compatible with python3

README.md

@@ -79,15 +79,19 @@ export PYTHONPATH=$PYTHONPATH:{your local DFace root path}
 
 #### 训练mtcnn模型
 
-MTCNN主要有三个网络，叫做**PNet**, **RNet** 和 **ONet**。因此我们的训练过程也需要分三步先后进行。为了更好的实现效果，当前被训练的网络都将依赖于上一个训练好的网络来生成数据。所有的人脸数据集都来自　**[WIDER FACE](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/)** 和 **[CelebA](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)**。WIDER FACE仅提供了大量的人脸边框定位数据，而CelebA包含了人脸关键点定位数据。以下训练除了　生成ONet的人脸关键点训练数据和标注文件　该步骤使用CelebA数据集，其他一律使用WIDER FACE。如果使用wider face的 wider_face_train.mat 注解文件需要转换成txt格式的，我这里用h5py写了个 [转换脚本](https://gitee.com/kuaikuaikim/dface/blob/master/src/prepare_data/widerface_annotation_gen/transform.py)
+MTCNN主要有三个网络，叫做**PNet**, **RNet** 和 **ONet**。因此我们的训练过程也需要分三步先后进行。为了更好的实现效果，当前被训练的网络都将依赖于上一个训练好的网络来生成数据。所有的人脸数据集都来自　**[WIDER FACE](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/)** 和 **[CelebA](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)**。WIDER FACE仅提供了大量的人脸边框定位数据，而CelebA包含了人脸关键点定位数据。以下训练除了　生成ONet的人脸关键点训练数据和标注文件　该步骤使用CelebA数据集，其他一律使用WIDER FACE。如果使用wider face的 wider_face_train.mat 注解文件需要转换成txt格式的，我这里用h5py写了个 [转换脚本](https://gitee.com/kuaikuaikim/dface/blob/master/dface/prepare_data/widerface_annotation_gen/transform.py). 这里我提供一个已经转换好的wider face注解文件 [anno_store/wider_origin_anno.txt](https://gitee.com/kuaikuaikim/dface/blob/master/anno_store/wider_origin_anno.txt), 以下训练过程参数名--anno_file默认就是使用该转换好的注解文件。
 
   
+* 创建 dface 训练数据临时目录，对应于以下所有的参数名　--dface_traindata_store
+```shell
+mkdir {your dface traindata folder}
+```
 
 
 * 生成PNet训练数据和标注文件
 
 ```shell
-python dface/prepare_data/gen_Pnet_train_data.py --dataset_path {your dataset path} --anno_file {your dataset original annotation path}
+python dface/prepare_data/gen_Pnet_train_data.py --prefix_path {注解文件中图片的目录前缀} --dface_traindata_store {之前创建的dface训练数据临时目录}　--anno_file {wider face 注解文件,可以不填，默认使用anno_store/wider_origin_anno.txt}
 ```
 * 乱序合并标注文件
 
@@ -104,7 +108,7 @@ python dface/train_net/train_p_net.py
 * 生成ＲNet训练数据和标注文件
 
 ```shell
-python dface/prepare_data/gen_Rnet_train_data.py --dataset_path {your dataset path} --anno_file {your dataset original annotation path} --pmodel_file {yout PNet model file trained before}
+python dface/prepare_data/gen_Rnet_train_data.py --dface_traindata_store {之前创建的dface训练数据临时目录} --anno_file {wider face 注解文件,可以不填，默认使用anno_store/wider_origin_anno.txt} --pmodel_file {之前训练的Pnet模型文件}
 ```
 * 乱序合并标注文件
 
@@ -121,16 +125,16 @@ python dface/train_net/train_r_net.py
 * 生成ONet训练数据和标注文件
 
 ```shell
-python dface/prepare_data/gen_Onet_train_data.py --dataset_path {your dataset path} --anno_file {your dataset original annotation path} --pmodel_file {yout PNet model file trained before} --rmodel_file {yout RNet model file trained before}
+python dface/prepare_data/gen_Onet_train_data.py --dface_traindata_store {之前创建的dface训练数据临时目录} --anno_file {wider face 注解文件,可以不填，默认使用anno_store/wider_origin_anno.txt} --pmodel_file {之前训练的Pnet模型文件} --rmodel_file {之前训练的Rnet模型文件}
 ```
 
-* 生成ONet的人脸关键点训练数据和标注文件
+* 生成ONet的人脸五官关键点训练数据和标注文件
 
 ```shell
 python dface/prepare_data/gen_landmark_48.py
 ```
 
-* 乱序合并标注文件(包括人脸关键点)
+* 乱序合并标注文件(包括人脸五官关键点)
 
 ```shell
 python dface/prepare_data/assemble_onet_imglist.py

dface/core/detect.py

@@ -623,7 +623,7 @@ face candidates:%d, current batch_size:%d"%(num_boxes, batch_size)
 
             t3 = time.time() - t
             t = time.time()
-            print "time cost " + '{:.3f}'.format(t1+t2+t3) + '  pnet {:.3f}  rnet {:.3f}  onet {:.3f}'.format(t1, t2, t3)
+            print("time cost " + '{:.3f}'.format(t1+t2+t3) + '  pnet {:.3f}  rnet {:.3f}  onet {:.3f}'.format(t1, t2, t3))
 
