# Copyright 2020 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='ResNet3dSlowFast',
pretrained=None,
resample_rate=8, # tau
speed_ratio=8, # alpha
channel_ratio=8, # beta_inv
slow_pathway=dict(
type='resnet3d',
depth=50,
pretrained=None,
lateral=True,
conv1_kernel=(1, 7, 7),
dilations=(1, 1, 1, 1),
conv1_stride_t=1,
pool1_stride_t=1,
inflate=(0, 0, 1, 1),
norm_eval=False),
fast_pathway=dict(
type='resnet3d',
depth=50,
pretrained=None,
lateral=False,
base_channels=8,
conv1_kernel=(5, 7, 7),
conv1_stride_t=1,
pool1_stride_t=1,
norm_eval=False)),
cls_head=dict(
type='SlowFastHead',
in_channels=2304, # 2048+256
num_classes=400,
spatial_type='avg',
dropout_ratio=0.5),
# model training and testing settings
train_cfg=None,
test_cfg=dict(average_clips='prob'))