[Fix] Fix configs for detection

configs/detection/_base_/models/slowonly_r50.py

@@ -4,7 +4,10 @@
     backbone=dict(
         type='ResNet3dSlowOnly',
         depth=50,
-        pretrained=None,
+        pretrained=(
+            'https://download.openmmlab.com/mmaction/recognition/slowonly/'
+            'slowonly_r50_4x16x1_256e_kinetics400_rgb/'
+            'slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth'),
         pretrained2d=False,
         lateral=False,
         num_stages=4,

configs/detection/acrn/README.md

@@ -20,25 +20,23 @@ Current state-of-the-art approaches for spatio-temporal action localization rely
 
 ### AVA2.1
 
-|                                       Model                                       | Modality |  Pretrained  | Backbone | Input | gpus |  mAP  |                  log                   |                  ckpt                   |
-| :-------------------------------------------------------------------------------: | :------: | :----------: | :------: | :---: | :--: | :---: | :------------------------------------: | :-------------------------------------: |
-| [slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava_rgb](/configs/detection/acrn/slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava_rgb.py) |   RGB    | Kinetics-400 | ResNet50 | 32x2  |  8   | 27.58 | [log](https://download.openmmlab.com/) | [ckpt](https://download.openmmlab.com/) |
+| frame sampling strategy | resolution | gpus |     backbone      |   pretrain   |  mAP  | gpu_mem(M) |                  config                   |                  ckpt                   |                   log                   |
+| :---------------------: | :--------: | :--: | :---------------: | :----------: | :---: | :--------: | :---------------------------------------: | :-------------------------------------: | :-------------------------------------: |
+|          8x8x1          |    raw     |  8   | SlowFast ResNet50 | Kinetics-400 | 27.58 |   15263    | [config](/configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb_20220906-0dae1a90.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb.log) |
 
 ### AVA2.2
 
-|                                       Model                                       | Modality |  Pretrained  | Backbone | Input | gpus |  mAP  |                  log                   |                  ckpt                   |
-| :-------------------------------------------------------------------------------: | :------: | :----------: | :------: | :---: | :--: | :---: | :------------------------------------: | :-------------------------------------: |
-| [slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava22_rgb](/configs/detection/acrn/slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava22_rgb.py) |   RGB    | Kinetics-400 | ResNet50 | 32x2  |  8   | 27.63 | [log](https://download.openmmlab.com/) | [ckpt](https://download.openmmlab.com/) |
+| frame sampling strategy | resolution | gpus |     backbone      |   pretrain   |  mAP  | gpu_mem(M) |                  config                   |                  ckpt                   |                   log                   |
+| :---------------------: | :--------: | :--: | :---------------: | :----------: | :---: | :--------: | :---------------------------------------: | :-------------------------------------: | :-------------------------------------: |
+|          8x8x1          |    raw     |  8   | SlowFast ResNet50 | Kinetics-400 | 27.63 |   15263    | [config](/configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb_20220906-0dae1a90.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb.log) |
 
-:::{note}
+Note:
 
 1. The **gpus** indicates the number of gpu we used to get the checkpoint.
    According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
    e.g., lr=0.01 for 4 GPUs x 2 video/gpu and lr=0.08 for 16 GPUs x 4 video/gpu.
 
-:::
-
-For more details on data preparation, you can refer to AVA in [Data Preparation](/docs/data_preparation.md).
+For more details on data preparation, you can refer to to [AVA Data Preparation](/tools/data/ava/README.md).
 
 ## Train
 
@@ -51,11 +49,11 @@ python tools/train.py ${CONFIG_FILE} [optional arguments]
 Example: train ACRN with SlowFast backbone on AVA in a deterministic option.
 
 ```shell
-python tools/train.py configs/detection/acrn/slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava_rgb.py \
+python tools/train.py configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb.py \
     --cfg-options randomness.seed=0 randomness.deterministic=True
 ```
 
-For more details and optional arguments infos, you can refer to **Training setting** part in [getting_started](/docs/getting_started.md#training-setting).
+For more details and optional arguments infos, you can refer to the **Training** part in the [Training and Test Tutorial](/docs/en/user_guides/4_train_test.md).
 