         return boxes_align, landmark_align
 

dface/core/imagedb.py

@@ -137,7 +137,7 @@ class ImageDB(object):
         imdb: dict
             image database with flipped image annotations added
         """
-        print 'append flipped images to imdb', len(imdb)
+        print('append flipped images to imdb', len(imdb))
         for i in range(len(imdb)):
             imdb_ = imdb[i]
             m_bbox = imdb_['bbox_target'].copy()

dface/prepare_data/assemble_onet_imglist.py

@@ -22,4 +22,4 @@ if __name__ == '__main__':
     imglist_file = os.path.join(anno_dir, imglist_filename)
 
     chose_count = assemble.assemble_data(imglist_file ,anno_list)
-    print "PNet train annotation result file path:%s" % imglist_file
+    print("PNet train annotation result file path:%s" % imglist_file)

dface/prepare_data/assemble_pnet_imglist.py

@@ -22,4 +22,4 @@ if __name__ == '__main__':
     imglist_file = os.path.join(anno_dir, imglist_filename)
 
     chose_count = assemble.assemble_data(imglist_file ,anno_list)
-    print "PNet train annotation result file path:%s" % imglist_file
+    print("PNet train annotation result file path:%s" % imglist_file)

dface/prepare_data/assemble_rnet_imglist.py

@@ -22,4 +22,4 @@ if __name__ == '__main__':
     imglist_file = os.path.join(anno_dir, imglist_filename)
 
     chose_count = assemble.assemble_data(imglist_file ,anno_list)
-    print "PNet train annotation result file path:%s" % imglist_file
+    print("PNet train annotation result file path:%s" % imglist_file)

dface/prepare_data/gen_Onet_train_data.py

@@ -9,7 +9,7 @@ import time
 import os
 import cPickle
 from dface.core.utils import convert_to_square,IoU
-import dface.config
+import dface.config as config
 import dface.core.vision as vision
 
 def gen_onet_data(data_dir, anno_file, pnet_model_file, rnet_model_file, prefix_path='', use_cuda=True, vis=False):
@@ -27,7 +27,7 @@ def gen_onet_data(data_dir, anno_file, pnet_model_file, rnet_model_file, prefix_
 
     for databatch in image_reader:
         if batch_idx % 100 == 0:
-            print "%d images done" % batch_idx
+            print("%d images done" % batch_idx)
         im = databatch
 
         t = time.time()
@@ -89,7 +89,7 @@ def gen_onet_sample_data(data_dir,anno_file,det_boxs_file):
     im_idx_list = list()
     gt_boxes_list = list()
     num_of_images = len(annotations)
-    print "processing %d images in total" % num_of_images
+    print("processing %d images in total" % num_of_images)
 
     for annotation in annotations:
         annotation = annotation.strip().split(' ')
@@ -112,7 +112,7 @@ def gen_onet_sample_data(data_dir,anno_file,det_boxs_file):
     det_handle = open(det_boxs_file, 'r')
 
     det_boxes = cPickle.load(det_handle)
-    print len(det_boxes), num_of_images
+    print(len(det_boxes), num_of_images)
     assert len(det_boxes) == num_of_images, "incorrect detections or ground truths"
 
     # index of neg, pos and part face, used as their image names
@@ -122,7 +122,7 @@ def gen_onet_sample_data(data_dir,anno_file,det_boxs_file):
     image_done = 0
     for im_idx, dets, gts in zip(im_idx_list, det_boxes, gt_boxes_list):
         if image_done % 100 == 0:
-            print "%d images done" % image_done
+            print("%d images done" % image_done)
         image_done += 1
 
         if dets.shape[0] == 0:
@@ -194,17 +194,17 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Test mtcnn',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 
-    parser.add_argument('--dataset_path', dest='dataset_path', help='dataset folder',
