Merge pull request #25 from shaanrockz/master

fix dot product for newer version of torch

Author: ozansener

multi_task/min_norm_solvers.py

@@ -41,16 +41,16 @@ def _min_norm_2d(vecs, dps):
                 if (i,j) not in dps:
                     dps[(i, j)] = 0.0
                     for k in range(len(vecs[i])):
-                        dps[(i,j)] += torch.dot(vecs[i][k], vecs[j][k]).data[0]
+                        dps[(i,j)] += torch.mul(vecs[i][k], vecs[j][k]).sum().data.cpu()
                     dps[(j, i)] = dps[(i, j)]
                 if (i,i) not in dps:
                     dps[(i, i)] = 0.0
                     for k in range(len(vecs[i])):
-                        dps[(i,i)] += torch.dot(vecs[i][k], vecs[i][k]).data[0]
+                        dps[(i,i)] += torch.mul(vecs[i][k], vecs[i][k]).sum().data.cpu()
                 if (j,j) not in dps:
                     dps[(j, j)] = 0.0   
                     for k in range(len(vecs[i])):
-                        dps[(j, j)] += torch.dot(vecs[j][k], vecs[j][k]).data[0]
+                        dps[(j, j)] += torch.mul(vecs[j][k], vecs[j][k]).sum().data.cpu()
                 c,d = MinNormSolver._min_norm_element_from2(dps[(i,i)], dps[(i,j)], dps[(j,j)])
                 if d < dmin:
                     dmin = d
@@ -184,16 +184,16 @@ def gradient_normalizers(grads, losses, normalization_type):
     gn = {}
     if normalization_type == 'l2':
         for t in grads:
-            gn[t] = np.sqrt(np.sum([gr.pow(2).sum().data[0] for gr in grads[t]]))
+            gn[t] = np.sqrt(np.sum([gr.pow(2).sum().data.cpu() for gr in grads[t]]))
     elif normalization_type == 'loss':
         for t in grads:
             gn[t] = losses[t]
     elif normalization_type == 'loss+':
         for t in grads:
-            gn[t] = losses[t] * np.sqrt(np.sum([gr.pow(2).sum().data[0] for gr in grads[t]]))
+            gn[t] = losses[t] * np.sqrt(np.sum([gr.pow(2).sum().data.cpu() for gr in grads[t]]))
     elif normalization_type == 'none':
         for t in grads:
             gn[t] = 1.0
     else:
         print('ERROR: Invalid Normalization Type')
-    return gn
+    return gn