[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

acceleration/fast_inference_tutorial/fast_inference_tutorial.ipynb

@@ -109,7 +109,7 @@
     "    Invertd,\n",
     "    Activationsd,\n",
     "    AsDiscreted,\n",
-    "    Compose\n",
+    "    Compose,\n",
     ")\n",
     "from monai.inferers import sliding_window_inference\n",
     "from monai.networks.nets import SegResNet\n",
@@ -316,6 +316,7 @@
     "\n",
     "    return infer_transforms\n",
     "\n",
+    "\n",
     "def get_post_transforms(infer_transforms):\n",
     "    post_transforms = Compose(\n",
     "        [\n",
@@ -332,6 +333,7 @@
     "    )\n",
     "    return post_transforms\n",
     "\n",
+    "\n",
     "def get_model(device, weights_path, trt_model_path, trt_flag=False):\n",
     "    if not trt_flag:\n",
     "        model = SegResNet(\n",
@@ -376,16 +378,20 @@
     "        data = infer_transforms({\"image\": sample})\n",
     "\n",
     "        with torch.no_grad():\n",
-    "            input_image = data[\"image\"].unsqueeze(0).to(device) if benchmark_type in [\"trt\", \"original\"] else data[\"image\"].unsqueeze(0)\n",
+    "            input_image = (\n",
+    "                data[\"image\"].unsqueeze(0).to(device)\n",
+    "                if benchmark_type in [\"trt\", \"original\"]\n",
+    "                else data[\"image\"].unsqueeze(0)\n",
+    "            )\n",
     "            if benchmark_type == \"original\":\n",
     "                with torch.autocast(device_type=\"cuda\"):\n",
     "                    output_image = sliding_window_inference(input_image, roi_size, sw_batch_size, model)\n",
     "            else:\n",
     "                output_image = sliding_window_inference(input_image, roi_size, sw_batch_size, model)\n",
-    "            \n",
+    "\n",
     "            data[\"pred\"] = output_image.squeeze(0)\n",
     "            # data = post_transforms(data)\n",
-    "        \n",
+    "\n",
     "            end = timer()\n",
     "\n",
     "        sample_name = sample.split(\"/\")[-1]\n",