cannot output the accuracy

[vansin]

I would like to ask why the evaluation of the config of the rkd algorithm in mmrazor cannot output the accuracy when written in this way.

问一下，为什么这样写mmrazor里rkd算法的config的evaluation无法输出准确率。

[kawaimahiro]

The total config code was written like this.

dataset_type = 'CustomDataset'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='RandomResizedCrop', size=224),
    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='ToTensor', keys=['gt_label']),
    dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='Resize', size=(256, -1)),
    dict(type='CenterCrop', crop_size=224),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='Collect', keys=['img'])
]
data = dict(
    samples_per_gpu=32,
    workers_per_gpu=2,
    train=dict(
        type='CustomDataset',
        data_prefix='/home/zly/Downloads/archive/data1a/training',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='RandomResizedCrop', size=224),
            dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='ToTensor', keys=['gt_label']),
            dict(type='Collect', keys=['img', 'gt_label'])
        ],
        classes=None,
        ann_file=None),
    val=dict(
        type='CustomDataset',
        data_prefix='/home/zly/Downloads/archive/data1a/validation',
        ann_file=None,
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='Resize', size=(256, -1)),
            dict(type='CenterCrop', crop_size=224),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ],
        classes=None),
    test=dict(
        type='CustomDataset',
        data_prefix='/home/zly/Downloads/archive/data1a/validation',
        ann_file=None,
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='Resize', size=(256, -1)),
            dict(type='CenterCrop', crop_size=224),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ],
        classes=None))
evaluation = dict(
    save_best='auto',
    interval=1,
    metric='accuracy',
    metric_options=dict(topk=(1, )))
optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(policy='OneCycle', max_lr=0.01)
runner = dict(type='EpochBasedRunner', max_epochs=120)
checkpoint_config = dict(interval=10)
log_config = dict(interval=10, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
student = dict(
    type='mmcls.ImageClassifier',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(3, ),
        style='pytorch',
        init_cfg=dict(
            type='Pretrained',
            checkpoint=
            'https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth',
            prefix='backbone')),
    neck=dict(type='GlobalAveragePooling'),
    head=dict(
        type='LinearClsHead',
        num_classes=2,
        in_channels=2048,
        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
        topk=(1, )))
teacher_ckpt = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth'
teacher = dict(
    type='mmcls.ImageClassifier',
    backbone=dict(type='RepVGG', arch='B1g4', out_indices=(3, )),
    neck=dict(type='GlobalAveragePooling'),
    head=dict(
        type='LinearClsHead',
        num_classes=1000,
        in_channels=2048,
        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
        topk=(1, )),
    init_cfg=dict(
        type='Pretrained',
        checkpoint='/home/zly/workspace/mmrazor/work_dir/VGGB2/epoch_111.pth'))
algorithm = dict(
    type='GeneralDistill',
    architecture=dict(
        type='MMClsArchitecture',
        model=dict(
            type='mmcls.ImageClassifier',
            backbone=dict(
                type='ResNet',
                depth=50,
                num_stages=4,
                out_indices=(3, ),
                style='pytorch',
                init_cfg=dict(
                    type='Pretrained',
                    checkpoint=
                    'https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth',
                    prefix='backbone')),
            neck=dict(type='GlobalAveragePooling'),
            head=dict(
                type='LinearClsHead',
                num_classes=2,
                in_channels=2048,
                loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
                topk=(1, )))),
    with_student_loss=True,
    with_teacher_loss=False,
    distiller=dict(
        type='SingleTeacherDistiller',
        teacher=dict(
            type='mmcls.ImageClassifier',
            backbone=dict(type='RepVGG', arch='B1g4', out_indices=(3, )),
            neck=dict(type='GlobalAveragePooling'),
            head=dict(
                type='LinearClsHead',
                num_classes=1000,
                in_channels=2048,
                loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
                topk=(1, )),
            init_cfg=dict(
                type='Pretrained',
                checkpoint=
                '/home/zly/workspace/mmrazor/work_dir/VGGB2/epoch_111.pth')),
        teacher_trainable=False,
        teacher_norm_eval=True,
        components=[
            dict(
                student_module='neck.gap',
                teacher_module='neck.gap',
                losses=[
                    dict(
                        type='DistanceWiseRKD',
                        name='distance_wise_loss',
                        loss_weight=25.0,
                        with_l2_norm=True),
                    dict(
                        type='AngleWiseRKD',
                        name='angle_wise_loss',
                        loss_weight=50.0,
                        with_l2_norm=True)
                ])
        ]))
find_unused_parameters = True
gpu_ids = [0]
work_dir = '/home/zly/workspace/mmrazor/work_dir'

[HIT-cwh]

The argument validate is False in function train_mmcls_model by default. (Ref to https://github.com/open-mmlab/mmrazor/blob/master/mmrazor/apis/mmcls/train.py#L51) Please set it to True and try again.