[Bug fix] Fix efficient test for multi-node (#707)

* [Bug fix] Fix efficient test for multi-node

* fixed CI

* add efficient test dir

* remove unused args

mmseg/apis/test.py

 import os.path as osp
-import pickle
-import shutil
 import tempfile
 
 import mmcv
 import numpy as np
 import torch
-import torch.distributed as dist
+from mmcv.engine import collect_results_cpu, collect_results_gpu
 from mmcv.image import tensor2imgs
 from mmcv.runner import get_dist_info
 
 
-def np2tmp(array, temp_file_name=None):
+def np2tmp(array, temp_file_name=None, tmpdir=None):
     """Save ndarray to local numpy file.
 
     Args:
@@ -19,6 +17,7 @@ def np2tmp(array, temp_file_name=None):
         temp_file_name (str): Numpy file name. If 'temp_file_name=None', this
             function will generate a file name with tempfile.NamedTemporaryFile
             to save ndarray. Default: None.
+        tmpdir (str): Temporary directory to save Ndarray files. Default: None.
 
     Returns:
         str: The numpy file name.
@@ -26,7 +25,7 @@ def np2tmp(array, temp_file_name=None):
 
     if temp_file_name is None:
         temp_file_name = tempfile.NamedTemporaryFile(
-            suffix='.npy', delete=False).name
+            suffix='.npy', delete=False, dir=tmpdir).name
     np.save(temp_file_name, array)
     return temp_file_name
 
@@ -58,6 +57,8 @@ def single_gpu_test(model,
     results = []
     dataset = data_loader.dataset
     prog_bar = mmcv.ProgressBar(len(dataset))
+    if efficient_test:
+        mmcv.mkdir_or_exist('.efficient_test')
     for i, data in enumerate(data_loader):
         with torch.no_grad():
             result = model(return_loss=False, **data)
@@ -90,11 +91,11 @@ def single_gpu_test(model,
 
         if isinstance(result, list):
             if efficient_test:
-                result = [np2tmp(_) for _ in result]
+                result = [np2tmp(_, tmpdir='.efficient_test') for _ in result]
             results.extend(result)
         else:
             if efficient_test:
-                result = np2tmp(result)
+                result = np2tmp(result, tmpdir='.efficient_test')
             results.append(result)
 
         batch_size = len(result)
@@ -120,7 +121,8 @@ def multi_gpu_test(model,
         model (nn.Module): Model to be tested.
         data_loader (utils.data.Dataloader): Pytorch data loader.
         tmpdir (str): Path of directory to save the temporary results from
-            different gpus under cpu mode.
+            different gpus under cpu mode. The same path is used for efficient
+            test.
         gpu_collect (bool): Option to use either gpu or cpu to collect results.
         efficient_test (bool): Whether save the results as local numpy files to
             save CPU memory during evaluation. Default: False.
@@ -135,17 +137,19 @@ def multi_gpu_test(model,
     rank, world_size = get_dist_info()
     if rank == 0:
         prog_bar = mmcv.ProgressBar(len(dataset))
+    if efficient_test:
+        mmcv.mkdir_or_exist('.efficient_test')
     for i, data in enumerate(data_loader):
         with torch.no_grad():
             result = model(return_loss=False, rescale=True, **data)
 
         if isinstance(result, list):
             if efficient_test:
-                result = [np2tmp(_) for _ in result]
+                result = [np2tmp(_, tmpdir='.efficient_test') for _ in result]
             results.extend(result)
         else:
             if efficient_test:
-                result = np2tmp(result)
+                result = np2tmp(result, tmpdir='.efficient_test')
             results.append(result)
 
         if rank == 0:
@@ -159,80 +163,3 @@ def multi_gpu_test(model,
     else:
         results = collect_results_cpu(results, len(dataset), tmpdir)
     return results
-
-
-def collect_results_cpu(result_part, size, tmpdir=None):
-    """Collect results with CPU."""
-    rank, world_size = get_dist_info()
-    # create a tmp dir if it is not specified
-    if tmpdir is None:
-        MAX_LEN = 512
-        # 32 is whitespace
-        dir_tensor = torch.full((MAX_LEN, ),
-                                32,
-                                dtype=torch.uint8,
-                                device='cuda')
-        if rank == 0:
-            tmpdir = tempfile.mkdtemp()
-            tmpdir = torch.tensor(
-                bytearray(tmpdir.encode()), dtype=torch.uint8, device='cuda')
-            dir_tensor[:len(tmpdir)] = tmpdir
-        dist.broadcast(dir_tensor, 0)
-        tmpdir = dir_tensor.cpu().numpy().tobytes().decode().rstrip()
-    else:
-        mmcv.mkdir_or_exist(tmpdir)
-    # dump the part result to the dir
-    mmcv.dump(result_part, osp.join(tmpdir, 'part_{}.pkl'.format(rank)))
-    dist.barrier()
-    # collect all parts
-    if rank != 0:
-        return None
-    else:
-        # load results of all parts from tmp dir
-        part_list = []
-        for i in range(world_size):
-            part_file = osp.join(tmpdir, 'part_{}.pkl'.format(i))
-            part_list.append(mmcv.load(part_file))
-        # sort the results
-        ordered_results = []
-        for res in zip(*part_list):
-            ordered_results.extend(list(res))
-        # the dataloader may pad some samples
-        ordered_results = ordered_results[:size]
-        # remove tmp dir
-        shutil.rmtree(tmpdir)
-        return ordered_results
-
-
-def collect_results_gpu(result_part, size):
-    """Collect results with GPU."""
-    rank, world_size = get_dist_info()
-    # dump result part to tensor with pickle
-    part_tensor = torch.tensor(
-        bytearray(pickle.dumps(result_part)), dtype=torch.uint8, device='cuda')
-    # gather all result part tensor shape
-    shape_tensor = torch.tensor(part_tensor.shape, device='cuda')
-    shape_list = [shape_tensor.clone() for _ in range(world_size)]
-    dist.all_gather(shape_list, shape_tensor)
-    # padding result part tensor to max length
-    shape_max = torch.tensor(shape_list).max()
-    part_send = torch.zeros(shape_max, dtype=torch.uint8, device='cuda')
-    part_send[:shape_tensor[0]] = part_tensor
-    part_recv_list = [
-        part_tensor.new_zeros(shape_max) for _ in range(world_size)
-    ]
-    # gather all result part
-    dist.all_gather(part_recv_list, part_send)
-
-    if rank == 0:
-        part_list = []
-        for recv, shape in zip(part_recv_list, shape_list):
-            part_list.append(
-                pickle.loads(recv[:shape[0]].cpu().numpy().tobytes()))
-        # sort the results
-        ordered_results = []
-        for res in zip(*part_list):
-            ordered_results.extend(list(res))
-        # the dataloader may pad some samples
-        ordered_results = ordered_results[:size]
-        return ordered_results