edit README, print less, save result pic in res dir

.gitignore

@@ -1,5 +1,4 @@
 *.pyc
-*.caffemodel
 .idea
 *.so
 results

README.md

@@ -4,7 +4,6 @@ The codes are used for implementing CTPN for scene text detection, described in:
     Z. Tian, W. Huang, T. He, P. He and Y. Qiao: Detecting Text in Natural Image with
     Connectionist Text Proposal Network, ECCV, 2016.
 
-Online demo is available at: [textdet.com](http://textdet.com)
 
 These demo codes (with our trained model) are for text-line detection (without 
 side-refinement part).
@@ -18,15 +17,15 @@ Python2.7, cython and all what Caffe depends on.
 
 # How to run this code
 
-1. Clone this repository with `git clone https://github.com/tianzhi0549/CTPN.git`. It will checkout the codes of CTPN and Caffe we ship.
+1. Clone this repository with `git clone https://github.com/Cabchinoe/CTPN.git`. It will checkout the codes of CTPN and Caffe we ship. This repo provides a caffe version works on cuda10 and cudnn 7.
 
 2. Install the caffe we ship with codes bellow.
-    * Install caffe's dependencies. You can follow [this tutorial](http://caffe.berkeleyvision.org/installation.html). *Note: we need Python support. The CUDA version we need is 7.0.*
+    * Install caffe's dependencies. You can follow [this tutorial](http://caffe.berkeleyvision.org/installation.html). *Note: we need Python support. The CUDA version we need over 10*
     * Enter the directory `caffe`.
     * Run `cp Makefile.config.example Makefile.config`.
     * Open Makefile.config and set `WITH_PYTHON_LAYER := 1`. If you want to use CUDNN, please also set `CUDNN := 1`. Uncomment the `CPU_ONLY :=1` if you want to compile it without GPU.
 
-      *Note: To use CUDNN, you need to download CUDNN from NVIDIA's official website, and install it in advance. The CUDNN version we use is 3.0.*
+      *Note: To use CUDNN, you need to download CUDNN from NVIDIA's official website, and install it in advance. The CUDNN version we use is 7*
     * Run `make -j && make pycaffe`.
 
 3. After Caffe is set up, you need to download a trained model (about 78M) from [Google Drive](https://drive.google.com/open?id=0B7c5Ix-XO7hqQWtKQ0lxTko4ZGs) or [our website](http://textdet.com/downloads/ctpn_trained_model.caffemodel), and then populate it into directory `models`. The model's name should be ` ctpn_trained_model.caffemodel`.
@@ -42,4 +41,4 @@ If you may want to use other Caffe instead of the one we ship for some reasons,
 * Lstm
 
 # License
-The codes are released under the MIT License.
+The codes are released under the MIT License. (And anti996)

src/detectors.py

@@ -14,12 +14,10 @@ def __init__(self, caffe_model):
 
     def detect(self, im, mean):
         im_data=prepare_img(im, mean)
-        print "dd1"
         _=self.caffe_model.forward2({
             "data": im_data[np.newaxis, :],
             "im_info": np.array([[im_data.shape[1], im_data.shape[2]]], np.float32)
         })
-	print "dd2"
         rois=self.caffe_model.blob("rois")
         scores=self.caffe_model.blob("scores")
         return rois, scores
@@ -38,19 +36,14 @@ def detect(self, im):
         Detecting texts from an image
         :return: the bounding boxes of the detected texts
         """
-        print "start"
         text_proposals, scores=self.text_proposal_detector.detect(im, cfg.MEAN)
-        print "000"
         keep_inds=np.where(scores>cfg.TEXT_PROPOSALS_MIN_SCORE)[0]
         text_proposals, scores=text_proposals[keep_inds], scores[keep_inds]
-       	print 111
         sorted_indices=np.argsort(scores.ravel())[::-1]
         text_proposals, scores=text_proposals[sorted_indices], scores[sorted_indices]
-        print 222
         # nms for text proposals
         keep_inds=nms(np.hstack((text_proposals, scores)), cfg.TEXT_PROPOSALS_NMS_THRESH)
         text_proposals, scores=text_proposals[keep_inds], scores[keep_inds]
-        print 333
         scores=normalize(scores)
 
         text_lines=self.text_proposal_connector.get_text_lines(text_proposals, scores, im.shape[:2])

src/other.py

@@ -91,7 +91,6 @@ def forward2(self, input_data):
         for k, v in input_data.items():
             self.net.blobs[k].reshape(*v.shape)
             self.net.blobs[k].data[...]=v
-        print 'net forward'
         return self.net.forward()
 
     def net_def_file(self):

tools/demo.py

@@ -24,7 +24,7 @@
 from detectors import TextProposalDetector, TextDetector
 import os.path as osp
 from utils.timer import Timer
-
+from PIL import Image
 DEMO_IMAGE_DIR="demo_images/"
 NET_DEF_FILE="models/deploy.prototxt"
 MODEL_FILE="models/ctpn_trained_model.caffemodel"
@@ -59,6 +59,9 @@
     print "Time: %f"%timer.toc()
 
     im_with_text_lines=draw_boxes(im, text_lines, caption=im_name, wait=False)
+    im_with_text_lines = cv2.cvtColor(im_with_text_lines,cv2.COLOR_BGR2RGB)
+    Image.fromarray(im_with_text_lines).save('./res/'+im_name)
+
 
 print "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
 print "Thank you for trying our demo. Press any key to exit..."