Merge pull request #2 from Austriker/python-3-support

More work on Python 3

README.md

@@ -1,11 +1,20 @@
 # *Faster* R-CNN Fork
 
+ - This fork adds support to python 3.4
+ - Uses an up-to-date Caffe Version
+
+
 #### Warning
 This Fork is still a work in progress 
 
-This fork :
  - Merged the [caffe-fast-rcnn](https://github.com/rbgirshick/caffe-fast-rcnn/tree/0dcd397b29507b8314e252e850518c5695efbb83) fork to the current Caffe version. The [PR](https://github.com/BVLC/caffe/pull/4163) is waiting to be Merged
  - Add support to Python 3.4
+ - Not tested with Python 2.7
+
+##### To-Do
+
+ - Detect GPU arch in setup.py
+ - Test with python2.7
 
 ### Disclaimer
 
@@ -97,9 +106,31 @@ If you find Faster R-CNN useful in your research, please consider citing:
     **Note 2:** The `caffe` submodule needs to be on the `fast-rcnn` branch (or equivalent detached state). This will happen automatically *if you followed step 1 instructions*.
 
 3. Build the Cython modules
+
+    Install pip packages
+    ```sh
+    pip install -r requirements.txt
+
+    ```
+
+    You have to check GPU arch default is sm_35
+
     ```Shell
     cd $FRCN_ROOT/lib
-    make
+
+    # For python 2
+    make python2
+
+    # For python 3
+    make python3
+    ```
+
+    If you want to rebuild :
+    ```sh
+    make clean
+
+    # Then
+    make python2/python3
     ```
 
 4. Build Caffe and pycaffe

lib/Makefile

@@ -1,3 +1,12 @@
-all:
+python3:
+	python3 setup.py build_ext --inplace
+	rm -rf build
+
+python2:
 	python setup.py build_ext --inplace
 	rm -rf build
+
+clean:
+	rm utils/bbox.c
+	rm nms/cpu_nms.c
+	rm nms/gpu_nms.cpp

lib/datasets/coco.py

@@ -13,7 +13,8 @@
 import numpy as np
 import scipy.sparse
 import scipy.io as sio
-import cPickle
+import six.moves.cPickle as pickle
+from six.moves import range
 import json
 import uuid
 # COCO API
@@ -36,7 +37,7 @@ def _filter_crowd_proposals(roidb, crowd_thresh):
         if len(crowd_inds) == 0 or len(non_gt_inds) == 0:
             continue
 
-        iscrowd = [int(True) for _ in xrange(len(crowd_inds))]
+        iscrowd = [int(True) for _ in range(len(crowd_inds))]
         crowd_boxes = ds_utils.xyxy_to_xywh(entry['boxes'][crowd_inds, :])
         non_gt_boxes = ds_utils.xyxy_to_xywh(entry['boxes'][non_gt_inds, :])
         ious = COCOmask.iou(non_gt_boxes, crowd_boxes, iscrowd)
@@ -65,7 +66,7 @@ def __init__(self, image_set, year):
         self._COCO = COCO(self._get_ann_file())
         cats = self._COCO.loadCats(self._COCO.getCatIds())
         self._classes = tuple(['__background__'] + [c['name'] for c in cats])
-        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
+        self._class_to_ind = dict(zip(self.classes, range(self.num_classes)))
         self._class_to_coco_cat_id = dict(zip([c['name'] for c in cats],
                                               self._COCO.getCatIds()))
         self._image_index = self._load_image_set_index()
@@ -126,10 +127,8 @@ def image_path_from_index(self, index):
                      str(index).zfill(12) + '.jpg')
         image_path = osp.join(self._data_path, 'images',
                               self._data_name, file_name)
-        assert(
-            osp.exists(image_path),
-            'Path does not exist: {}'.format(image_path)
-        )
+
+        assert osp.exists(image_path), 'Path does not exist: {}'.format(image_path)
 
         return image_path
 
@@ -153,7 +152,7 @@ def _roidb_from_proposals(self, method):
 
         if osp.exists(cache_file):
             with open(cache_file, 'rb') as fid:
-                roidb = cPickle.load(fid)
+                roidb = pickle.load(fid)
 
             print('{:s} {:s} roidb loaded from {:s}'.format(
                     self.name,
@@ -174,7 +173,7 @@ def _roidb_from_proposals(self, method):
         else:
             roidb = self._load_proposals(method, None)
         with open(cache_file, 'wb') as fid:
-            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
+            pickle.dump(roidb, fid, pickle.HIGHEST_PROTOCOL)
 
         print('wrote {:s} roidb to {:s}'.format(method, cache_file))
 
@@ -196,8 +195,10 @@ def _load_proposals(self, method, gt_roidb):
             'MCG',
             'selective_search',
             'edge_boxes_AR',
-            'edge_boxes_70']
-        assert(method in valid_methods)
+            'edge_boxes_70'
+        ]
+
+        assert method in valid_methods
 
         print('Loading {} boxes'.format(method))
 
@@ -239,7 +240,7 @@ def gt_roidb(self):
         cache_file = osp.join(self.cache_path, self.name + '_gt_roidb.pkl')
         if osp.exists(cache_file):
             with open(cache_file, 'rb') as fid:
-                roidb = cPickle.load(fid)
+                roidb = pickle.load(fid)
 