+    parser.add_argument('--dface_traindata_store', dest='traindata_store', help='dface train data temporary folder,include 12,24,48/postive,negative,part,landmark',
                         default='../data/wider/', type=str)
-    parser.add_argument('--anno_file', dest='annotation_file', help='output data folder',
-                        default='../data/wider/anno.txt', type=str)
+    parser.add_argument('--anno_file', dest='annotation_file', help='wider face original annotation file',
+                        default=os.path.join(config.ANNO_STORE_DIR,"wider_origin_anno.txt"), type=str)
     parser.add_argument('--pmodel_file', dest='pnet_model_file', help='PNet model file path',
-                        default='/idata/workspace/mtcnn/model_store/pnet_epoch_5best.pt', type=str)
+                        default='/idata/workspace/dface/model_store/pnet_epoch.pt', type=str)
     parser.add_argument('--rmodel_file', dest='rnet_model_file', help='RNet model file path',
-                        default='/idata/workspace/mtcnn/model_store/rnet_epoch_1.pt', type=str)
+                        default='/idata/workspace/dface/model_store/rnet_epoch.pt', type=str)
     parser.add_argument('--gpu', dest='use_cuda', help='with gpu',
                         default=config.USE_CUDA, type=bool)
-    parser.add_argument('--prefix_path', dest='prefix_path', help='image prefix root path',
+    parser.add_argument('--prefix_path', dest='prefix_path', help='annotation file image prefix root path',
                         default='', type=str)
 
     args = parser.parse_args()
@@ -214,7 +214,7 @@ def parse_args():
 
 if __name__ == '__main__':
     args = parse_args()
-    gen_onet_data(args.dataset_path, args.annotation_file, args.pnet_model_file, args.rnet_model_file, args.prefix_path, args.use_cuda)
+    gen_onet_data(args.traindata_store, args.annotation_file, args.pnet_model_file, args.rnet_model_file, args.prefix_path, args.use_cuda)
 
 
 

dface/prepare_data/gen_Pnet_train_data.py

@@ -6,7 +6,7 @@ import numpy.random as npr
 from dface.core.utils import IoU
 import dface.config as config
 
-def gen_pnet_data(data_dir,anno_file):
+def gen_pnet_data(data_dir,anno_file,prefix):
 
     neg_save_dir =  os.path.join(data_dir,"12/negative")
     pos_save_dir =  os.path.join(data_dir,"12/positive")
@@ -32,7 +32,7 @@ def gen_pnet_data(data_dir,anno_file):
         annotations = f.readlines()
 
     num = len(annotations)
-    print "%d pics in total" % num
+    print("%d pics in total" % num)
     p_idx = 0
     n_idx = 0
     d_idx = 0
@@ -40,13 +40,13 @@ def gen_pnet_data(data_dir,anno_file):
     box_idx = 0
     for annotation in annotations:
         annotation = annotation.strip().split(' ')
-        im_path = annotation[0]
+        im_path = os.path.join(prefix,annotation[0])
         bbox = map(float, annotation[1:])
         boxes = np.array(bbox, dtype=np.int32).reshape(-1, 4)
         img = cv2.imread(im_path)
         idx += 1
         if idx % 100 == 0:
-            print idx, "images done"
+            print(idx, "images done")
 
         height, width, channel = img.shape
 
@@ -145,7 +145,7 @@ def gen_pnet_data(data_dir,anno_file):
                     cv2.imwrite(save_file, resized_im)
                     d_idx += 1
             box_idx += 1
-            print "%s images done, pos: %s part: %s neg: %s"%(idx, p_idx, d_idx, n_idx)
+            print("%s images done, pos: %s part: %s neg: %s"%(idx, p_idx, d_idx, n_idx))
 
     f1.close()
     f2.close()
@@ -157,16 +157,19 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Test mtcnn',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 
