Resolving merge conflicts for flake8

scripts/orig_scripts/img2img.py

@@ -1,6 +1,7 @@
 """make variations of input image"""
 
-import argparse, os, sys, glob
+import argparse
+import os
 import PIL
 import torch
 import numpy as np
@@ -12,7 +13,6 @@ from einops import rearrange, repeat
 from torchvision.utils import make_grid
 from torch import autocast
 from contextlib import nullcontext
-import time
 from pytorch_lightning import seed_everything
 
 from ldm.util import instantiate_from_config
@@ -234,7 +234,6 @@ def main():
     with torch.no_grad():
         with precision_scope(device.type):
             with model.ema_scope():
-                tic = time.time()
                 all_samples = list()
                 for n in trange(opt.n_iter, desc="Sampling"):
                     for prompts in tqdm(data, desc="data"):
@@ -279,8 +278,6 @@ def main():
                     Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f"grid-{grid_count:04}.png"))
                     grid_count += 1
 
-                toc = time.time()
-
     print(f"Your samples are ready and waiting for you here: \n{outpath} \n" f" \nEnjoy.")
 
 

scripts/orig_scripts/inpaint.py

@@ -1,4 +1,6 @@
-import argparse, os, sys, glob
+import argparse
+import glob
+import os
 from omegaconf import OmegaConf
 from PIL import Image
 from tqdm import tqdm

scripts/orig_scripts/knn2img.py

@@ -1,13 +1,13 @@
-import argparse, os, sys, glob
-import clip
+import argparse
+import glob
+import os
 import torch
-import torch.nn as nn
 import numpy as np
 from omegaconf import OmegaConf
 from PIL import Image
 from tqdm import tqdm, trange
 from itertools import islice
-from einops import rearrange, repeat
+from einops import rearrange
 from torchvision.utils import make_grid
 import scann
 import time
@@ -390,8 +390,8 @@ if __name__ == "__main__":
                     grid = make_grid(grid, nrow=n_rows)
 
                     # to image
-                    grid = 255.0 * rearrange(grid, "c h w -> h w c").cpu().numpy()
-                    Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f"grid-{grid_count:04}.png"))
+                    grid_np = 255.0 * rearrange(grid, "c h w -> h w c").cpu().numpy()
+                    Image.fromarray(grid_np.astype(np.uint8)).save(os.path.join(outpath, f"grid-{grid_count:04}.png"))
                     grid_count += 1
 
     print(f"Your samples are ready and waiting for you here: \n{outpath} \nEnjoy.")

scripts/orig_scripts/main.py

@@ -1,24 +1,24 @@
-import argparse, os, sys, datetime, glob, importlib, csv
+import argparse
+import datetime
+import glob
+import os
+import sys
+
 import numpy as np
 import time
 import torch
-
 import torchvision
 import pytorch_lightning as pl
 
 from packaging import version
 from omegaconf import OmegaConf
-from torch.utils.data import random_split, DataLoader, Dataset, Subset
+from torch.utils.data import DataLoader, Dataset
 from functools import partial
 from PIL import Image
 
 from pytorch_lightning import seed_everything
 from pytorch_lightning.trainer import Trainer
-from pytorch_lightning.callbacks import (
-    ModelCheckpoint,
-    Callback,
-    LearningRateMonitor,
-)
+from pytorch_lightning.callbacks import Callback
 from pytorch_lightning.utilities.distributed import rank_zero_only
 from pytorch_lightning.utilities import rank_zero_info
 
@@ -651,7 +651,7 @@ if __name__ == "__main__":
         trainer_config["accelerator"] = "auto"
         for k in nondefault_trainer_args(opt):
             trainer_config[k] = getattr(opt, k)
-        if not "gpus" in trainer_config:
+        if "gpus" not in trainer_config:
             del trainer_config["accelerator"]
             cpu = True
         else:
@@ -803,7 +803,7 @@ if __name__ == "__main__":
             trainer_opt.detect_anomaly = False
 
         trainer = Trainer.from_argparse_args(trainer_opt, **trainer_kwargs)
-        trainer.logdir = logdir  ###
+        trainer.logdir = logdir
 
         # data
         config.data.params.train.params.data_root = opt.data_root

scripts/orig_scripts/merge_embeddings.py

@@ -2,7 +2,7 @@ from ldm.modules.encoders.modules import FrozenCLIPEmbedder, BERTEmbedder
 from ldm.modules.embedding_manager import EmbeddingManager
 from ldm.invoke.globals import Globals
 
-import argparse, os
+import argparse
 from functools import partial
 
 import torch
@@ -108,7 +108,7 @@ if __name__ == "__main__":
         manager.load(manager_ckpt)
 
         for placeholder_string in manager.string_to_token_dict:
-            if not placeholder_string in string_to_token_dict:
+            if placeholder_string not in string_to_token_dict:
                 string_to_token_dict[placeholder_string] = manager.string_to_token_dict[placeholder_string]
                 string_to_param_dict[placeholder_string] = manager.string_to_param_dict[placeholder_string]
 

scripts/orig_scripts/sample_diffusion.py

@@ -1,6 +1,12 @@
-import argparse, os, sys, glob, datetime, yaml
-import torch
+import argparse
+import datetime
+import glob
+import os
+import sys
 import time
+import yaml
+
+import torch
 import numpy as np
 from tqdm import trange
 
@@ -10,7 +16,9 @@ from PIL import Image
 from ldm.models.diffusion.ddim import DDIMSampler
 from ldm.util import instantiate_from_config
 
-rescale = lambda x: (x + 1.0) / 2.0
+
+def rescale(x: float) -> float:
+    return (x + 1.0) / 2.0
 
 
 def custom_to_pil(x):
@@ -45,7 +53,7 @@ def logs2pil(logs, keys=["sample"]):
             else:
                 print(f"Unknown format for key {k}. ")
                 img = None
-        except:
+        except Exception:
             img = None
         imgs[k] = img
     return imgs

scripts/orig_scripts/train_searcher.py

@@ -1,4 +1,5 @@
-import os, sys
+import os
+import sys
 import numpy as np
 import scann
 import argparse

scripts/orig_scripts/txt2img.py

@@ -1,4 +1,5 @@
-import argparse, os, sys, glob
+import argparse
+import os
 import torch
 import numpy as np
 from omegaconf import OmegaConf
@@ -7,10 +8,9 @@ from tqdm import tqdm, trange
 from itertools import islice
 from einops import rearrange
 from torchvision.utils import make_grid
-import time
 from pytorch_lightning import seed_everything
 from torch import autocast
-from contextlib import contextmanager, nullcontext
+from contextlib import nullcontext
 
 import k_diffusion as K
 import torch.nn as nn
@@ -251,7 +251,6 @@ def main():
     with torch.no_grad():
         with precision_scope(device.type):
             with model.ema_scope():
-                tic = time.time()
                 all_samples = list()
                 for n in trange(opt.n_iter, desc="Sampling"):
                     for prompts in tqdm(data, desc="data"):
@@ -310,8 +309,6 @@ def main():
                     Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f"grid-{grid_count:04}.png"))
                     grid_count += 1
 
-                toc = time.time()
-
     print(f"Your samples are ready and waiting for you here: \n{outpath} \n" f" \nEnjoy.")