init apex

Author: speedingwisp

README.md

@@ -1,33 +1,31 @@
-# Pytorch-segmentation-toolbox [DOC](https://weiyc.github.io/assets/pdf/toolbox.pdf)
+# Pytorch-segmentation-toolbox Pytorch-1.1 [DOC](https://weiyc.github.io/assets/pdf/toolbox.pdf)
 Pytorch code for semantic segmentation. This is a minimal code to run PSPnet and Deeplabv3 on Cityscape dataset.
 Shortly afterwards, the code will be reviewed and reorganized for convenience.
 
-**The new version toolbox is released on branch [Pytorch-1.1](https://github.com/speedinghzl/pytorch-segmentation-toolbox/tree/pytorch-1.1) which supports Pytorch 1.0 or later and distributed multiprocessing training and testing**
-
 ### Highlights of Our Implementations
 - Synchronous BN
 - Fewness of Training Time
 - Better Reproduced Performance
 
-### Requirements
-
-To install PyTorch==0.4.0, please refer to https://github.com/pytorch/pytorch#installation. 
+### Requirements && Install
+Python 3.7
 
-4 x 12g GPUs (e.g. TITAN XP) 
+4 x 12g GPUs (e.g. TITAN XP)
 
-Python 3.6
+```bash
+# Install **Pytorch-1.1**
+$ conda install pytorch torchvision cudatoolkit=9.0 -c pytorch
 
-### Compiling
+# Install **Apex**
+$ git clone https://github.com/NVIDIA/apex
+$ cd apex
+$ pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
 
-Some parts of InPlace-ABN have a native CUDA implementation, which must be compiled with the following commands:
-```bash
-cd libs
-sh build.sh
-python build.py
-``` 
-The `build.sh` script assumes that the `nvcc` compiler is available in the current system search path.
-The CUDA kernels are compiled for `sm_50`, `sm_52` and `sm_61` by default.
-To change this (_e.g._ if you are using a Kepler GPU), please edit the `CUDA_GENCODE` variable in `build.sh`.
+# Install **Inplace-ABN**
+$ git clone https://github.com/mapillary/inplace_abn.git
+$ cd inplace_abn
+$ python setup.py install
+```
 
 ### Dataset and pretrained model
 
@@ -37,7 +35,7 @@ Please download MIT imagenet pretrained [resnet101-imagenet.pth](http://scenepar
 
 ### Training and Evaluation
 ```bash
-./run_local.sh YOUR_CS_PATH
+./run_local.sh YOUR_CS_PATH [pspnet|deeplabv3] 40000 769,769 0
 ``` 
 
 ### Benefits