-    parser.add_argument('--dataset_path', dest='dataset_path', help='dataset folder',
+    parser.add_argument('--dface_traindata_store', dest='traindata_store', help='dface train data temporary folder,include 12,24,48/postive,negative,part,landmark',
                         default='../data/wider/', type=str)
-    parser.add_argument('--anno_file', dest='annotation_file', help='dataset original annotation file',
-                        default='../data/wider/anno.txt', type=str)
-    parser.add_argument('--prefix_path', dest='prefix_path', help='image prefix root path',
+    parser.add_argument('--anno_file', dest='annotation_file', help='wider face original annotation file',
+                        default=os.path.join(config.ANNO_STORE_DIR,"wider_origin_anno.txt"), type=str)
+    parser.add_argument('--prefix_path', dest='prefix_path', help='annotation file image prefix root path',
                         default='', type=str)
 
+
+
+
     args = parser.parse_args()
     return args
 
 if __name__ == '__main__':
     args = parse_args()
-    gen_pnet_data(args.dataset_path,args.annotation_file)
+    gen_pnet_data(args.traindata_store,args.annotation_file,args.prefix_path)

dface/prepare_data/gen_Rnet_train_data.py

@@ -28,7 +28,7 @@ def gen_rnet_data(data_dir, anno_file, pnet_model_file, prefix_path='', use_cuda
 
     for databatch in image_reader:
         if batch_idx % 100 == 0:
-            print "%d images done" % batch_idx
+            print ("%d images done" % batch_idx)
         im = databatch
 
         t = time.time()
@@ -58,11 +58,11 @@ def gen_rnet_data(data_dir, anno_file, pnet_model_file, prefix_path='', use_cuda
         cPickle.dump(all_boxes, f, cPickle.HIGHEST_PROTOCOL)
 
 
-    gen_rnet_sample_data(data_dir,anno_file,save_file)
+    gen_rnet_sample_data(data_dir,anno_file,save_file,prefix_path)
 
 
 
-def gen_rnet_sample_data(data_dir,anno_file,det_boxs_file):
+def gen_rnet_sample_data(data_dir,anno_file,det_boxs_file,prefix_path):
 
     neg_save_dir = os.path.join(data_dir, "24/negative")
     pos_save_dir = os.path.join(data_dir, "24/positive")
@@ -85,11 +85,11 @@ def gen_rnet_sample_data(data_dir,anno_file,det_boxs_file):
     im_idx_list = list()
     gt_boxes_list = list()
     num_of_images = len(annotations)
-    print "processing %d images in total" % num_of_images
+    print ("processing %d images in total" % num_of_images)
 
     for annotation in annotations:
         annotation = annotation.strip().split(' ')
-        im_idx = annotation[0]
+        im_idx = os.path.join(prefix_path,annotation[0])
 
         boxes = map(float, annotation[1:])
         boxes = np.array(boxes, dtype=np.float32).reshape(-1, 4)
@@ -108,7 +108,7 @@ def gen_rnet_sample_data(data_dir,anno_file,det_boxs_file):
     det_handle = open(det_boxs_file, 'r')
 
     det_boxes = cPickle.load(det_handle)
-    print len(det_boxes), num_of_images
+    print(len(det_boxes), num_of_images)
     assert len(det_boxes) == num_of_images, "incorrect detections or ground truths"
 
     # index of neg, pos and part face, used as their image names
@@ -118,7 +118,7 @@ def gen_rnet_sample_data(data_dir,anno_file,det_boxs_file):
     image_done = 0
     for im_idx, dets, gts in zip(im_idx_list, det_boxes, gt_boxes_list):
         if image_done % 100 == 0:
-            print "%d images done" % image_done
+            print("%d images done" % image_done)
         image_done += 1
 
         if dets.shape[0] == 0:
@@ -194,15 +194,15 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Test mtcnn',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 
