super().__init__()
self.rescale = rescale
self.batch_freq = batch_frequency
self.max_images = max_images
if not increase_log_steps:
self.log_steps = [self.batch_freq]
self.clamp = clamp
self.disabled = disabled
self.log_on_batch_idx = log_on_batch_idx
self.log_images_kwargs = log_images_kwargs if log_images_kwargs else {}
self.log_first_step = log_first_step
@rank_zero_only
def log_local(self, save_dir, split, images, global_step, current_epoch, batch_idx):
root = os.path.join(save_dir, "image_log", split)
for k in images:
grid = torchvision.utils.make_grid(images[k], nrow=4)
if self.rescale:
grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
grid = grid.transpose(0, 1).transpose(1, 2).squeeze(-1)
grid = grid.numpy()
grid = (grid * 255).astype(np.uint8)
filename = "{}_gs-{:06}_e-{:06}_b-{:06}.png".format(k, global_step, current_epoch, batch_idx)
path = os.path.join(root, filename)
os.makedirs(os.path.split(path)[0], exist_ok=True)
Image.fromarray(grid).save(path)
def log_img(self, pl_module, batch, batch_idx, split="train"):
check_idx = batch_idx # if self.log_on_batch_idx else pl_module.global_step
if (self.check_frequency(check_idx) and # batch_idx % self.batch_freq == 0
hasattr(pl_module, "log_images") and
callable(pl_module.log_images) and
self.max_images > 0):
logger = type(pl_module.logger)
is_train = pl_module.training
if is_train:
pl_module.eval()
with torch.no_grad():
images = pl_module.log_images(batch, split=split, **self.log_images_kwargs)
for k in images:
N = min(images[k].shape[0], self.max_images)
images[k] = images[k][:N]
if isinstance(images[k], torch.Tensor):
images[k] = images[k].detach().cpu()
if self.clamp:
images[k] = torch.clamp(images[k], -1., 1.)
self.log_local(pl_module.logger.save_dir, split, images,
pl_module.global_step, pl_module.current_epoch, batch_idx)
if is_train:
pl_module.train()
def check_frequency(self, check_idx):
return check_idx % self.batch_freq == 0
def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
if not self.disabled:
self.log_img(pl_module, batch, batch_idx, split="train")
|