updated densenet121 efficentnet-b2 seresnet50 shufflenet-v2

configs/_base_/datasets/tiny_imagenet_bs64.py

+# dataset settings
+dataset_type = 'CustomDataset'
+data_preprocessor = dict(
+    num_classes=200,
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=224),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        data_prefix='train',
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        data_prefix='val',
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='Accuracy', topk=(1, 5))
+
+# If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

configs/_base_/datasets/tiny_imagenet_bs64_pil_resize.py

+# dataset settings
+dataset_type = 'CustomDataset'
+data_preprocessor = dict(
+    num_classes=200,
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=224, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        data_prefix='train',
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        data_prefix='val',
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='Accuracy', topk=(1, 5))
+
+# If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

configs/_base_/models/densenet/tiny_densenet121.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='DenseNet', arch='121'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=200,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/tiny_efficientnet_b2.py

+_base_ = [
+    'configs/_base_/models/tiny_efficientnet_b2.py',
+    'configs/_base_/datasets/tiny_imagenet_bs32.py',
+    'configs/_base_/schedules/imagenet_bs256.py',
+    'configs/_base_/default_runtime.py',
+]
+
+# dataset settings
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='EfficientNetRandomCrop', scale=260),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='EfficientNetCenterCrop', crop_size=260),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+root@K100_AI02:/renzhc/workdir/mmpretrain# cat configs/_base_/models/tiny_efficientnet_b2.py 
+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b2'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=200,
+        in_channels=1408,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/tiny_seresnet50.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SEResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=200,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/tiny_shufflenet_v2_1x.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ShuffleNetV2', widen_factor=1.0),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=200,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))
+

densenet121-test.py

+_base_ = [
+    'configs/_base_/models/densenet/tiny_densenet121.py',
+    'configs/_base_/datasets/tiny_imagenet_bs64.py',
+    'configs/_base_/schedules/imagenet_bs256.py',
+    'configs/_base_/default_runtime.py',
+]
+
+# dataset settings
+train_dataloader = dict(batch_size=256)
+
+# schedule settings
+train_cfg = dict(by_epoch=True, max_epochs=90)
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (256 samples per GPU)
+auto_scale_lr = dict(base_batch_size=1024)
+

efficientnet-b2-test.py

+_base_ = [
+    'configs/_base_/models/tiny_efficientnet_b2.py',
+    'configs/_base_/datasets/tiny_imagenet_bs32.py',
+    'configs/_base_/schedules/imagenet_bs256.py',
+    'configs/_base_/default_runtime.py',
+]
+
+# dataset settings
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='EfficientNetRandomCrop', scale=260),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='EfficientNetCenterCrop', crop_size=260),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+

seresnet50-test.py

+_base_ = [
+    'configs/_base_/models/tiny_seresnet50.py',
+    'configs/_base_/datasets/tiny_imagenet_bs32_pil_resize.py',
+    'configs/_base_/schedules/imagenet_bs256_140e.py',
+    'configs/_base_/default_runtime.py'
+]

shufflenet-v2-test.py

+_base_ = [
+    'configs/_base_/models/tiny_shufflenet_v2_1x.py',
+    'configs/_base_/datasets/tiny_imagenet_bs64_pil_resize.py',
+    'configs/_base_/schedules/imagenet_bs1024_linearlr_bn_nowd.py',
+    'configs/_base_/default_runtime.py'
+]