-    parser.add_argument('--dataset_path', dest='dataset_path', help='dataset folder',
+    parser.add_argument('--dface_traindata_store', dest='traindata_store', help='dface train data temporary folder,include 12,24,48/postive,negative,part,landmark',
                         default='../data/wider/', type=str)
-    parser.add_argument('--anno_file', dest='annotation_file', help='dataset original annotation file',
-                        default='../data/wider/anno.txt', type=str)
+    parser.add_argument('--anno_file', dest='annotation_file', help='wider face original annotation file',
+                        default=os.path.join(config.ANNO_STORE_DIR,"wider_origin_anno.txt"), type=str)
     parser.add_argument('--pmodel_file', dest='pnet_model_file', help='PNet model file path',
-                        default='/idata/workspace/mtcnn/model_store/pnet_epoch_5best.pt', type=str)
+                        default='/idata/workspace/dface/model_store/pnet_epoch.pt', type=str)
     parser.add_argument('--gpu', dest='use_cuda', help='with gpu',
                         default=config.USE_CUDA, type=bool)
-    parser.add_argument('--prefix_path', dest='prefix_path', help='image prefix root path',
+    parser.add_argument('--prefix_path', dest='prefix_path', help='annotation file image prefix root path',
                         default='', type=str)
 
 
@@ -213,7 +213,7 @@ def parse_args():
 
 if __name__ == '__main__':
     args = parse_args()
-    gen_rnet_data(args.dataset_path, args.annotation_file, args.pnet_model_file, args.prefix_path, args.use_cuda)
+    gen_rnet_data(args.traindata_store, args.annotation_file, args.pnet_model_file, args.prefix_path, args.use_cuda)
 
 
 

dface/prepare_data/gen_landmark_12.py

@@ -34,7 +34,7 @@ def gen_data(anno_file, data_dir, prefix):
         annotations = f2.readlines()
 
     num = len(annotations)
-    print "%d pics in total" % num
+    print("%d pics in total" % num)
 
     l_idx =0
     idx = 0
@@ -68,7 +68,7 @@ def gen_data(anno_file, data_dir, prefix):
 
         idx = idx + 1
         if idx % 100 == 0:
-            print "%d images done, landmark images: %d"%(idx,l_idx)
+            print("%d images done, landmark images: %d"%(idx,l_idx))
 
         x1, y1, x2, y2 = gt_box
 
@@ -137,11 +137,11 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Test mtcnn',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 
-    parser.add_argument('--dataset_path', dest='dataset_path', help='dataset folder',
+    parser.add_argument('--dface_traindata_store', dest='traindata_store', help='dataset folder',
                         default='../data/wider/', type=str)
     parser.add_argument('--anno_file', dest='annotation_file', help='dataset original annotation file',
                         default='../data/wider/anno.txt', type=str)
-    parser.add_argument('--prefix_path', dest='prefix_path', help='image prefix root path',
+    parser.add_argument('--prefix_path', dest='prefix_path', help='annotation file image prefix root path',
                         default='../data/', type=str)
 
 
@@ -151,6 +151,6 @@ def parse_args():
 if __name__ == '__main__':
     args = parse_args()
 
-    gen_data(args.annotation_file, args.dataset_path, args.prefix_path)
+    gen_data(args.annotation_file, args.traindata_store, args.prefix_path)
 
 

dface/prepare_data/gen_landmark_24.py

@@ -35,7 +35,7 @@ def gen_data(anno_file, data_dir, prefix):
         annotations = f2.readlines()
 
     num = len(annotations)
-    print "%d total images" % num
+    print("%d total images" % num)
 
     l_idx =0
     idx = 0
