sixth commit

Author: yl9393

Diff for: README.md

@@ -20,7 +20,7 @@ The CTW1500 dataset can be downloaded through the following link:
 
 (https://pan.baidu.com/s/1eSvpq7o PASSWORD: fatf) (Size = 836Mb).
 
-unzip the file in ./data/ 
+unzip the file in ROOT/data/ 
 
 ### Dataset Information
 
@@ -37,13 +37,13 @@ We use resnet-50 model as our pre-trained model, which can be download through t
 
 (https://pan.baidu.com/s/1eSJBL5K PASSWORD: mcic) (Size = 102Mb).
 
-put model in ./data/imagenet_models
+put model in ROOT/data/imagenet_models/
 
 Our model trained with CTW1500 training set can be download through the following link:
 
 (https://pan.baidu.com/s/1gfs5vH5 PASSWORD: 1700) (Size = 114Mb).
 
-put model in ./output/
+put model in ROOT/output/
 
 * [test.sh](./test.py) After downloading the dataset and our ctd_tloc.caffemodel, simply run the this file can evaluate our method on the CTW1500 test set. Uncommend --vis to visualize the detecting results.
 
@@ -53,9 +53,9 @@ put model in ./output/
 If you find our method or the dataset useful for your research, please cite
 
 ## Requirement 
-1. Clone this repository.
-2. cd ROOT/caffe/  and compile. (ROOT is where root directory of this repository)
-3. cd ROOT/lib make 
+1. Clone this repository. ROOT is the directory where you clone.
+2. cd ROOT/caffe/  and use your own Makefile.config to compile. 
+3. cd ROOT/lib make (based on python2)
 4. pip install shapely. (Enable computing polygon intersection.)
 
 

Diff for: data/.gitignore

@@ -1,5 +1,4 @@
 selective_search*
-imagenet_models*
 fast_rcnn_models*
 faster_rcnn_models*
 rfcn_models*