flaxdiff 0.1.12__py3-none-any.whl → 0.1.14__py3-none-any.whl

flaxdiff/data/__init__.py

@@ -0,0 +1 @@
+from .online_loader import OnlineStreamingDataLoader

flaxdiff/data/online_loader.py

@@ -0,0 +1,208 @@
+import multiprocessing
+import threading
+from multiprocessing import Queue
+# from arrayqueues.shared_arrays import ArrayQueue
+# from faster_fifo import Queue
+import time
+import albumentations as A
+import queue
+import cv2
+from functools import partial
+from typing import Any, Dict, List, Tuple
+
+import numpy as np
+from functools import partial
+
+from datasets import load_dataset, concatenate_datasets, Dataset
+from datasets.utils.file_utils import get_datasets_user_agent
+from concurrent.futures import ThreadPoolExecutor
+import io
+import urllib
+
+import PIL.Image
+import cv2
+
+USER_AGENT = get_datasets_user_agent()
+
+data_queue = Queue(16*2000)
+error_queue = Queue(16*2000)
+
+
+def fetch_single_image(image_url, timeout=None, retries=0):
+    for _ in range(retries + 1):
+        try:
+            request = urllib.request.Request(
+                image_url,
+                data=None,
+                headers={"user-agent": USER_AGENT},
+            )
+            with urllib.request.urlopen(request, timeout=timeout) as req:
+                image = PIL.Image.open(io.BytesIO(req.read()))
+            break
+        except Exception:
+            image = None
+    return image
+
+def map_sample(
+    url, caption, 
+    image_shape=(256, 256),
+    upscale_interpolation=cv2.INTER_LANCZOS4,
+    downscale_interpolation=cv2.INTER_AREA,
+):
+    try:
+        image = fetch_single_image(url, timeout=15, retries=3)  # Assuming fetch_single_image is defined elsewhere
+        if image is None:
+            return
+        
+        image = np.array(image)
+        original_height, original_width = image.shape[:2]
+        # check if the image is too small
+        if min(original_height, original_width) < min(image_shape):
+            return
+        # check if wrong aspect ratio
+        if max(original_height, original_width) / min(original_height, original_width) > 2:
+            return
+        # check if the variance is too low
+        if np.std(image) < 1e-4:
+            return
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+        downscale = max(original_width, original_height) > max(image_shape)
+        interpolation = downscale_interpolation if downscale else upscale_interpolation
+        image = A.longest_max_size(image, max(image_shape), interpolation=interpolation)
+        image = A.pad(
+            image,
+            min_height=image_shape[0],
+            min_width=image_shape[1],
+            border_mode=cv2.BORDER_CONSTANT,
+            value=[255, 255, 255],
+        )
+        data_queue.put({
+            "url": url,
+            "caption": caption,
+            "image": image,
+            "original_height": original_height,
+            "original_width": original_width,
+        })
+    except Exception as e:
+        error_queue.put({
+            "url": url,
+            "caption": caption,
+            "error": str(e)
+        })
+        
+def map_batch(batch, num_threads=256, image_shape=(256, 256), timeout=None, retries=0):
+    with ThreadPoolExecutor(max_workers=num_threads) as executor:
+        executor.map(map_sample, batch["url"], batch['caption'], image_shape=image_shape, timeout=timeout, retries=retries)
+    
+def parallel_image_loader(dataset: Dataset, num_workers: int = 8, image_shape=(256, 256), num_threads=256):
+    map_batch_fn = partial(map_batch, num_threads=num_threads, image_shape=image_shape)
+    shard_len = len(dataset) // num_workers
+    print(f"Local Shard lengths: {shard_len}")
+    with multiprocessing.Pool(num_workers) as pool:
+        iteration = 0
+        while True:
+            # Repeat forever