@@ -67,7 +67,7 @@ def gen_data(anno_file, data_dir, prefix):
 
         idx = idx + 1
         if idx % 100 == 0:
-            print "%d images done, landmark images: %d"%(idx,l_idx)
+            print("%d images done, landmark images: %d"%(idx,l_idx))
 
         x1, y1, x2, y2 = gt_box
 
@@ -135,11 +135,11 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Test mtcnn',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 
-    parser.add_argument('--dataset_path', dest='dataset_path', help='dataset folder',
+    parser.add_argument('--dface_traindata_store', dest='traindata_store', help='dataset folder',
                         default='/idata/data/wider/', type=str)
     parser.add_argument('--anno_file', dest='annotation_file', help='dataset original annotation file',
                         default='/idata/data/trainImageList.txt', type=str)
-    parser.add_argument('--prefix_path', dest='prefix_path', help='image prefix root path',
+    parser.add_argument('--prefix_path', dest='prefix_path', help='annotation file image prefix root path',
                         default='/idata/data', type=str)
 
 
@@ -149,6 +149,6 @@ def parse_args():
 if __name__ == '__main__':
     args = parse_args()
 
-    gen_data(args.annotation_file, args.dataset_path, args.prefix_path)
+    gen_data(args.annotation_file, args.traindata_store, args.prefix_path)
 
 

dface/prepare_data/gen_landmark_48.py

@@ -34,7 +34,7 @@ def gen_data(anno_file, data_dir, prefix):
         annotations = f2.readlines()
 
     num = len(annotations)
-    print "%d total images" % num
+    print("%d total images" % num)
 
     l_idx =0
     idx = 0
@@ -66,7 +66,7 @@ def gen_data(anno_file, data_dir, prefix):
 
         idx = idx + 1
         if idx % 100 == 0:
-            print "%d images done, landmark images: %d"%(idx,l_idx)
+            print("%d images done, landmark images: %d"%(idx,l_idx))
 
         x1, y1, x2, y2 = gt_box
 
@@ -134,11 +134,11 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Test mtcnn',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 
-    parser.add_argument('--dataset_path', dest='dataset_path', help='dataset folder',
+    parser.add_argument('--dface_traindata_store', dest='traindata_store', help='dataset folder',
                         default='/idata/data/wider/', type=str)
     parser.add_argument('--anno_file', dest='annotation_file', help='dataset original annotation file',
                         default='/idata/data/trainImageList.txt', type=str)
-    parser.add_argument('--prefix_path', dest='prefix_path', help='image prefix root path',
+    parser.add_argument('--prefix_path', dest='prefix_path', help='annotation file image prefix root path',
                         default='/idata/data', type=str)
 
 
@@ -148,6 +148,6 @@ def parse_args():
 if __name__ == '__main__':
     args = parse_args()
 
-    gen_data(args.annotation_file, args.dataset_path, args.prefix_path)
+    gen_data(args.annotation_file, args.traindata_store, args.prefix_path)
 
 

dface/prepare_data/gen_landmark_net_48.py

@@ -27,7 +27,7 @@ def gen_landmark48_data(data_dir, anno_file, pnet_model_file, rnet_model_file, p
 
     for databatch in image_reader:
         if batch_idx % 100 == 0:
-            print "%d images done" % batch_idx
+            print("%d images done" % batch_idx)
         im = databatch
 
 
@@ -91,7 +91,7 @@ def gen_sample_data(data_dir, anno_file, det_boxs_file, prefix_path =''):
     gt_boxes_list = list()
     gt_landmark_list = list()
     num_of_images = len(annotations)
-    print "processing %d images in total" % num_of_images
+    print("processing %d images in total" % num_of_images)
 
