--- a
+++ b/configs/recognition/slowonly/config_test.py
@@ -0,0 +1,93 @@
+_base_ = [
+    '../../_base_/models/slowonly_r50.py',
+    '../../_base_/schedules/sgd_150e_warmup.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(cls_head=dict(num_classes=101))
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = '../mmaction/data/ucf101/rawframes/'
+data_root_val = '../mmaction/data/ucf101/rawframes/'
+split = 1  # official train/test splits. valid numbers: 1, 2, 3
+ann_file_train = f'../mmaction/data/ucf101/ucf101_train_split_{split}_rawframes.txt'
+ann_file_val = f'../mmaction/data/ucf101/ucf101_val_split_{split}_rawframes.txt'
+ann_file_test = f'../mmaction/data/ucf101/ucf101_val_split_{split}_rawframes.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='SampleFrames', clip_len=8, frame_interval=4, num_clips=1),
+    dict(type='RawFrameDecode'),
+    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='SampleFrames',
+        clip_len=8,
+        frame_interval=4,
+        num_clips=1,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    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='SampleFrames',
+        clip_len=8,
+        frame_interval=4,
+        num_clips=10,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='ThreeCrop', crop_size=256),
+    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,
+    test_dataloader=dict(videos_per_gpu=1),
+    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))
+evaluation = dict(
+    interval=1, metrics=['top_k_accuracy', 'mean_class_accuracy'])
+
+# optimizer
+optimizer = dict(lr=0.1)  # this lr is used for 8 gpus
+# learning policy
+lr_config = dict(policy='CosineAnnealing', min_lr=0, by_epoch=False)
+total_epochs = 64
+
+# runtime settings
+work_dir = './work_dirs/slowonly_r50_8x4x1_64e_ucf101_rgb'