# Copyright 2021 Huawei Technologies Co., Ltd
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# model settings
model = dict(
    type='Recognizer3D',
    backbone=dict(
        type='ResNet3d',
        pretrained2d=True,
        pretrained='torchvision://resnet50',
        depth=50,
        conv1_kernel=(5, 7, 7),
        conv1_stride_t=2,
        pool1_stride_t=2,
        conv_cfg=dict(type='Conv3d'),
        norm_eval=False,
        inflate=((1, 1, 1), (1, 0, 1, 0), (1, 0, 1, 0, 1, 0), (0, 1, 0)),
        zero_init_residual=False),
    cls_head=dict(
        type='I3DHead',
        num_classes=400,
        in_channels=2048,
        spatial_type='avg',
        dropout_ratio=0.5,
        init_std=0.01),
    # model training and testing settings
    train_cfg=None,
    test_cfg=dict(average_clips='prob'))

# This setting refers to https://github.com/open-mmlab/mmaction/blob/master/mmaction/models/tenons/backbones/resnet_i3d.py#L329-L332  # noqa: E501