     for annotation in annotations:
         annotation = annotation.strip().split(' ')
@@ -117,7 +117,7 @@ def gen_sample_data(data_dir, anno_file, det_boxs_file, prefix_path =''):
     det_handle = open(det_boxs_file, 'r')
 
     det_boxes = cPickle.load(det_handle)
-    print len(det_boxes), num_of_images
+    print(len(det_boxes), num_of_images)
     assert len(det_boxes) == num_of_images, "incorrect detections or ground truths"
 
     # index of neg, pos and part face, used as their image names
@@ -125,7 +125,7 @@ def gen_sample_data(data_dir, anno_file, det_boxs_file, prefix_path =''):
     image_done = 0
     for im_idx, dets, gts, landmark in zip(im_idx_list, det_boxes, gt_boxes_list, gt_landmark_list):
         if image_done % 100 == 0:
-            print "%d images done" % image_done
+            print("%d images done" % image_done)
         image_done += 1
 
         if dets.shape[0] == 0:
@@ -208,7 +208,7 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Test mtcnn',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 
-    parser.add_argument('--dataset_path', dest='dataset_path', help='dataset folder',
+    parser.add_argument('--dface_traindata_store', dest='traindata_store', help='dataset folder',
                         default='../data/wider/', type=str)
     parser.add_argument('--anno_file', dest='annotation_file', help='output data folder',
                         default='../data/wider/anno.txt', type=str)
@@ -228,7 +228,7 @@ def parse_args():
 
 if __name__ == '__main__':
     args = parse_args()
-    gen_landmark48_data(args.dataset_path, args.annotation_file, args.pnet_model_file, args.rnet_model_file, args.prefix_path, args.use_cuda)
+    gen_landmark48_data(args.traindata_store, args.annotation_file, args.pnet_model_file, args.rnet_model_file, args.prefix_path, args.use_cuda)
 
 
 

dface/prepare_data/widerface_annotation_gen/transform.py

@@ -1,4 +1,4 @@
-from wider_loader import WIDER
+from dface.prepare_data.widerface_annotation_gen.wider_loader import WIDER
 import cv2
 import time
 
@@ -17,7 +17,7 @@ wider = WIDER(file_to_label, path_to_image)
 line_count = 0
 box_count = 0
 
-print 'start transforming....'
+print('start transforming....')
 t = time.time()
 
 with open(target_file, 'w+') as f:
@@ -37,10 +37,10 @@ with open(target_file, 'w+') as f:
         f.write(line_str)
 
 st = time.time()-t
-print 'end transforming'
+print('end transforming')
 
-print 'spend time:%ld'%st
-print 'total line(images):%d'%line_count
-print 'total boxes(faces):%d'%box_count
+print('spend time:%ld'%st)
+print('total line(images):%d'%line_count)
+print('total boxes(faces):%d'%box_count)
 
 

dface/train_net/train.py

@@ -84,7 +84,7 @@ def train_pnet(model_store_path, end_epoch,imdb,
                 show3 = box_offset_loss.data.tolist()[0]
                 show5 = all_loss.data.tolist()[0]
 
-                print "%s : Epoch: %d, Step: %d, accuracy: %s, det loss: %s, bbox loss: %s, all_loss: %s, lr:%s "%(datetime.datetime.now(),cur_epoch,batch_idx, show1,show2,show3,show5,base_lr)
+                print("%s : Epoch: %d, Step: %d, accuracy: %s, det loss: %s, bbox loss: %s, all_loss: %s, lr:%s "%(datetime.datetime.now(),cur_epoch,batch_idx, show1,show2,show3,show5,base_lr))
                 accuracy_list.append(accuracy)
                 cls_loss_list.append(cls_loss)
                 bbox_loss_list.append(box_offset_loss)
@@ -103,7 +103,7 @@ def train_pnet(model_store_path, end_epoch,imdb,
         show7 = cls_loss_avg.data.tolist()[0]
         show8 = bbox_loss_avg.data.tolist()[0]
 
