From 7dc05ceaaac7bd164736f697ac0b04652e2a8060 Mon Sep 17 00:00:00 2001 From: endernewton Date: Wed, 1 Mar 2017 20:16:59 -0500 Subject: [PATCH] Update server. --- README.md | 8 ++++---- data/scripts/fetch_coco_long_models.sh | 2 +- data/scripts/fetch_faster_rcnn_models.sh | 2 +- data/scripts/fetch_imagenet_weights.sh | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 987615a3..8679d5c0 100644 --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ We only tested it on plain VGG16 architecture so far. Our best performance as of - The above 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 result in slightly worse performance (see [report](https://arxiv.org/pdf/1702.02138.pdf), for COCO it drops 0.3 - 0.4 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). - - For COCO, we find the performance improving with more iterations (350k/490k: 26.9, 600k/790k: 28.3, 900k/1190k: 29.5), and potentially better performance can be achieved with even more iterations. Check out [here](http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/coco_longer/) for the latest models. + - For COCO, we find the performance improving with more iterations (350k/490k: 26.9, 600k/790k: 28.3, 900k/1190k: 29.5), and potentially better performance can be achieved with even more iterations. Check out [here](http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/coco_longer/) or ([here](http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/coco_longer/)/[here](https://drive.google.com/open?id=0B1_fAEgxdnvJSmF3YUlZcHFqWTQ)) for the latest models. COCO 2014 minival (900k/1190k): ``` @@ -107,8 +107,8 @@ repo. ./data/scripts/fetch_imagenet_weights.sh ``` **Note**: if you cannot download the models through the link. You can check out the following solutions: - - Another server [here](http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/). - - Google drive [here](https://drive.google.com/open?id=0B1_fAEgxdnvJSmF3YUlZcHFqWTQ) + - Another server [here](http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/). + - Google drive [here](https://drive.google.com/open?id=0B1_fAEgxdnvJSmF3YUlZcHFqWTQ). 5. Install the [Python COCO API](https://github.com/pdollar/coco). And create a symbolic link to it within ``tf-faster-rcnn/data``, The code requires the API to access COCO dataset. @@ -117,7 +117,7 @@ Right now the imagenet weights are used to initialize layers for both training a ### 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. The steps involve downloading data and 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. -If you find it useful, the ``data/cache`` folder created on my side is also shared [here](http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/cache.tgz). +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). ### Testing 1. Create a folder and a softlink to use the pretrained model diff --git a/data/scripts/fetch_coco_long_models.sh b/data/scripts/fetch_coco_long_models.sh index e8b67a2b..cb81992c 100755 --- a/data/scripts/fetch_coco_long_models.sh +++ b/data/scripts/fetch_coco_long_models.sh @@ -4,7 +4,7 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )/../" && pwd )" cd $DIR FILE=coco_long.tgz -URL=http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/$FILE +URL=http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/$FILE CHECKSUM=099f637235d24ec97d9708b3ff66bd7f if [ -f $FILE ]; then diff --git a/data/scripts/fetch_faster_rcnn_models.sh b/data/scripts/fetch_faster_rcnn_models.sh index 4ccac688..7c6f0367 100755 --- a/data/scripts/fetch_faster_rcnn_models.sh +++ b/data/scripts/fetch_faster_rcnn_models.sh @@ -4,7 +4,7 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )/../" && pwd )" cd $DIR FILE=faster_rcnn_models.tgz -URL=http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/$FILE +URL=http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/$FILE CHECKSUM=865cdf7350a87ef41d6476e6e33b7212 if [ -f $FILE ]; then diff --git a/data/scripts/fetch_imagenet_weights.sh b/data/scripts/fetch_imagenet_weights.sh index 1fcca768..be4564cd 100755 --- a/data/scripts/fetch_imagenet_weights.sh +++ b/data/scripts/fetch_imagenet_weights.sh @@ -4,7 +4,7 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )/../" && pwd )" cd $DIR FILE=imagenet_weights.tgz -URL=http://gs11655.sp.cs.cmu.edu/xinleic/tf-faster-rcnn/$FILE +URL=http://ladoga.graphics.cs.cmu.edu/xinleic/tf-faster-rcnn/$FILE CHECKSUM=e9772d7c761040f10a67d389336b90ce if [ -f $FILE ]; then