update readme

kevinlin311tw · kevinlin311tw · commit 20c44c928633 · 2016-01-07T23:34:11.000+08:00
diff --git a/README.md b/README.md
@@ -7,13 +7,13 @@ Created by Kevin Lin, Huei-Fang Yang, and Chu-Song Chen at Academia Sinica, Taip
 
 ## Introduction
 
-<img src="https://www.csie.ntu.edu.tw/~r01944012/ssdh_intro.png" width="800">
-
 We present a simple yet effective supervised deep hash approach that constructs binary hash codes from labeled data for large-scale image search. SSDH constructs hash functions as a latent layer in a deep network and the binary codes are learned by minimizing an objective function defined over classification error and other desirable hash codes properties. Compared to state-of-the-art results, SSDH achieves 26.30% (89.68% vs. 63.38%), 17.11% (89.00% vs. 71.89%) and 19.56% (31.28% vs. 11.72%) higher precisions averaged over a different number of top returned images for the CIFAR-10, NUS-WIDE, and SUN397 datasets, respectively.
 
 The details can be found in the following [arXiv preprint.](http://arxiv.org/abs/1507.00101)
-Presentation slide [PDF](http://www.csie.ntu.edu.tw/~r01944012/deepworkshop-slide.pdf)
 
+Deep Learning workshop presentation slide [PDF](http://www.csie.ntu.edu.tw/~r01944012/deepworkshop-slide.pdf)
+
+<img src="https://www.csie.ntu.edu.tw/~r01944012/ssdh_intro.png" width="800">
 
 ### Citing the deep hashing work
 
@@ -23,13 +23,18 @@ If you find our work useful in your research, please consider citing:
     Huei-Fang Yang, Kevin Lin, Chu-Song Chen
     arXiv preprint arXiv:1507.00101
 
+    Deep Learning of Binary Hash Codes for Fast Image Retrieval
+    K. Lin, H.-F. Yang, J.-H. Hsiao, C.-S. Chen
+    CVPR Workshop (CVPRW) on Deep Learning in Computer Vision, DeepVision 2015, June 2015.
+
+
 ## Prerequisites
 
   0. MATLAB (tested with 2012b on 64-bit Linux)
   0. Caffe's [prerequisites](http://caffe.berkeleyvision.org/installation.html#prequequisites)
 
 
-## Install Caffe-cvprw15
+## Install Caffe-DeepBinaryCode
 
 Adjust Makefile.config and simply run the following commands:
 
@@ -42,13 +47,11 @@ For a faster build, compile in parallel by doing `make all -j8` where 8 is the n
 
 ## Demo
  
-Launch matlab and run `demo.m`
+Launch matlab and run `demo.m`. This demo will generate 48-bits binary codes for each image using the proposed SSDH.
     
     >> demo
 
-This demo will generate 48-bits binary codes for each image using the proposed SSDH.
-
-<img src="https://www.csie.ntu.edu.tw/~r01944012/ssdh_demo.png" width="200">
+<img src="https://www.csie.ntu.edu.tw/~r01944012/ssdh_demo.png" width="600">
 
 
 ## Retrieval evaluation on CIFAR10
@@ -70,16 +73,27 @@ Moreover, simply run the following commands to generate the `precision at k` cur
 You will reproduce the precision curves with respect to different number of top retrieved samples when the 48-bit hash codes are
 used in the evaluation.
  
-## Train your own model on CIFAR10
+## Train your SSDH on CIFAR10
 
 Simply run the following command to train SSDH:
 
 
     $ ./examples/SSDH/train.sh
 
 
-The training process takes roughly 2~3 hours on a desktop with Titian X GPU.
-You will finally get your model named `SSDH48_iter_xxxxxx.caffemodel` under folder `/examples/SSDH/`
+After 50,000 iterations, the top-1 error is 9.7% on the test set of CIFAR10 dataset:
+```
+I0107 19:24:32.258903 23945 solver.cpp:326] Iteration 50000, loss = 0.0274982
+I0107 19:24:32.259012 23945 solver.cpp:346] Iteration 50000, Testing net (#0)
+I0107 19:24:36.696506 23945 solver.cpp:414]     Test net output #0: accuracy = 0.903125
+I0107 19:24:36.696543 23945 solver.cpp:414]     Test net output #1: loss: 50%-fire-rate = 1.47562e-06 (* 1 = 1.47562e-06 loss)
+I0107 19:24:36.696552 23945 solver.cpp:414]     Test net output #2: loss: classfication-error = 0.332657 (* 1 = 0.332657 loss)
+I0107 19:24:36.696559 23945 solver.cpp:414]     Test net output #3: loss: forcing-binary = -0.00317774 (* 1 = -0.00317774 loss)
+I0107 19:24:36.696565 23945 solver.cpp:331] Optimization Done.
+I0107 19:24:36.696570 23945 caffe.cpp:214] Optimization Done.
+```
+
+The training process takes roughly 2~3 hours on a desktop with Titian X GPU. You will finally get your model named `SSDH48_iter_xxxxxx.caffemodel` under folder `/examples/SSDH/`
 
 To use the model, modify the `model_file` in `demo.m` to link to your model:
 
