diff --git a/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py b/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py
index 49a30be6..388843b6 100644
--- a/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py
@@ -7,4 +7,79 @@ model = dict(
         channel_ratio=8,  # beta_inv
         slow_pathway=dict(fusion_kernel=7)))
 
+# dataset settings
+dataset_type = 'VideoDataset'
+data_root = 'data/kinetics400/videos_train'
+data_root_val = 'data/kinetics400/videos_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_videos.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_videos.txt'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_videos.txt'
+
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+
+train_pipeline = [
+    dict(type='DecordInit'),
+    dict(type='SampleFrames', clip_len=32, frame_interval=2, num_clips=1),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='RandomResizedCrop'),
+    dict(type='Resize', scale=(224, 224), keep_ratio=False),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs', 'label'])
+]
+val_pipeline = [
+    dict(type='DecordInit'),
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=1,
+        test_mode=True),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+test_pipeline = [
+    dict(type='DecordInit'),
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=1,
+        test_mode=True),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    videos_per_gpu=8,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        data_prefix=data_root,
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        data_prefix=data_root_val,
+        pipeline=val_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=ann_file_test,
+        data_prefix=data_root_val,
+        pipeline=test_pipeline))
+
 work_dir = './work_dirs/slowfast_r50_3d_8x8x1_256e_kinetics400_rgb'
diff --git a/mmaction/models/backbones/resnet3d_slowfast.py b/mmaction/models/backbones/resnet3d_slowfast.py
index 0b70f4ac..f9f8d955 100644
--- a/mmaction/models/backbones/resnet3d_slowfast.py
+++ b/mmaction/models/backbones/resnet3d_slowfast.py
@@ -488,18 +488,13 @@ class ResNet3dSlowFast(nn.Module):
             tuple[torch.Tensor]: The feature of the input samples extracted
                 by the backbone.
         """
-        x_slow = nn.functional.interpolate(
-            x,
-            mode='nearest',
-            scale_factor=(1.0 / self.resample_rate, 1.0, 1.0))
+        t = x.size(2)
+        x_slow = x.index_select(2, torch.arange(0, t, self.resample_rate))
         x_slow = self.slow_path.conv1(x_slow)
         x_slow = self.slow_path.maxpool(x_slow)
 
-        x_fast = nn.functional.interpolate(
-            x,
-            mode='nearest',
-            scale_factor=(1.0 / (self.resample_rate // self.speed_ratio), 1.0,
-                          1.0))
+        x_fast = x.index_select(
+            2, torch.arange(0, t, self.resample_rate // self.speed_ratio))
         x_fast = self.fast_path.conv1(x_fast)
         x_fast = self.fast_path.maxpool(x_fast)
 
-- 
2.25.1