enhancing readability (pytorch#495)

* enhancing readability

Removing `sys` package as it wasn't used. Also, renaming all `input` instances to `predictor` as `input` is a builtin keyword.

* renaming `input` to `images`

imagenet/main.py

@@ -4,7 +4,6 @@
 import shutil
 import time
 import warnings
-import sys
 
 import torch
 import torch.nn as nn
@@ -269,23 +268,23 @@ def train(train_loader, model, criterion, optimizer, epoch, args):
     model.train()
 
     end = time.time()
-    for i, (input, target) in enumerate(train_loader):
+    for i, (images, target) in enumerate(train_loader):
         # measure data loading time
         data_time.update(time.time() - end)
 
         if args.gpu is not None:
-            input = input.cuda(args.gpu, non_blocking=True)
+            images = images.cuda(args.gpu, non_blocking=True)
         target = target.cuda(args.gpu, non_blocking=True)
 
         # compute output
-        output = model(input)
+        output = model(images)
         loss = criterion(output, target)
 
         # measure accuracy and record loss
         acc1, acc5 = accuracy(output, target, topk=(1, 5))
-        losses.update(loss.item(), input.size(0))
-        top1.update(acc1[0], input.size(0))
-        top5.update(acc5[0], input.size(0))
+        losses.update(loss.item(), images.size(0))
+        top1.update(acc1[0], images.size(0))
+        top5.update(acc5[0], images.size(0))
 
         # compute gradient and do SGD step
         optimizer.zero_grad()
@@ -313,20 +312,20 @@ def validate(val_loader, model, criterion, args):
 
     with torch.no_grad():
         end = time.time()
-        for i, (input, target) in enumerate(val_loader):
+        for i, (images, target) in enumerate(val_loader):
             if args.gpu is not None:
-                input = input.cuda(args.gpu, non_blocking=True)
+                images = images.cuda(args.gpu, non_blocking=True)
             target = target.cuda(args.gpu, non_blocking=True)
 
             # compute output
-            output = model(input)
+            output = model(images)
             loss = criterion(output, target)
 
             # measure accuracy and record loss
             acc1, acc5 = accuracy(output, target, topk=(1, 5))
-            losses.update(loss.item(), input.size(0))
-            top1.update(acc1[0], input.size(0))
-            top5.update(acc5[0], input.size(0))
+            losses.update(loss.item(), images.size(0))
+            top1.update(acc1[0], images.size(0))
+            top5.update(acc5[0], images.size(0))
 
             # measure elapsed time
             batch_time.update(time.time() - end)