Pedro Cuenca commited on
Commit
df5e2f0
1 Parent(s): 35406cd

Reorganization: move JAX VQGAN notebook to dev

Browse files

And remove vqgan-jax-encoding-howto.py, which will be simply included
inline in the model card.

{examples → dev/notebooks/vqgan}/JAX_VQGAN_f16_16384_Reconstruction.ipynb RENAMED
File without changes
examples/vqgan-jax-encoding-howto.py DELETED
@@ -1,124 +0,0 @@
1
- #!/usr/bin/env python
2
- # coding: utf-8
3
-
4
- # VQGAN-JAX - Encoding HowTo
5
-
6
- import numpy as np
7
-
8
- # For data loading
9
- import torch
10
- import torchvision.transforms.functional as TF
11
- from torch.utils.data import Dataset, DataLoader
12
- from torchvision.datasets.folder import default_loader
13
- from torchvision.transforms import InterpolationMode
14
-
15
- # For data saving
16
- from pathlib import Path
17
- import pandas as pd
18
- from tqdm import tqdm
19
-
20
- import jax
21
- from jax import pmap
22
-
23
- from vqgan_jax.modeling_flax_vqgan import VQModel
24
-
25
- ## Params and arguments
26
-
27
- image_list = '/sddata/dalle-mini/CC12M/10k.tsv' # List of paths containing images to encode
28
- output_tsv = 'output.tsv' # Encoded results
29
- batch_size = 64
30
- num_workers = 4 # TPU v3-8s have 96 cores, so feel free to increase this number when necessary
31
-
32
- # Load model
33
- model = VQModel.from_pretrained("flax-community/vqgan_f16_16384")
34
-
35
- ## Data Loading.
36
-
37
- # Simple torch Dataset to load images from paths.
38
- # You can use your own pipeline instead.
39
- class ImageDataset(Dataset):
40
- def __init__(self, image_list_path: str, image_size: int, max_items=None):
41
- """
42
- :param image_list_path: Path to a file containing a list of all images. We assume absolute paths for now.
43
- :param image_size: Image size. Source images will be resized and center-cropped.
44
- :max_items: Limit dataset size for debugging
45
- """
46
- self.image_list = pd.read_csv(image_list_path, sep='\t', header=None)
47
- if max_items is not None: self.image_list = self.image_list[:max_items]
48
- self.image_size = image_size
49
-
50
- def __len__(self):
51
- return len(self.image_list)
52
-
53
- def _get_raw_image(self, i):
54
- image_path = Path(self.image_list.iloc[i][0])
55
- return default_loader(image_path)
56
-
57
- def resize_image(self, image):
58
- s = min(image.size)
59
- r = self.image_size / s
60
- s = (round(r * image.size[1]), round(r * image.size[0]))
61
- image = TF.resize(image, s, interpolation=InterpolationMode.LANCZOS)
62
- image = TF.center_crop(image, output_size = 2 * [self.image_size])
63
- image = np.expand_dims(np.array(image), axis=0)
64
- return image
65
-
66
- def __getitem__(self, i):
67
- image = self._get_raw_image(i)
68
- return self.resize_image(image)
69
-
70
- ## Encoding
71
-
72
- # Encoding function to be parallelized with `pmap`
73
- # Note: images have to be square
74
- def encode(model, batch):
75
- _, indices = model.encode(batch)
76
- return indices
77
-
78
- # Alternative: create a batch with num_tpus*batch_size and use `shard` to distribute.
79
- def superbatch_generator(dataloader, num_tpus):
80
- iter_loader = iter(dataloader)
81
- for batch in iter_loader:
82
- superbatch = [batch.squeeze(1)]
83
- try:
84
- for _ in range(num_tpus-1):
85
- batch = next(iter_loader)
86
- if batch is None:
87
- break
88
- # Skip incomplete last batch
89
- if batch.shape[0] == dataloader.batch_size:
90
- superbatch.append(batch.squeeze(1))
91
- except StopIteration:
92
- pass
93
- superbatch = torch.stack(superbatch, axis=0)
94
- yield superbatch
95
-
96
- def encode_dataset(dataset, batch_size=32):
97
- dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=num_workers)
98
- superbatches = superbatch_generator(dataloader, num_tpus=jax.device_count())
99
-
100
- num_tpus = jax.device_count()
101
- dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=num_workers)
102
- superbatches = superbatch_generator(dataloader, num_tpus=num_tpus)
103
-
104
- p_encoder = pmap(lambda batch: encode(model, batch))
105
-
106
- # We save each superbatch to avoid reallocation of buffers as we process them.
107
- # We keep the file open to prevent excessive file seeks.
108
- with open(output_tsv, "w") as file:
109
- iterations = len(dataset) // (batch_size * num_tpus)
110
- for n in tqdm(range(iterations)):
111
- superbatch = next(superbatches)
112
- encoded = p_encoder(superbatch.numpy())
113
- encoded = encoded.reshape(-1, encoded.shape[-1])
114
-
115
- # Extract paths from the dataset, and save paths and encodings (as string) to disk
116
- start_index = n * batch_size * num_tpus
117
- end_index = (n+1) * batch_size * num_tpus
118
- paths = dataset.image_list[start_index:end_index][0].values
119
- encoded_as_string = list(map(lambda item: np.array2string(item, separator=',', max_line_width=50000, formatter={'int':lambda x: str(x)}), encoded))
120
- batch_df = pd.DataFrame.from_dict({"image_file": paths, "encoding": encoded_as_string})
121
- batch_df.to_csv(file, sep='\t', header=(n==0), index=None)
122
-
123
- dataset = ImageDataset(image_list, image_size=256)
124
- encoded_dataset = encode_dataset(dataset, batch_size=batch_size)