update readme

Author: Xinlei Chen

README.md

@@ -21,7 +21,7 @@ More Results:
   - Train Resnet50 on COCO 2014 trainval35k and test on minival (900k/1190k), **32.4**.
   - Train Resnet152 on COCO 2014 trainval35k and test on minival (900k/1190k), **36.1**.
 
-Approximate *baseline* [setup](https://github.com/endernewton/tf-faster-rcnn/blob/master/experiments/cfgs/res101-lg.yml) from [FPN](https://arxiv.org/abs/1612.03144) (this repo does not contain training code for FPN yet):
+Approximate *baseline* [setup](https://github.com/endernewton/tf-faster-rcnn/blob/master/experiments/cfgs/res101-lg.yml) from [FPN](https://arxiv.org/abs/1612.03144) (this repository does not contain training code for FPN yet):
   - Train Resnet50 on COCO 2014 trainval35k and test on minival (900k/1190k), **34.2**.
   - Train Resnet101 on COCO 2014 trainval35k and test on minival (900k/1190k), **37.4**.
   - Train Resnet152 on COCO 2014 trainval35k and test on minival (900k/1190k), **38.2**.
@@ -41,12 +41,12 @@ Approximate *baseline* [setup](https://github.com/endernewton/tf-faster-rcnn/blo
 
 ### Additional features
 Additional features not mentioned in the [report](https://arxiv.org/pdf/1702.02138.pdf) are added to make research life easier:
-  - **Support for train-and-validation**. During training, the validation data will also be tested from time to time to monitor the process and check potential overfitting. Ideally training and validation should be separate, where the model is loaded everytime to test on validation. However I have implemented it in a joint way to save time and GPU memory. Though in the default setup the testing data is used for validation, no special attempts is made to overfit on testing set.
-  - **Support for resuming training**. I tried to store as much information as possible when snapshoting, with the purpose to resume training from the lateset snapshot properly. The meta information includes current image index, permutation of images, and random state of numpy. However, when you resume training the random seed for tensorflow will be reset (not sure how to save the random state of tensorflow now), so it will result in a difference. **Note** that, the current implementation still cannot force the model to behave deterministically even with the random seeds set. Suggestion/solution is welcome and much appreciated.
-  - **Support for visualization**. The current implementation will summarize ground truth detections, statistics of losses, activations and variables during training, and dump it to a separate folder for tensorboard visualization. The computing graph is also saved for debugging.
+  - **Support for train-and-validation**. During training, the validation data will also be tested from time to time to monitor the process and check potential overfitting. Ideally training and validation should be separate, where the model is loaded every time to test on validation. However I have implemented it in a joint way to save time and GPU memory. Though in the default setup the testing data is used for validation, no special attempts is made to overfit on testing set.
+  - **Support for resuming training**. I tried to store as much information as possible when snapshoting, with the purpose to resume training from the latest snapshot properly. The meta information includes current image index, permutation of images, and random state of numpy. However, when you resume training the random seed for tensorflow will be reset (not sure how to save the random state of tensorflow now), so it will result in a difference. **Note** that, the current implementation still cannot force the model to behave deterministically even with the random seeds set. Suggestion/solution is welcome and much appreciated.
+  - **Support for visualization**. The current implementation will summarize ground truth boxes, statistics of losses, activations and variables during training, and dump it to a separate folder for tensorboard visualization. The computing graph is also saved for debugging.
 
 ### Prerequisites
-  - A basic Tensorflow installation. The code follows **r1.2** format. If you are using r1.0, please check out the r1.0 branch to fix the slim resnet block issue. If you are using an older version (r0.1-r0.12), please check out the r0.12 branch. While it is not required, for experimenting the original RoI pooling (which requires modification of the C++ code in tensorflow), you can check out my tensorflow [fork](https://github.com/endernewton/tensorflow) and look for ``tf.image.roi_pooling``.
+  - A basic Tensorflow installation. The code follows **r1.2** format. If you are using r1.0, please check out the r1.0 branch to fix the slim Resnet block issue. If you are using an older version (r0.1-r0.12), please check out the r0.12 branch. While it is not required, for experimenting the original RoI pooling (which requires modification of the C++ code in tensorflow), you can check out my tensorflow [fork](https://github.com/endernewton/tensorflow) and look for ``tf.image.roi_pooling``.
   - Python packages you might not have: `cython`, `opencv-python`, `easydict` (similar to [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn)). For `easydict` make sure you have the right version. I use 1.6.
   - Docker users: Since the recent upgrade, the docker image on docker hub (https://hub.docker.com/r/mbuckler/tf-faster-rcnn-deps/) is no longer valid. However, you can still build your own image by using dockerfile located at `docker` folder (cuda 8 version, as it is required by Tensorflow r1.0.) And make sure following Tensorflow installation to install and use nvidia-docker[https://github.com/NVIDIA/nvidia-docker]. Last, after launching the container, you have to build the Cython modules within the running container. 
 
