Bump to python3

tf_ops/3d_interpolation/tf_interpolate.py

@@ -51,8 +51,8 @@ def _three_interpolate_grad(op, grad_out):
         now = time.time() 
         for _ in range(100):
             ret = sess.run(interpolated_points)
-        print time.time() - now
-        print ret.shape, ret.dtype
+        print(time.time() - now)
+        print(ret.shape, ret.dtype)
         #print ret
 
 

tf_ops/grouping/tf_grouping.py

@@ -59,16 +59,16 @@ def knn_point(k, xyz1, xyz2):
     n = xyz1.get_shape()[1].value
     c = xyz1.get_shape()[2].value
     m = xyz2.get_shape()[1].value
-    print b, n, c, m
-    print xyz1, (b,1,n,c)
+    print(b, n, c, m)
+    print(xyz1, (b,1,n,c))
     xyz1 = tf.tile(tf.reshape(xyz1, (b,1,n,c)), [1,m,1,1])
     xyz2 = tf.tile(tf.reshape(xyz2, (b,m,1,c)), [1,1,n,1])
     dist = tf.reduce_sum((xyz1-xyz2)**2, -1)
-    print dist, k
+    print(dist, k)
     outi, out = select_top_k(k, dist)
     idx = tf.slice(outi, [0,0,0], [-1,-1,k])
     val = tf.slice(out, [0,0,0], [-1,-1,k])
-    print idx, val
+    print(idx, val)
     #val, idx = tf.nn.top_k(-dist, k=k) # ONLY SUPPORT CPU
     return val, idx
 
@@ -98,8 +98,8 @@ def knn_point(k, xyz1, xyz2):
         now = time.time() 
         for _ in range(100):
             ret = sess.run(grouped_points)
-        print time.time() - now
-        print ret.shape, ret.dtype
-        print ret
+        print(time.time() - now)
+        print(ret.shape, ret.dtype)
+        print(ret)
 
 

tf_ops/sampling/tf_sampling.py

@@ -79,11 +79,11 @@ def farthest_point_sample(npoint,inp):
         us=(uplusv+uminusv)*0.5
         vs=(uplusv-uminusv)*0.5
         pt_sample=tria_sample+(trib_sample-tria_sample)*tf.expand_dims(us,-1)+(tric_sample-tria_sample)*tf.expand_dims(vs,-1)
-        print 'pt_sample: ', pt_sample
+        print('pt_sample: ', pt_sample)
         reduced_sample=gather_point(pt_sample,farthest_point_sample(1024,pt_sample))
-        print reduced_sample
+        print(reduced_sample)
     with tf.Session('') as sess:
         ret=sess.run(reduced_sample)
-    print ret.shape,ret.dtype
+    print(ret.shape,ret.dtype)
     import cPickle as pickle
     pickle.dump(ret,open('1.pkl','wb'),-1)

train.py

@@ -130,7 +130,7 @@ def train():
             accuracy = tf.reduce_sum(tf.cast(correct, tf.float32)) / float(BATCH_SIZE)
             tf.summary.scalar('accuracy', accuracy)
 
-            print "--- Get training operator"
+            print("--- Get training operator")
             # Get training operator
             learning_rate = get_learning_rate(batch)
             tf.summary.scalar('learning_rate', learning_rate)

utils/provider.py

@@ -38,7 +38,7 @@ def rotate_point_cloud(batch_data):
           BxNx3 array, rotated batch of point clouds
     """
     rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
-    for k in xrange(batch_data.shape[0]):
+    for k in range(batch_data.shape[0]):
         rotation_angle = np.random.uniform() * 2 * np.pi
         cosval = np.cos(rotation_angle)
         sinval = np.sin(rotation_angle)
@@ -58,7 +58,7 @@ def rotate_point_cloud_z(batch_data):
           BxNx3 array, rotated batch of point clouds
     """
     rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
-    for k in xrange(batch_data.shape[0]):
+    for k in range(batch_data.shape[0]):
         rotation_angle = np.random.uniform() * 2 * np.pi
         cosval = np.cos(rotation_angle)
         sinval = np.sin(rotation_angle)
@@ -76,7 +76,7 @@ def rotate_point_cloud_with_normal(batch_xyz_normal):
         Output:
             B,N,6, rotated XYZ, normal point cloud
     '''
-    for k in xrange(batch_xyz_normal.shape[0]):
+    for k in range(batch_xyz_normal.shape[0]):
         rotation_angle = np.random.uniform() * 2 * np.pi
         cosval = np.cos(rotation_angle)
         sinval = np.sin(rotation_angle)
@@ -97,7 +97,7 @@ def rotate_perturbation_point_cloud_with_normal(batch_data, angle_sigma=0.06, an
           BxNx3 array, rotated batch of point clouds
     """
     rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
-    for k in xrange(batch_data.shape[0]):
+    for k in range(batch_data.shape[0]):
         angles = np.clip(angle_sigma*np.random.randn(3), -angle_clip, angle_clip)
         Rx = np.array([[1,0,0],
                        [0,np.cos(angles[0]),-np.sin(angles[0])],
@@ -124,7 +124,7 @@ def rotate_point_cloud_by_angle(batch_data, rotation_angle):
           BxNx3 array, rotated batch of point clouds
     """
     rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
-    for k in xrange(batch_data.shape[0]):
+    for k in range(batch_data.shape[0]):
         #rotation_angle = np.random.uniform() * 2 * np.pi
         cosval = np.cos(rotation_angle)
         sinval = np.sin(rotation_angle)
@@ -144,7 +144,7 @@ def rotate_point_cloud_by_angle_with_normal(batch_data, rotation_angle):
           BxNx6 array, rotated batch of point clouds iwth normal
     """
     rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
-    for k in xrange(batch_data.shape[0]):
+    for k in range(batch_data.shape[0]):
         #rotation_angle = np.random.uniform() * 2 * np.pi
         cosval = np.cos(rotation_angle)
         sinval = np.sin(rotation_angle)
@@ -167,7 +167,7 @@ def rotate_perturbation_point_cloud(batch_data, angle_sigma=0.06, angle_clip=0.1
           BxNx3 array, rotated batch of point clouds
     """
     rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
-    for k in xrange(batch_data.shape[0]):
+    for k in range(batch_data.shape[0]):
         angles = np.clip(angle_sigma*np.random.randn(3), -angle_clip, angle_clip)
         Rx = np.array([[1,0,0],
                        [0,np.cos(angles[0]),-np.sin(angles[0])],