Py Faster RCNN Caffe Fix

py-faster-rcnn-caffe_fix.diff

diff --git a/caffe-fast-rcnn b/caffe-fast-rcnn
index 0dcd397..cdddca3 160000
--- a/caffe-fast-rcnn
+++ b/caffe-fast-rcnn
@@ -1 +1 @@
-Subproject commit 0dcd397b29507b8314e252e850518c5695efbb83
+Subproject commit cdddca3ad7967dbd80cc660b45fd4347c60e380e-dirty
diff --git a/lib/datasets/factory.py b/lib/datasets/factory.py
index 8c3fdb8..56dd3f5 100644
--- a/lib/datasets/factory.py
+++ b/lib/datasets/factory.py
@@ -31,6 +31,12 @@ for year in ['2015']:
         name = 'coco_{}_{}'.format(year, split)
         __sets[name] = (lambda split=split, year=year: coco(split, year))
 
+from datasets.basketball import basketball
+basketball_devkit_path = './data/basketball'
+for split in ['train', 'val']:
+        name = '{}_{}'.format('basketball', split)
+        __sets[name] = (lambda split=split: basketball(split, basketball_devkit_path))
+
 def get_imdb(name):
     """Get an imdb (image database) by name."""
     if not __sets.has_key(name):
diff --git a/lib/datasets/imdb.py b/lib/datasets/imdb.py
index b56bf0a..e576825 100644
--- a/lib/datasets/imdb.py
+++ b/lib/datasets/imdb.py
@@ -99,6 +99,25 @@ class imdb(object):
       return [PIL.Image.open(self.image_path_at(i)).size[0]
               for i in xrange(self.num_images)]
 
+    # MATLAB Data - Index Starts at 1
+    # def append_flipped_images(self):
+    #     num_images = self.num_images
+    #     widths = self._get_widths()
+    #     for i in xrange(num_images):
+    #         boxes = self.roidb[i]['boxes'].copy()
+    #         oldx1 = boxes[:, 0].copy()
+    #         oldx2 = boxes[:, 2].copy()
+    #         boxes[:, 0] = widths[i] - oldx2 - 1
+    #         boxes[:, 2] = widths[i] - oldx1 - 1
+    #         assert (boxes[:, 2] >= boxes[:, 0]).all()
+    #         entry = {'boxes' : boxes,
+    #                  'gt_overlaps' : self.roidb[i]['gt_overlaps'],
+    #                  'gt_classes' : self.roidb[i]['gt_classes'],
+    #                  'flipped' : True}
+    #         self.roidb.append(entry)
+    #     self._image_index = self._image_index * 2
+
+    # Python Data - Index Starts at 0
     def append_flipped_images(self):
         num_images = self.num_images
         widths = self._get_widths()
@@ -106,8 +125,11 @@ class imdb(object):
             boxes = self.roidb[i]['boxes'].copy()
             oldx1 = boxes[:, 0].copy()
             oldx2 = boxes[:, 2].copy()
-            boxes[:, 0] = widths[i] - oldx2 - 1
-            boxes[:, 2] = widths[i] - oldx1 - 1
+            boxes[:, 0] = widths[i] - oldx2 
+            boxes[:, 2] = widths[i] - oldx1 
+            for b in range(len(boxes)):
+                if boxes[b][2] < boxes[b][0]:
+                    boxes[b][0]=0
             assert (boxes[:, 2] >= boxes[:, 0]).all()
             entry = {'boxes' : boxes,
                      'gt_overlaps' : self.roidb[i]['gt_overlaps'],
diff --git a/lib/roi_data_layer/layer.py b/lib/roi_data_layer/layer.py
index 9f145fe..04f4172 100644
--- a/lib/roi_data_layer/layer.py
+++ b/lib/roi_data_layer/layer.py
@@ -84,7 +84,7 @@ class RoIDataLayer(caffe.Layer):
         """Setup the RoIDataLayer."""
 
         # parse the layer parameter string, which must be valid YAML
-        layer_params = yaml.load(self.param_str_)
+        layer_params = yaml.load(self.param_str)
 
         self._num_classes = layer_params['num_classes']
 
diff --git a/lib/rpn/anchor_target_layer.py b/lib/rpn/anchor_target_layer.py
index 4563df1..3934cdd 100644
--- a/lib/rpn/anchor_target_layer.py
+++ b/lib/rpn/anchor_target_layer.py
@@ -24,7 +24,7 @@ class AnchorTargetLayer(caffe.Layer):
     """
 