-        print "Epoch: %d, accuracy: %s, cls loss: %s, bbox loss: %s" % (cur_epoch, show6, show7, show8)
+        print("Epoch: %d, accuracy: %s, cls loss: %s, bbox loss: %s" % (cur_epoch, show6, show7, show8))
         torch.save(net.state_dict(), os.path.join(model_store_path,"pnet_epoch_%d.pt" % cur_epoch))
         torch.save(net, os.path.join(model_store_path,"pnet_epoch_model_%d.pkl" % cur_epoch))
 
@@ -169,7 +169,7 @@ def train_rnet(model_store_path, end_epoch,imdb,
                 # show4 = landmark_loss.data.tolist()[0]
                 show5 = all_loss.data.tolist()[0]
 
-                print "%s : Epoch: %d, Step: %d, accuracy: %s, det loss: %s, bbox loss: %s, all_loss: %s, lr:%s "%(datetime.datetime.now(), cur_epoch, batch_idx, show1, show2, show3, show5, base_lr)
+                print("%s : Epoch: %d, Step: %d, accuracy: %s, det loss: %s, bbox loss: %s, all_loss: %s, lr:%s "%(datetime.datetime.now(), cur_epoch, batch_idx, show1, show2, show3, show5, base_lr))
                 accuracy_list.append(accuracy)
                 cls_loss_list.append(cls_loss)
                 bbox_loss_list.append(box_offset_loss)
@@ -190,7 +190,7 @@ def train_rnet(model_store_path, end_epoch,imdb,
         show8 = bbox_loss_avg.data.tolist()[0]
         # show9 = landmark_loss_avg.data.tolist()[0]
 
-        print "Epoch: %d, accuracy: %s, cls loss: %s, bbox loss: %s" % (cur_epoch, show6, show7, show8)
+        print("Epoch: %d, accuracy: %s, cls loss: %s, bbox loss: %s" % (cur_epoch, show6, show7, show8))
         torch.save(net.state_dict(), os.path.join(model_store_path,"rnet_epoch_%d.pt" % cur_epoch))
         torch.save(net, os.path.join(model_store_path,"rnet_epoch_model_%d.pkl" % cur_epoch))
 
@@ -275,7 +275,7 @@ def train_onet(model_store_path, end_epoch,imdb,
         show8 = bbox_loss_avg.data.tolist()[0]
         show9 = landmark_loss_avg.data.tolist()[0]
 
-        print "Epoch: %d, accuracy: %s, cls loss: %s, bbox loss: %s, landmark loss: %s " % (cur_epoch, show6, show7, show8, show9)
+        print("Epoch: %d, accuracy: %s, cls loss: %s, bbox loss: %s, landmark loss: %s " % (cur_epoch, show6, show7, show8, show9))
         torch.save(net.state_dict(), os.path.join(model_store_path,"onet_epoch_%d.pt" % cur_epoch))
         torch.save(net, os.path.join(model_store_path,"onet_epoch_model_%d.pkl" % cur_epoch))
 

dface/train_net/train_o_net.py

@@ -42,7 +42,7 @@ def parse_args():
 
 if __name__ == '__main__':
     args = parse_args()
-    print 'train ONet argument:'
+    print('train ONet argument:')
     print args
 
 

dface/train_net/train_p_net.py

@@ -2,7 +2,7 @@ import argparse
 import sys
 from dface.core.imagedb import ImageDB
 from train import train_pnet
-import dface.config
+import dface.config as config
 import os
 
 
@@ -42,7 +42,7 @@ def parse_args():
 
 if __name__ == '__main__':
     args = parse_args()
-    print 'train Pnet argument:'
+    print('train Pnet argument:')
     print args
 
     train_net(annotation_file=args.annotation_file, model_store_path=args.model_store_path,

dface/train_net/train_r_net.py

@@ -2,7 +2,7 @@ import argparse
 import sys
 from dface.core.imagedb import ImageDB
 import train as train
-import dface.config
+import dface.config as config
 import os
 
 
@@ -42,7 +42,7 @@ def parse_args():
 
 if __name__ == '__main__':
     args = parse_args()
-    print 'train Rnet argument:'
+    print('train Rnet argument:')
     print args
 
 

test_image.py

@@ -3,7 +3,6 @@ from dface.core.detect import create_mtcnn_net, MtcnnDetector
 from dface.core import vision
 
 
-
 if __name__ == '__main__':
 
     # refer to your local model path