flaxdiff 0.1.35.1__py3-none-any.whl → 0.1.35.3__py3-none-any.whl

flaxdiff/data/online_loader.py

@@ -26,7 +26,6 @@ import traceback
 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):
@@ -78,13 +77,6 @@ def default_image_processor(
     return image, original_height, original_width
 
 
-def default_feature_extractor(sample):
-    return {
-        "url": sample["url"],
-        "caption": sample["caption"],
-    }
-
-
 def map_sample(
     url,
     caption,
@@ -129,6 +121,13 @@ def map_sample(
         pass
 
 
+def default_feature_extractor(sample):
+    return {
+        "url": sample["url"],
+        "caption": sample["caption"],
+    }
+
+
 def map_batch(
     batch, num_threads=256, image_shape=(256, 256),
     min_image_shape=(128, 128),
@@ -142,54 +141,22 @@ def map_batch(
             map_sample, image_shape=image_shape, min_image_shape=min_image_shape,
             timeout=timeout, retries=retries, image_processor=image_processor,
             upscale_interpolation=upscale_interpolation,
-            downscale_interpolation=downscale_interpolation,
-            feature_extractor=feature_extractor
+            downscale_interpolation=downscale_interpolation
         )
-        features = feature_extractor(batch)
-        url, caption = features["url"], features["caption"]
         with ThreadPoolExecutor(max_workers=num_threads) as executor:
+            features = feature_extractor(batch)
+            url, caption = features["url"], features["caption"]
             executor.map(map_sample_fn, url, caption)
     except Exception as e:
         print(f"Error maping batch", e)
         traceback.print_exc()
-        error_queue.put_nowait({
-            "batch": batch,
-            "error": str(e)
-        })
+        # error_queue.put_nowait({
+        #     "batch": batch,
+        #     "error": str(e)
+        # })
         pass
 
 
-def map_batch_repeat_forever(
-    batch, num_threads=256, image_shape=(256, 256),
-    min_image_shape=(128, 128),
-    timeout=15, retries=3, image_processor=default_image_processor,
-    upscale_interpolation=cv2.INTER_CUBIC,
-    downscale_interpolation=cv2.INTER_AREA,
-    feature_extractor=default_feature_extractor,
-):
-    while True:  # Repeat forever
-        try:
-            map_sample_fn = partial(
-                map_sample, image_shape=image_shape, min_image_shape=min_image_shape,
-                timeout=timeout, retries=retries, image_processor=image_processor,
-                upscale_interpolation=upscale_interpolation,
-                downscale_interpolation=downscale_interpolation,
-                feature_extractor=feature_extractor
-            )
-            with ThreadPoolExecutor(max_workers=num_threads) as executor:
-                executor.map(map_sample_fn, batch)
-            # Shuffle the batch
-            batch = batch.shuffle(seed=np.random.randint(0, 1000000))
-        except Exception as e:
-            print(f"Error maping batch", e)
-            traceback.print_exc()
-            error_queue.put_nowait({
-                "batch": batch,
-                "error": str(e)
-            })
-            pass
-
-
 def parallel_image_loader(
     dataset: Dataset, num_workers: int = 8, image_shape=(256, 256),
     min_image_shape=(128, 128),
@@ -197,11 +164,9 @@ def parallel_image_loader(
     upscale_interpolation=cv2.INTER_CUBIC,
     downscale_interpolation=cv2.INTER_AREA,
     feature_extractor=default_feature_extractor,
-    map_batch_fn=map_batch,
-
 ):
     map_batch_fn = partial(
-        map_batch_fn, num_threads=num_threads, image_shape=image_shape,
+        map_batch, num_threads=num_threads, image_shape=image_shape,
         min_image_shape=min_image_shape,
         timeout=timeout, retries=retries, image_processor=image_processor,
         upscale_interpolation=upscale_interpolation,
@@ -209,20 +174,18 @@ def parallel_image_loader(
         feature_extractor=feature_extractor
     )
     shard_len = len(dataset) // num_workers
-    print(f"Local Shard lengths: {shard_len}, workers: {num_workers}")
+    print(f"Local Shard lengths: {shard_len}")
     with multiprocessing.Pool(num_workers) as pool:
         iteration = 0
         while True:
             # Repeat forever
             shards = [dataset[i*shard_len:(i+1)*shard_len]
                       for i in range(num_workers)]
-            # shards = [dataset.shard(num_shards=num_workers, index=i) for i in range(num_workers)]
             print(f"mapping {len(shards)} shards")
             pool.map(map_batch_fn, shards)
             iteration += 1
             print(f"Shuffling dataset with seed {iteration}")
             dataset = dataset.shuffle(seed=iteration)
-            print(f"Dataset shuffled")
             # Clear the error queue
             # while not error_queue.empty():
             #     error_queue.get_nowait()
@@ -237,7 +200,6 @@ class ImageBatchIterator:
         upscale_interpolation=cv2.INTER_CUBIC,
         downscale_interpolation=cv2.INTER_AREA,
         feature_extractor=default_feature_extractor,
-        map_batch_fn=map_batch,
     ):
         self.dataset = dataset
         self.num_workers = num_workers
@@ -252,22 +214,10 @@ class ImageBatchIterator:
             image_processor=image_processor,
             upscale_interpolation=upscale_interpolation,
             downscale_interpolation=downscale_interpolation,
-            feature_extractor=feature_extractor,
-            map_batch_fn=map_batch_fn,
+            feature_extractor=feature_extractor
         )
         self.thread = threading.Thread(target=loader, args=(dataset,))
         self.thread.start()
-        self.error_queue = queue.Queue()
-
-        def error_fetcher():
-            while True:
-                error = error_queue.get()
-                self.error_queue.put(error)
-        self.error_thread = threading.Thread(target=error_fetcher)
-        self.error_thread.start()
-
-    def get_error(self):
-        yield self.error_queue.get()
 
