Fix typos

docs/install.md

@@ -40,7 +40,7 @@ PyTorch 1.3.1., you need to install the prebuilt PyTorch with CUDA 9.2.
 conda install pytorch=1.3.1 cudatoolkit=9.2 torchvision=0.4.2 -c pytorch
 ```
 
-If you build PyTorch from source instead of installing the prebuilt pacakge,
+If you build PyTorch from source instead of installing the prebuilt package,
 you can use more CUDA versions such as 9.0.
 
 c. Clone the mmediting repository.

tools/data/matting/bgm/preprocess_bgm_dataset.py

@@ -7,7 +7,7 @@
 
 
 def generate_json(data_root, seg_root, bg_root, all_data):
-    """Generate training json list for Backgroung Matting video dataset.
+    """Generate training json list for Background Matting video dataset.
 
     Args:
         data_root (str): Background Matting video data root.

tools/data/matting/comp1k/README.md

@@ -86,7 +86,7 @@ mmediting
 ## Prepare the dataset for FBA
 
 FBA adopts dynamic dataset augmentation proposed in [Learning-base Sampling for Natural Image Matting](https://openaccess.thecvf.com/content_CVPR_2019/papers/Tang_Learning-Based_Sampling_for_Natural_Image_Matting_CVPR_2019_paper.pdf).
-In addition, to reduce artifacts during augmentation, it uses the extened version of foreground as foreground.
+In addition, to reduce artifacts during augmentation, it uses the extended version of foreground as foreground.
 We provide scripts to estimate foregrounds.
 
 Prepare the test set as follows:

tools/data/matting/comp1k/extend_fg.py

@@ -81,7 +81,7 @@ def parse_args():
         formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument('data_root', help='Adobe composition 1k dataset root')
     parser.add_argument(
-        '--nproc', type=int, default=4, help='number of processer')
+        '--nproc', type=int, default=4, help='number of processor')
     args = parser.parse_args()
     return args
 

tools/pytorch2onnx.py

@@ -127,7 +127,7 @@ def parse_args():
     data = dict(merged_path=args.img_path, trimap_path=args.trimap_path)
     data = test_pipeline(data)
 
-    # conver model to onnx file
+    # convert model to onnx file
     pytorch2onnx(
         model,
         data,

tools/slurm_train.sh

@@ -1,7 +1,6 @@
 #!/usr/bin/env bash
 export MASTER_PORT=$((12000 + $RANDOM % 20000))
 
-
 set -x
 
 PARTITION=$1