cspresnext50_8xb32_in1k.py

_base_ = [
    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]

# model settings
model = dict(
    type='ImageClassifier',
    backbone=dict(type='CSPResNeXt', depth=50),
    neck=dict(type='GlobalAveragePooling'),
    head=dict(
        type='LinearClsHead',
        num_classes=1000,
        in_channels=2048,
        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
        topk=(1, 5),
    ))

# dataset settings
dataset_type = 'ImageNet'
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,
        backend='pillow',
        interpolation='bicubic'),
    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
    dict(type='Normalize', **img_norm_cfg),
    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),
        backend='pillow',
        interpolation='bicubic'),
    dict(type='CenterCrop', crop_size=224),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='Collect', keys=['img'])
]
data = dict(
    samples_per_gpu=32,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        data_prefix='data/imagenet/train',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        data_prefix='data/imagenet/val',
        ann_file='data/imagenet/meta/val.txt',
        pipeline=test_pipeline),
    test=dict(
        # replace `data/val` with `data/test` for standard test
        type=dataset_type,
        data_prefix='data/imagenet/val',
        ann_file='data/imagenet/meta/val.txt',
        pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')