     def setup(self, bottom, top):
-        layer_params = yaml.load(self.param_str_)
+        layer_params = yaml.load(self.param_str)
         anchor_scales = layer_params.get('scales', (8, 16, 32))
         self._anchors = generate_anchors(scales=np.array(anchor_scales))
         self._num_anchors = self._anchors.shape[0]
diff --git a/lib/rpn/proposal_layer.py b/lib/rpn/proposal_layer.py
index b157160..6fd2fb9 100644
--- a/lib/rpn/proposal_layer.py
+++ b/lib/rpn/proposal_layer.py
@@ -23,7 +23,7 @@ class ProposalLayer(caffe.Layer):
 
     def setup(self, bottom, top):
         # parse the layer parameter string, which must be valid YAML
-        layer_params = yaml.load(self.param_str_)
+        layer_params = yaml.load(self.param_str)
 
         self._feat_stride = layer_params['feat_stride']
         anchor_scales = layer_params.get('scales', (8, 16, 32))
@@ -61,7 +61,7 @@ class ProposalLayer(caffe.Layer):
         assert bottom[0].data.shape[0] == 1, \
             'Only single item batches are supported'
 
-        cfg_key = str(self.phase) # either 'TRAIN' or 'TEST'
+        cfg_key = 'TEST' if self.phase == 1 else 'TRAIN'
         pre_nms_topN  = cfg[cfg_key].RPN_PRE_NMS_TOP_N
         post_nms_topN = cfg[cfg_key].RPN_POST_NMS_TOP_N
         nms_thresh    = cfg[cfg_key].RPN_NMS_THRESH
diff --git a/lib/rpn/proposal_target_layer.py b/lib/rpn/proposal_target_layer.py
index 38e1f2c..89f2c6e 100644
--- a/lib/rpn/proposal_target_layer.py
+++ b/lib/rpn/proposal_target_layer.py
@@ -22,7 +22,7 @@ class ProposalTargetLayer(caffe.Layer):
     """
 
     def setup(self, bottom, top):
-        layer_params = yaml.load(self.param_str_)
+        layer_params = yaml.load(self.param_str)
         self._num_classes = layer_params['num_classes']
 
         # sampled rois (0, x1, y1, x2, y2)
diff --git a/tools/demo.py b/tools/demo.py
index 631c68a..6e3f149 100755
--- a/tools/demo.py
+++ b/tools/demo.py
@@ -24,17 +24,23 @@ import scipy.io as sio
 import caffe, os, sys, cv2
 import argparse
 
+# CLASSES = ('__background__',
+#            'aeroplane', 'bicycle', 'bird', 'boat',
+#            'bottle', 'bus', 'car', 'cat', 'chair',
+#            'cow', 'diningtable', 'dog', 'horse',
+#            'motorbike', 'person', 'pottedplant',
+#            'sheep', 'sofa', 'train', 'tvmonitor')
+
 CLASSES = ('__background__',
-           'aeroplane', 'bicycle', 'bird', 'boat',
-           'bottle', 'bus', 'car', 'cat', 'chair',
-           'cow', 'diningtable', 'dog', 'horse',
-           'motorbike', 'person', 'pottedplant',
-           'sheep', 'sofa', 'train', 'tvmonitor')
+           'n02802426')
 
 NETS = {'vgg16': ('VGG16',
                   'VGG16_faster_rcnn_final.caffemodel'),
         'zf': ('ZF',
-                  'ZF_faster_rcnn_final.caffemodel')}
+                  'ZF_faster_rcnn_final.caffemodel'),
+        'basketball': ('Basketball',
+                  'zf_faster_rcnn_basketball.caffemodel')
+        }
 
 
 def vis_detections(im, class_name, dets, thresh=0.5):
@@ -117,11 +123,19 @@ if __name__ == '__main__':
 
     args = parse_args()
 
-    prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
-                            'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
+    # prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
+    #                         'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
+    # caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
+    #                           NETS[args.demo_net][1])
+
+    args.demo_net = "basketball"
+    prototxt = "/home/ac2vision/py-faster-rcnn/models/basketball/test.prototxt"
     caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
                               NETS[args.demo_net][1])
 
+    print prototxt
+    print caffemodel
+
     if not os.path.isfile(caffemodel):
         raise IOError(('{:s} not found.\nDid you run ./data/script/'
                        'fetch_faster_rcnn_models.sh?').format(caffemodel))
@@ -141,8 +155,9 @@ if __name__ == '__main__':
     for i in xrange(2):
         _, _= im_detect(net, im)
 
-    im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
-                '001763.jpg', '004545.jpg']
+    # im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
+    #             '001763.jpg', '004545.jpg']
+    im_names = ['bb.jpg']
     for im_name in im_names:
         print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
         print 'Demo for data/demo/{}'.format(im_name)