+            dataset = dataset.shuffle(seed=iteration)
+            shards = [dataset[i*shard_len:(i+1)*shard_len] for i in range(num_workers)]
+            pool.map(map_batch_fn, shards)
+            iteration += 1
+            
+class ImageBatchIterator:
+    def __init__(self, dataset: Dataset, batch_size: int = 64, image_shape=(256, 256), num_workers: int = 8, num_threads=256):
+        self.dataset = dataset
+        self.num_workers = num_workers
+        self.batch_size = batch_size
+        loader = partial(parallel_image_loader, num_threads=num_threads, image_shape=image_shape, num_workers=num_workers)
+        self.thread = threading.Thread(target=loader, args=(dataset))
+        self.thread.start()
+        
+    def __iter__(self):
+        return self
+    
+    def __next__(self):
+        def fetcher(_):
+            return data_queue.get()
+        with ThreadPoolExecutor(max_workers=self.batch_size) as executor:
+            batch = list(executor.map(fetcher, range(self.batch_size)))
+        return batch
+    
+    def __del__(self):
+        self.thread.join()
+        
+    def __len__(self):
+        return len(self.dataset) // self.batch_size
+    
+def default_collate(batch):
+    urls = [sample["url"] for sample in batch]
+    captions = [sample["caption"] for sample in batch]
+    images = np.stack([sample["image"] for sample in batch], axis=0)
+    return {
+        "url": urls,
+        "caption": captions,
+        "image": images,
+    }
+    
+def dataMapper(map: Dict[str, Any]):
+    def _map(sample) -> Dict[str, Any]:
+        return {
+            "url": sample[map["url"]],
+            "caption": sample[map["caption"]],
+        }
+    return _map
+
+class OnlineStreamingDataLoader():
+    def __init__(
+        self, 
+        dataset, 
+        batch_size=64, 
+        image_shape=(256, 256),
+        num_workers=16, 
+        num_threads=512,
+        default_split="all",
+        pre_map_maker=dataMapper, 
+        pre_map_def={
+            "url": "URL",
+            "caption": "TEXT",
+        },
+        global_process_count=1,
+        global_process_index=0,
+        prefetch=1000,
+        collate_fn=default_collate,
+    ):
+        if isinstance(dataset, str):
+            dataset_path = dataset
+            print("Loading dataset from path")
+            dataset = load_dataset(dataset_path, split=default_split)
+        elif isinstance(dataset, list):
+            if isinstance(dataset[0], str):
+                print("Loading multiple datasets from paths")
+                dataset = [load_dataset(dataset_path, split=default_split) for dataset_path in dataset]
+            else:
+                print("Concatenating multiple datasets")
+                dataset = concatenate_datasets(dataset)
+        dataset = dataset.map(pre_map_maker(pre_map_def))
+        self.dataset = dataset.shard(num_shards=global_process_count, index=global_process_index)
+        print(f"Dataset length: {len(dataset)}")
+        self.iterator = ImageBatchIterator(self.dataset, image_shape=image_shape, num_workers=num_workers, batch_size=batch_size, num_threads=num_threads)
+        self.collate_fn = collate_fn
+        
+        # Launch a thread to load batches in the background
+        self.batch_queue = queue.Queue(prefetch)
+        
+        def batch_loader():
+            for batch in self.iterator:
+                self.batch_queue.put(batch)
+        
+        self.loader_thread = threading.Thread(target=batch_loader)
+        self.loader_thread.start()
+        
+    def __iter__(self):
+        return self
+    
+    def __next__(self):
+        return self.collate_fn(self.batch_queue.get())
+        # return self.collate_fn(next(self.iterator))
+        
+    def __len__(self):
+        return len(self.dataset) // self.batch_size
+    