             print('{} gt roidb loaded from {}'.format(self.name, cache_file))
 
@@ -249,7 +250,7 @@ def gt_roidb(self):
                     for index in self._image_index]
 
         with open(cache_file, 'wb') as fid:
-            cPickle.dump(gt_roidb, fid, cPickle.HIGHEST_PROTOCOL)
+            pickle.dump(gt_roidb, fid, pickle.HIGHEST_PROTOCOL)
 
         print('wrote gt roidb to {}'.format(cache_file))
 
@@ -329,7 +330,7 @@ def _get_thr_ind(coco_eval, thr):
             ind = np.where((coco_eval.params.iouThrs > thr - 1e-5) &
                            (coco_eval.params.iouThrs < thr + 1e-5))[0][0]
             iou_thr = coco_eval.params.iouThrs[ind]
-            assert(np.isclose(iou_thr, thr))
+            assert np.isclose(iou_thr, thr)
 
             return ind
 
@@ -373,7 +374,7 @@ def _do_detection_eval(self, res_file, output_dir):
         eval_file = osp.join(output_dir, 'detection_results.pkl')
 
         with open(eval_file, 'wb') as fid:
-            cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
+            pickle.dump(coco_eval, fid, pickle.HIGHEST_PROTOCOL)
 
         print('Wrote COCO eval results to: {}'.format(eval_file))
 
@@ -392,7 +393,7 @@ def _coco_results_one_category(self, boxes, cat_id):
               [{'image_id': index,
                 'category_id': cat_id,
                 'bbox': [xs[k], ys[k], ws[k], hs[k]],
-                'score': scores[k]} for k in xrange(dets.shape[0])])
+                'score': scores[k]} for k in range(dets.shape[0])])
 
         return results
 

lib/datasets/imdb.py

@@ -11,6 +11,7 @@
 import numpy as np
 import scipy.sparse
 from fast_rcnn.config import cfg
+from six.moves import range
 
 
 class imdb(object):
@@ -98,21 +99,21 @@ def evaluate_detections(self, all_boxes, output_dir=None):
     def _get_widths(self):
         return [
             PIL.Image.open(self.image_path_at(i)).size[0]
-            for i in xrange(self.num_images)
+            for i in range(self.num_images)
         ]
 
     def append_flipped_images(self):
         num_images = self.num_images
         widths = self._get_widths()
 
-        for i in xrange(num_images):
+        for i in range(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())
+            assert (boxes[:, 2] >= boxes[:, 0]).all()
 
             entry = {'boxes': boxes,
                      'gt_overlaps': self.roidb[i]['gt_overlaps'],
@@ -152,13 +153,13 @@ def evaluate_recall(self, candidate_boxes=None, thresholds=None,
             [512**2, 1e5**2]   # 512-inf
         ]
 
-        assert(area in areas, 'unknown area range: {}'.format(area))
+        assert area in areas, 'unknown area range: {}'.format(area)
 
         area_range = area_ranges[areas[area]]
         gt_overlaps = np.zeros(0)
         num_pos = 0
 
-        for i in xrange(self.num_images):
+        for i in range(self.num_images):
             # Checking for max_overlaps == 1 avoids including crowd annotations
             # (...pretty hacking :/)
             max_gt_overlaps = self.roidb[i]['gt_overlaps'].toarray().max(axis=1)
@@ -189,7 +190,7 @@ def evaluate_recall(self, candidate_boxes=None, thresholds=None,
                                      gt_boxes.astype(np.float))
 
             _gt_overlaps = np.zeros((gt_boxes.shape[0]))
-            for j in xrange(gt_boxes.shape[0]):
+            for j in range(gt_boxes.shape[0]):
                 # find which proposal box maximally covers each gt box
                 argmax_overlaps = overlaps.argmax(axis=0)
                 # and get the iou amount of coverage for each gt box
@@ -223,13 +224,11 @@ def evaluate_recall(self, candidate_boxes=None, thresholds=None,
                 'gt_overlaps': gt_overlaps}
 
     def create_roidb_from_box_list(self, box_list, gt_roidb):
-        assert(
-            len(box_list) == self.num_images,
-            'Number of boxes must match number of ground-truth images'
-        )
+
+        assert len(box_list) == self.num_images, 'Number of boxes must match number of ground-truth images'
 
         roidb = []
-        for i in xrange(self.num_images):
+        for i in range(self.num_images):
             boxes = box_list[i]
             num_boxes = boxes.shape[0]
             overlaps = np.zeros((num_boxes, self.num_classes), dtype=np.float32)
@@ -257,7 +256,7 @@ def create_roidb_from_box_list(self, box_list, gt_roidb):
     @staticmethod
     def merge_roidbs(a, b):
         assert len(a) == len(b)
-        for i in xrange(len(a)):
+        for i in range(len(a)):
             a[i]['boxes'] = np.vstack((a[i]['boxes'], b[i]['boxes']))
             a[i]['gt_classes'] = np.hstack((a[i]['gt_classes'],
                                             b[i]['gt_classes']))