fix maskrnn typo (#154)

ABSTRACTIONS.md

@@ -16,7 +16,7 @@ We provide a convenience function `to_image_list` that accepts a few different
 input types, including a list of tensors, and returns an `ImageList` object.
 
 ```python
-from maskrnn_benchmark.structures.image_list import to_image_list
+from maskrcnn_benchmark.structures.image_list import to_image_list
 
 images = [torch.rand(3, 100, 200), torch.rand(3, 150, 170)]
 batched_images = to_image_list(images)

INSTALL.md

@@ -23,7 +23,7 @@ source activate maskrcnn_benchmark
 # this installs the right pip and dependencies for the fresh python
 conda install ipython
 
-# maskrnn_benchmark and coco api dependencies
+# maskrcnn_benchmark and coco api dependencies
 pip install ninja yacs cython matplotlib
 
 # follow PyTorch installation in https://pytorch.org/get-started/locally/

README.md

@@ -99,7 +99,7 @@ In order to be able to run it on fewer GPUs, there are a few possibilities:
 **1. Run the following without modifications**
 
 ```bash
-python /path_to_maskrnn_benchmark/tools/train_net.py --config-file "/path/to/config/file.yaml"
+python /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "/path/to/config/file.yaml"
 ```
 This should work out of the box and is very similar to what we should do for multi-GPU training.
 But the drawback is that it will use much more GPU memory. The reason is that we set in the

setup.py

@@ -60,7 +60,7 @@ def get_extensions():
     name="maskrcnn_benchmark",
     version="0.1",
     author="fmassa",
-    url="https://github.com/facebookresearch/maskrnn-benchmark",
+    url="https://github.com/facebookresearch/maskrcnn-benchmark",
     description="object detection in pytorch",
     packages=find_packages(exclude=("configs", "tests",)),
     # install_requires=requirements,