[style] consistent nn. and nn.functional: part 4 examples (#12156)

* consistent nn. and nn.functional: p4 examples

* restore

examples/research_projects/mm-imdb/run_mmimdb.py

@@ -25,8 +25,8 @@ import random
 
 import numpy as np
 import torch
-import torch.nn as nn
 from sklearn.metrics import f1_score
+from torch import nn
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
@@ -107,11 +107,11 @@ def train(args, train_dataset, model, tokenizer, criterion):
 
     # multi-gpu training (should be after apex fp16 initialization)
     if args.n_gpu > 1:
-        model = torch.nn.DataParallel(model)
+        model = nn.DataParallel(model)
 
     # Distributed training (should be after apex fp16 initialization)
     if args.local_rank != -1:
-        model = torch.nn.parallel.DistributedDataParallel(
+        model = nn.parallel.DistributedDataParallel(
             model, device_ids=[args.local_rank], output_device=args.local_rank, find_unused_parameters=True
         )
 
@@ -166,9 +166,9 @@ def train(args, train_dataset, model, tokenizer, criterion):
             tr_loss += loss.item()
             if (step + 1) % args.gradient_accumulation_steps == 0:
                 if args.fp16:
-                    torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm)
+                    nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm)
                 else:
-                    torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm)
+                    nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm)
 
                 optimizer.step()
                 scheduler.step()  # Update learning rate schedule
@@ -248,8 +248,8 @@ def evaluate(args, model, tokenizer, criterion, prefix=""):
     )
 
     # multi-gpu eval
-    if args.n_gpu > 1 and not isinstance(model, torch.nn.DataParallel):
-        model = torch.nn.DataParallel(model)
+    if args.n_gpu > 1 and not isinstance(model, nn.DataParallel):
+        model = nn.DataParallel(model)
 
     # Eval!
     logger.info("***** Running evaluation {} *****".format(prefix))

examples/research_projects/mm-imdb/utils_mmimdb.py

@@ -19,10 +19,10 @@ import os
 from collections import Counter
 
 import torch
-import torch.nn as nn
 import torchvision
 import torchvision.transforms as transforms
 from PIL import Image
+from torch import nn
 from torch.utils.data import Dataset