Merge commit 'ef88cd1944215fdaddcb3635968b0f3bdaad762c'

* commit 'ef88cd1944215fdaddcb3635968b0f3bdaad762c':
  Update README.md
  clean up testing code.
  Update README.md
  add images.
  add images.

# Conflicts:
#	README.md

Author: ruotianluo

README.md

@@ -34,14 +34,18 @@ Approximate *baseline* [setup](https://github.com/endernewton/tf-faster-rcnn/blo
   - Train Resnet152 on COCO 2014 trainval35k and test on minival (1000k/1390k), ~~**37.2**~~.
 
 **Note**:
-  - Due to the randomness in GPU training espeicially 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.
-  - **All** the numbers are obtained with a different testing scheme without selecting region proposals using non-maximal suppression (TEST.MODE top), the default and original testing scheme (TEST.MODE nms) will likely result in slightly worse performance (see [report](https://arxiv.org/pdf/1702.02138.pdf), for COCO it drops 0.X AP).
+  - Due to the randomness in GPU training with Tensorflow 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.
+  - 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 all) 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.
   - 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 (VGG16 350k/490k: 26.9, 600k/790k: 28.3, 900k/1190k: 29.5) (number from tf-faster-rcnn), 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 Xinlei find useless especially for COCO). The final feature maps are average-pooled for classification and regression. All batch normalization parameters are fixed. Weight decay is set to Renset101 default 1e-4. Learning rate for biases is not doubled.
   - 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.
-  - Check out ~~[here](http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/)/[here](http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/)/~~[here](https://drive.google.com/open?id=0B7fNdx_jAqhtWERtcnZOanZGSG8) for the latest models, including longer COCO VGG16 models and Resnet ones.
+  - Check out [here](http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/)/[here](http://xinlei.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/)/[here](https://drive.google.com/open?id=0B1_fAEgxdnvJSmF3YUlZcHFqWTQ) for the latest models, including longer COCO VGG16 models and Resnet ones.
+  
+![](data/imgs/gt.png)      |  ![](data/imgs/pred.png)
+:-------------------------:|:-------------------------:
+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:

data/imgs/gt.png

@@ -126,7 +126,7 @@ def apply_nms(all_boxes, thresh):
       x2 = dets[:, 2]
       y2 = dets[:, 3]
       scores = dets[:, 4]
-      inds = np.where((x2 > x1) & (y2 > y1) & (scores > cfg.TEST.DET_THRESHOLD))[0]
+      inds = np.where((x2 > x1) & (y2 > y1))[0]
       dets = dets[inds,:]
       if dets == []:
         continue