Autofix formatting issues with benchmarks

activeloopai · Jan 23, 2021 · 81a302f · 81a302f
1 parent 25f9783
commit 81a302f
Show file tree

Hide file tree

Showing 3 changed files with 40 additions and 37 deletions.
diff --git a/benchmarks/benchmark_compress_time.py b/benchmarks/benchmark_compress_time.py
@@ -11,12 +11,14 @@
 
 REPEAT_TIMES = 100
 
+
 def bench_pil_compression(times=REPEAT_TIMES):
     with Timer("PIL compression"):
         for i in range(times):
             b = BytesIO()
             IMG.save(b, format="png")
 
+
 def bench_hub_compression(times=REPEAT_TIMES):
     arr = np.array(IMG)
     ds = hub.Dataset(
@@ -33,7 +35,7 @@ def bench_hub_compression(times=REPEAT_TIMES):
     with Timer("Hub compression"):
         ds["image", :times] = batch
 
+
 if __name__ == "__main__":
     bench_pil_compression()
     bench_hub_compression()
-
diff --git a/benchmarks/benchmark_dataset_iter.py b/benchmarks/benchmark_dataset_iter.py
@@ -1,59 +1,54 @@
-import time
 import torch
-import tensorflow as tf
 
 from hub import Dataset
 from hub.utils import Timer
-from hub.schema.features import (
-    Primitive,
-    Tensor,
-    SchemaDict,
-    HubSchema,
-    featurify,
-)
 
-DATASET_NAMES = ['activeloop/mnist', 'activeloop/cifar10_train']
+DATASET_NAMES = ["activeloop/mnist", "activeloop/cifar10_train"]
 
 BATCH_SIZES = [1, 16, 128]
 
 PREFETCH_SIZES = [1, 4, 16, 128]
 
-def time_iter_pytorch(dataset_name="activeloop/mnist",
-                      batch_size=1,
-                      prefetch_factor=0,
-                      process=None):
 
-    dset = Dataset(dataset_name, cache=False, storage_cache=False, mode='r')
+def time_iter_pytorch(
+    dataset_name="activeloop/mnist", batch_size=1, prefetch_factor=0, process=None
+):
 
-    loader = torch.utils.data.DataLoader(
-            dset.to_pytorch(),
-            batch_size=batch_size,
-            prefetch_factor=prefetch_factor,
-            num_workers=1
-            )
+    dset = Dataset(dataset_name, cache=False, storage_cache=False, mode="r")
 
-    with Timer(f"{dataset_name} PyTorch prefetch {prefetch_factor:03} in batches of {batch_size:03}"):
+    loader = torch.utils.data.DataLoader(
+        dset.to_pytorch(),
+        batch_size=batch_size,
+        prefetch_factor=prefetch_factor,
+        num_workers=1,
+    )
+
+    with Timer(
+        f"{dataset_name} PyTorch prefetch {prefetch_factor:03} in batches of {batch_size:03}"
+    ):
         for idx, (image, label) in enumerate(loader):
             if process is not None:
                 process(idx, image, label)
 
 
-def time_iter_tensorflow(dataset_name="activeloop/mnist",
-                         batch_size=1,
-                         prefetch_factor=0,
-                         process=None):
+def time_iter_tensorflow(
+    dataset_name="activeloop/mnist", batch_size=1, prefetch_factor=0, process=None
+):
 
-    dset = Dataset(dataset_name, cache=False, storage_cache=False, mode='r')
+    dset = Dataset(dataset_name, cache=False, storage_cache=False, mode="r")
 
     loader = dset.to_tensorflow().batch(batch_size).prefetch(prefetch_factor)
 
-    with Timer(f"{dataset_name} TF prefetch {prefetch_factor:03} in batches of {batch_size:03}"):
+    with Timer(
+        f"{dataset_name} TF prefetch {prefetch_factor:03} in batches of {batch_size:03}"
+    ):
         for idx, batch in enumerate(loader):
             image = batch["image"]
             label = batch["label"]
             if process is not None:
                 process(idx, image, label)
 
+
 if __name__ == "__main__":
     for name in DATASET_NAMES:
         for size in BATCH_SIZES:

diff --git a/benchmarks/benchmark_random_access.py b/benchmarks/benchmark_random_access.py
@@ -4,21 +4,27 @@
 from hub import Dataset
 from hub.utils import Timer
 
-DATASET_NAMES = ['activeloop/mnist', 
-                 'activeloop/omniglot_test',
-                 'activeloop/cifar10_train', 
-                 'activeloop/cifar100_train']
+DATASET_NAMES = [
+    "activeloop/mnist",
+    "activeloop/omniglot_test",
+    "activeloop/cifar10_train",
+    "activeloop/cifar100_train",
+]
 
 SPAN_POWER_MAX = 10
 
-def time_random_access(dataset_name="activeloop/mnist", offset=1000, span=1000, field="image"):
+
+def time_random_access(
+    dataset_name="activeloop/mnist", offset=1000, span=1000, field="image"
+):
     dset = Dataset(dataset_name, cache=False, storage_cache=False)
     with Timer(f"{dataset_name} read at offset {offset:03} of length {span:03}"):
-        dset[field][offset:offset+span].compute()
+        dset[field][offset : offset + span].compute()
+
 
 if __name__ == "__main__":
     for name in DATASET_NAMES:
         for span in range(SPAN_POWER_MAX):
-            offset = randint(0,999)
-            time_random_access(name, offset, 2**span)
+            offset = randint(0, 999)
+            time_random_access(name, offset, 2 ** span)
         print()