@@ -91,7 +91,7 @@ Additional features not mentioned in the [report](https://arxiv.org/pdf/1702.021
   ```
 
 ### Setup data
-Please follow the instructions of py-faster-rcnn [here](https://github.com/rbgirshick/py-faster-rcnn#beyond-the-demo-installation-for-training-and-testing-models) to setup VOC and COCO datasets (Part of COCO is done). The steps involve downloading data and optionally creating softlinks in the ``data`` folder. Since faster RCNN does not rely on pre-computed proposals, it is safe to ignore the steps that setup proposals.
+Please follow the instructions of py-faster-rcnn [here](https://github.com/rbgirshick/py-faster-rcnn#beyond-the-demo-installation-for-training-and-testing-models) to setup VOC and COCO datasets (Part of COCO is done). The steps involve downloading data and optionally creating soft links in the ``data`` folder. Since faster RCNN does not rely on pre-computed proposals, it is safe to ignore the steps that setup proposals.
 
 If you find it useful, the ``data/cache`` folder created on my side is also shared [here](http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/cache.tgz).
 
@@ -105,7 +105,7 @@ If you find it useful, the ``data/cache`` folder created on my side is also shar
   - Another server [here](http://xinlei.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/).
   - Google drive [here](https://drive.google.com/open?id=0B1_fAEgxdnvJSmF3YUlZcHFqWTQ).
 
-2. Create a folder and a softlink to use the pre-trained model
+2. Create a folder and a soft link to use the pre-trained model
   ```Shell
   NET=res101
   TRAIN_IMDB=voc_2007_trainval+voc_2012_trainval
@@ -117,7 +117,7 @@ If you find it useful, the ``data/cache`` folder created on my side is also shar
 
 3. Demo for testing on custom images
   ```Shell
-  # at reposistory root
+  # at repository root
   GPU_ID=0
   CUDA_VISIBLE_DEVICES=${GPU_ID} ./tools/demo.py
   ```
@@ -128,7 +128,7 @@ If you find it useful, the ``data/cache`` folder created on my side is also shar
   GPU_ID=0
   ./experiments/scripts/test_faster_rcnn.sh $GPU_ID pascal_voc_0712 res101
   ```
-  **Note**: If you cannot get the reported numbers (78.7 on my side), then probabaly the NMS function is compiled improperly, refer to [Issue 5](https://github.com/endernewton/tf-faster-rcnn/issues/5).
+  **Note**: If you cannot get the reported numbers (79.8 on my side), then probably the NMS function is compiled improperly, refer to [Issue 5](https://github.com/endernewton/tf-faster-rcnn/issues/5).
 
 ### Train your own model
 1. Download pre-trained models and weights. The current code support VGG16 and Resnet V1 models. Pre-trained models are provided by slim, you can get the pre-trained models [here](https://github.com/tensorflow/models/tree/master/slim#pre-trained-models) and set them in the ``data/imagenet_weights`` folder. For example for VGG16 model, you can set up like:
@@ -160,7 +160,7 @@ If you find it useful, the ``data/cache`` folder created on my side is also shar
   ./experiments/scripts/train_faster_rcnn.sh 0 pascal_voc vgg16
   ./experiments/scripts/train_faster_rcnn.sh 1 coco res101
   ```
-  **Note**: Please double check you have deleted softlink to the pre-trained models before training. If you find NaNs during training, please refer to [Issue 86](https://github.com/endernewton/tf-faster-rcnn/issues/86).
+  **Note**: Please double check you have deleted soft link to the pre-trained models before training. If you find NaNs during training, please refer to [Issue 86](https://github.com/endernewton/tf-faster-rcnn/issues/86). Also if you want to have multi-gpu support, check out [Issue 121](https://github.com/endernewton/tf-faster-rcnn/issues/121).
 
 3. Visualization with Tensorboard
   ```Shell