     def __iter__(self):
         return self
@@ -331,7 +281,6 @@ class OnlineStreamingDataLoader():
         upscale_interpolation=cv2.INTER_CUBIC,
         downscale_interpolation=cv2.INTER_AREA,
         feature_extractor=default_feature_extractor,
-        map_batch_fn=map_batch,
     ):
         if isinstance(dataset, str):
             dataset_path = dataset
@@ -359,8 +308,7 @@ class OnlineStreamingDataLoader():
             timeout=timeout, retries=retries, image_processor=image_processor,
             upscale_interpolation=upscale_interpolation,
             downscale_interpolation=downscale_interpolation,
-            feature_extractor=feature_extractor,
-            map_batch_fn=map_batch_fn,
+            feature_extractor=feature_extractor
         )
         self.batch_size = batch_size
 
@@ -372,7 +320,7 @@ class OnlineStreamingDataLoader():
                 try:
                     self.batch_queue.put(collate_fn(batch))
                 except Exception as e:
-                    print("Error collating batch", e)
+                    print("Error processing batch", e)
 
         self.loader_thread = threading.Thread(target=batch_loader)
         self.loader_thread.start()

{flaxdiff-0.1.35.1.dist-info → flaxdiff-0.1.35.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flaxdiff
-Version: 0.1.35.1
+Version: 0.1.35.3
 Summary: A versatile and easy to understand Diffusion library
 Author: Ashish Kumar Singh
 Author-email: ashishkmr472@gmail.com

{flaxdiff-0.1.35.1.dist-info → flaxdiff-0.1.35.3.dist-info}/RECORD

@@ -1,7 +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=reMG_EYbzcNi5rTVbGnAZE7gq1iY6YxYY7K6D5JIsbw,13293
+flaxdiff/data/online_loader.py,sha256=fUM91etaEZmxP0ZxzE1TfxOyHzk1Yq45tYT_P3F-HT0,11311
 flaxdiff/models/__init__.py,sha256=FAivVYXxM2JrCFIXf-C3374RB2Hth25dBrzOeNFhH1U,26
 flaxdiff/models/attention.py,sha256=ZbDGIb5Q6FRqJ6qRY660cqw4WvF9IwCnhEuYdTpLPdM,13023
 flaxdiff/models/common.py,sha256=hWsSs2BP2J-JN1s4qLRr-h-KYkcVyl2hOp1Wsm_L-h8,10994
@@ -34,7 +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-0.1.35.1.dist-info/METADATA,sha256=ktAM1HUTLykCSmVZzH3VJHj4PzeCoOEOlpslyavlOWs,22085
-flaxdiff-0.1.35.1.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-flaxdiff-0.1.35.1.dist-info/top_level.txt,sha256=-2-nXnfkJgSfkki1tjm5Faw6Dso7vhtdn2szwCdX5CQ,9
-flaxdiff-0.1.35.1.dist-info/RECORD,,
+flaxdiff-0.1.35.3.dist-info/METADATA,sha256=g845MSjktfjXWKWtae4_ELwFvtsND8ysj4_yt572Rl4,22085
+flaxdiff-0.1.35.3.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+flaxdiff-0.1.35.3.dist-info/top_level.txt,sha256=-2-nXnfkJgSfkki1tjm5Faw6Dso7vhtdn2szwCdX5CQ,9
+flaxdiff-0.1.35.3.dist-info/RECORD,,