 ## Test
 
@@ -65,13 +63,14 @@ You can use the following command to test a model.
 python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
 ```
 
-Example: test ACRN with SlowFast backbone.
+Example: test ACRN with SlowFast backbone on AVA and dump the result to a pkl file.
 
 ```shell
-python tools/test.py configs/detection/acrn/slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava_rgb.py checkpoints/SOME_CHECKPOINT.pth
+python tools/test.py configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb.py \
+    checkpoints/SOME_CHECKPOINT.pth --dump result.pkl
 ```
 
-For more details and optional arguments infos, you can refer to **Test a dataset** part in [getting_started](/docs/getting_started.md#test-a-dataset) .
+For more details and optional arguments infos, you can refer to the **Test** part in the [Training and Test Tutorial](/docs/en/user_guides/4_train_test.md).
 
 ## Citation
 

configs/detection/acrn/metafile.yml

@@ -6,8 +6,8 @@ Collections:
     Title: "Actor-Centric Relation Network"
 
 Models:
-  - Name: slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava_rgb
-    Config: configs/detection/ava/slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava_rgb.py
+  - Name: slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb
+    Config: configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb.py
     In Collection: ACRN
     Metadata:
       Architecture: ResNet50
@@ -23,9 +23,11 @@ Models:
         Task: Action Detection
         Metrics:
               mAP: 27.58
+    Training Log: https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb.log
+    Weights: https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb_20220906-0dae1a90.pth
 
-  - Name: slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava22_rgb
-    Config: configs/detection/ava/slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava22_rgb.py
+  - Name: slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb
+    Config: configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb.py
     In Collection: ACRN
     Metadata:
       Architecture: ResNet50
@@ -41,3 +43,5 @@ Models:
         Task: Action Detection
         Metrics:
               mAP: 27.63
+    Training Log: https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb.log
+    Weights: https://download.openmmlab.com/mmaction/v1.0/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb_20220906-0dae1a90.pth

configs/detection/acrn/slowfast_acrn_kinetics400_pretrained_r50_8x8x1_cosine_10e_8xb8_ava_rgb.py → configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava21-rgb.py

@@ -7,7 +7,10 @@
         _delete_=True,
         type='ResNet3dSlowFast',
         _scope_='mmaction',
-        pretrained=None,
+        pretrained=(
+            'https://download.openmmlab.com/mmaction/recognition/slowfast/'
+            'slowfast_r50_8x8x1_256e_kinetics400_rgb/'
+            'slowfast_r50_8x8x1_256e_kinetics400_rgb_20200716-73547d2b.pth'),
         resample_rate=4,
         speed_ratio=4,
         channel_ratio=8,
@@ -134,7 +137,3 @@
 optim_wrapper = dict(
     optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.00001),
     clip_grad=dict(max_norm=40, norm_type=2))
-
-load_from = ('https://download.openmmlab.com/mmaction/recognition/slowfast/'
-             'slowfast_r50_8x8x1_256e_kinetics400_rgb/'
-             'slowfast_r50_8x8x1_256e_kinetics400_rgb_20200716-73547d2b.pth')

configs/detection/acrn/slowfast-acrn_kinetics400-pretrained-r50_8xb8-8x8x1-cosine-10e_ava22-rgb.py

@@ -0,0 +1,73 @@
+_base_ = [('slowfast-acrn_kinetics400-pretrained-r50'
+           '_8xb8-8x8x1-cosine-10e_ava21-rgb.py')]
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.2.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.2.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.2.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.2.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.2_for_activitynet_2019.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+train_pipeline = [
+    dict(type='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='PackActionInputs')
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='PackActionInputs')
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=8,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        data_prefix=dict(img=data_root)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=8,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        data_prefix=dict(img=data_root),
+        test_mode=True))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='AVAMetric',
+    ann_file=ann_file_val,
+    label_file=label_file,
+    exclude_file=exclude_file_val)
+test_evaluator = val_evaluator