update readme.

Author: ruotianluo

README.md

@@ -34,14 +34,14 @@ Approximate *baseline* [setup](https://github.com/endernewton/tf-faster-rcnn/blo
   - Train Resnet152 on COCO 2014 trainval35k and test on minival (900k/1190k), ~~**38.2**~~.
 
 **Note**:
-  - Due to the randomness in GPU training especially for VOC, the best numbers are reported (with 2-3 attempts) here. According to my experience, for COCO you can almost always get a very close number (within ~0.2%) despite the randomness.
+  - Due to the randomness in GPU training especially for VOC, the best numbers are reported (with 2-3 attempts) here. According to Xinlei's experience, for COCO you can almost always get a very close number (within ~0.2%) despite the randomness.
   - The numbers are obtained with the **default** testing scheme which selects region proposals using non-maximal suppression (TEST.MODE nms), the alternative testing scheme (TEST.MODE nms) will likely result in slightly better performance (see [report](https://arxiv.org/pdf/1702.02138.pdf), for COCO it boosts 0.X AP).
   - Since we keep the small proposals (\< 16 pixels width/height), our performance is especially good for small objects.
   - We do not set a threshold (instead of 0.05) for a detection to be included in the final result, which increases recall.
   - Weight decay is set to 1e-4.
   - For other minor modifications, please check the [report](https://arxiv.org/pdf/1702.02138.pdf). Notable ones include using ``crop_and_resize``, and excluding ground truth boxes in RoIs during training.
   - For COCO, we find the performance improving with more iterations, and potentially better performance can be achieved with even more iterations.
-  - For Resnets, we fix the first block (total 4) when fine-tuning the network, and only use ``crop_and_resize`` to resize the RoIs (7x7) without max-pool (which I find useless especially for COCO). The final feature maps are average-pooled for classification and regression. All batch normalization parameters are fixed. Learning rate for biases is not doubled.
+  - For Resnets, we fix the first block (total 4) when fine-tuning the network, and only use ``crop_and_resize`` to resize the RoIs (7x7) without max-pool (which Xinlei finds useless especially for COCO). The final feature maps are average-pooled for classification and regression. All batch normalization parameters are fixed. Learning rate for biases is not doubled.
   - For Mobilenets, we fix the first five layers when fine-tuning the network. All batch normalization parameters are fixed. Weight decay for Mobilenet layers is set to 4e-5.
 
   - For approximate [FPN](https://arxiv.org/abs/1612.03144) baseline setup we simply resize the image with 800 pixels, add 32^2 anchors, and take 1000 proposals during testing.
@@ -53,13 +53,13 @@ Displayed Ground Truth on Tensorboard |  Displayed Predictions on Tensorboard
 
 ### 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 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 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 Xinlei 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**. Xinlei 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 pytorch installation. The code follows **0.2**. If you are using old **0.1.12**, you can checkout 0.1.12 branch.
-  - Python packages you might not have: `cffi`, `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.
+  - Python packages you might not have: `cffi`, `opencv-python`, `easydict` (similar to [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn)). For `easydict` make sure you have the right version. Xinlei uses 1.6.
   - [tensorboard-pytorch](https://github.com/lanpa/tensorboard-pytorch) to visualize the training and validation curve. Please build from source to use the latest tensorflow-tensorboard.
   - ~~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.~~
 
@@ -115,7 +115,7 @@ 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 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).
+If you find it useful, the ``data/cache`` folder created on Xinlei's side is also shared [here](http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/cache.tgz).
 
 ### Demo and Test with pre-trained models
 1. Download pre-trained model (only google drive works)
@@ -251,7 +251,7 @@ tensorboard/[NET]/[DATASET]/default/
 tensorboard/[NET]/[DATASET]/default_val/
 ```
 
-The default number of training iterations is kept the same to the original faster RCNN for VOC 2007, however I find it is beneficial to train longer (see [report](https://arxiv.org/pdf/1702.02138.pdf) for COCO), probably due to the fact that the image batch size is one. For VOC 07+12 we switch to a 80k/110k schedule following [R-FCN](https://github.com/daijifeng001/R-FCN). Also note that due to the nondeterministic nature of the current implementation, the performance can vary a bit, but in general it should be within ~1% of the reported numbers for VOC, and ~0.2% of the reported numbers for COCO. Suggestions/Contributions are welcome.
+The default number of training iterations is kept the same to the original faster RCNN for VOC 2007, however Xinlei finds it is beneficial to train longer (see [report](https://arxiv.org/pdf/1702.02138.pdf) for COCO), probably due to the fact that the image batch size is one. For VOC 07+12 we switch to a 80k/110k schedule following [R-FCN](https://github.com/daijifeng001/R-FCN). Also note that due to the nondeterministic nature of the current implementation, the performance can vary a bit, but in general it should be within ~1% of the reported numbers for VOC, and ~0.2% of the reported numbers for COCO. Suggestions/Contributions are welcome.
 
 ### Citation
 If you find this implementation or the analysis conducted in our report helpful, please consider citing: