Python3 fixes

[piromyces]

Here's some fixes I need to make to get this to work under python3:

diff --git a/util.py b/util.py
index 19037ad..f05b4c2 100644
--- a/util.py
+++ b/util.py
@@ -16,17 +16,16 @@ def readPFM(file):
     endian = None

     header = file.readline().rstrip()
-    if header == 'PF':
+    if header == b'PF':
         color = True
-    elif header == 'Pf':
+    elif header == b'Pf':
         color = False
     else:
         raise Exception('Not a PFM file.')
-
-    dim_match = re.match(r'^(\d+)\s(\d+)\s$', file.readline())
-    if dim_match:
-        width, height = map(int, dim_match.groups())
-    else:
+    dims = file.readline()
+    try:
+        width,height = list(map(int,dims.split()))
+    except:
         raise Exception('Malformed PFM header.')

In dispnet.py :

-        targets = [tf.image.resize_nearest_neighbor(target, [height / np.power(2, n),
-                                                    width / np.power(2, n)])
+        targets = [tf.image.resize_nearest_neighbor(target, [height // np.power(2, n),
+                                                    width // np.power(2, n)])

And in train.py:

-            schedule_current = min(step / schedule_step, len(weights_schedule)-1)
+            schedule_current = min(step // schedule_step, len(weights_schedule)-1)
-                    schedule_current = min(step / schedule_step, len(weights_schedule)-1)
+                    schedule_current = min(step // schedule_step, len(weights_schedule)-1)

Also MODEL_NAME needs to be set in train.py and not just the ipynb.

[xue1liu2]

Did it work on Corr1D ? It doesn't work when I use Corr1D net.

How is your result? Do you get the result as same as the model in caffe version.

I try it ,but it didn't work well,I don't know why.

[fedor-chervinskii]

Hey! Thanks for you income! I will update the code soon, I definitely should include python 3 support. Also with these new updates coming some fixes for CUDA corr layer part. Now I'm training it from scratch to test it, gonna take some time.