flaxdiff/models/autoencoder/diffusers.py

@@ -11,15 +11,15 @@ All credits for the model go to the developers of Stable Diffusion VAE and all c
 """
 
 class StableDiffusionVAE(AutoEncoder):
-    def __init__(self, modelname = "CompVis/stable-diffusion-v1-4"):
+    def __init__(self, modelname = "CompVis/stable-diffusion-v1-4", revision="bf16", dtype=jnp.bfloat16):
         
         from diffusers.models.vae_flax import FlaxEncoder, FlaxDecoder
         from diffusers import FlaxStableDiffusionPipeline
         
         pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
             modelname,
-            revision="bf16",
-            dtype=jnp.bfloat16,
+            revision=revision,
+            dtype=dtype,
         )
         
         vae = pipeline.vae

{flaxdiff-0.1.12.dist-info → flaxdiff-0.1.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flaxdiff
-Version: 0.1.12
+Version: 0.1.14
 Summary: A versatile and easy to understand Diffusion library
 Author: Ashish Kumar Singh
 Author-email: ashishkmr472@gmail.com

{flaxdiff-0.1.12.dist-info → flaxdiff-0.1.14.dist-info}/RECORD

@@ -1,5 +1,7 @@
 flaxdiff/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 flaxdiff/utils.py,sha256=B0GcHlzlVYDNEIdh2v5qmP4u0neIT-FqexNohuyuCvg,2452
+flaxdiff/data/__init__.py,sha256=PM3PkHihyohT5SHVYKc8vQ4IeVfGPpCktkSVwvqMjQ4,52
+flaxdiff/data/online_loader.py,sha256=IjCVdeq18lF71eLX8RplJLezjKASO1cSFVe2GSYkLQ8,7283
 flaxdiff/models/__init__.py,sha256=FAivVYXxM2JrCFIXf-C3374RB2Hth25dBrzOeNFhH1U,26
 flaxdiff/models/attention.py,sha256=ZbDGIb5Q6FRqJ6qRY660cqw4WvF9IwCnhEuYdTpLPdM,13023
 flaxdiff/models/common.py,sha256=fd-Fl0VCNEBjijHNwGBqYL5VvXe9u0347h25czNTmRw,10780
@@ -8,7 +10,7 @@ flaxdiff/models/simple_unet.py,sha256=h1o9mQlLJy7Ec8Pz_O5miRbAyUaM5UNhSs-oXzpQvZ
 flaxdiff/models/simple_vit.py,sha256=xD23i1b7WEvoH4tUMsLyCe9ebDcv-PpaV0Nso38Jlb8,3887
 flaxdiff/models/autoencoder/__init__.py,sha256=qY-7MldZpsfkF-_T2LqlRK7VHbqfmosz0NmvzDlBkOk,78
 flaxdiff/models/autoencoder/autoencoder.py,sha256=27_hYl0yXAdH9Mx4Xu9J79mSNo-FEKr9SxhVaS3ffn4,591
-flaxdiff/models/autoencoder/diffusers.py,sha256=l4teVksXd9XCCQWcVn9eB820xJyLT8hpg1CXQ_aHZ6M,3611
+flaxdiff/models/autoencoder/diffusers.py,sha256=JHeFLCxiHhu-QHwhKiCuKsQJn4AZumquiuxgZkiYGQ0,3643
 flaxdiff/models/autoencoder/simple_autoenc.py,sha256=UXHPgDmwGTnv3Uts6Zj3p9R9nJXnEiEXbllgarwDfXM,805
 flaxdiff/predictors/__init__.py,sha256=SKkYYRF9Wfgk2zhtZw4vCXOdOeRlrm2Mk6cvuaEvAzc,4403
 flaxdiff/samplers/__init__.py,sha256=_S-9TwDeshrI0VmapV-J2hqjTByOa0-oOeUs_IdovjU,285
@@ -32,7 +34,7 @@ flaxdiff/trainer/__init__.py,sha256=T-vUVq4zHcMK6kpCsG4Gu8vn71q6lZD-lg-Ul7yKfEk,
 flaxdiff/trainer/autoencoder_trainer.py,sha256=al7AsZ7yeDMEiDD-gbcXf0ADq_xfk1VMxvg24GfA-XQ,7008
 flaxdiff/trainer/diffusion_trainer.py,sha256=wKkg63DWZjx2MoM3VQNCDIr40rWN8fUGxH9jWWxfZao,9373
 flaxdiff/trainer/simple_trainer.py,sha256=Z77zRS5viJpd2Mpl6sonJk5WcnEWi2Cd4gl4u5tIX2M,18206
-flaxdiff-0.1.12.dist-info/METADATA,sha256=s3rIj9jqh1Xr1NABqOJZw9XwyHdaLd01c_jKpzEMErQ,22083
-flaxdiff-0.1.12.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-flaxdiff-0.1.12.dist-info/top_level.txt,sha256=-2-nXnfkJgSfkki1tjm5Faw6Dso7vhtdn2szwCdX5CQ,9
-flaxdiff-0.1.12.dist-info/RECORD,,
+flaxdiff-0.1.14.dist-info/METADATA,sha256=rcwF7cCFfgPLHn5gD7GZ_KvtG6EmiAIiel7xt8HylAo,22083
+flaxdiff-0.1.14.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+flaxdiff-0.1.14.dist-info/top_level.txt,sha256=-2-nXnfkJgSfkki1tjm5Faw6Dso7vhtdn2szwCdX5CQ,9
+flaxdiff-0.1.14.dist-info/RECORD,,