RuntimeError: mat1 and mat2 shapes cannot be multiplied (286720x7 and 1280x3)

[wenshuyuan]

i want to utlize mobilenet v2 to train my own data.
i dont know what cause the error.
my config are as follows :

my_mobilenet_v2_3_classes.py

base = [
'../base/models/mobilenet_v2_1x.py',
#'../base/datasets/imagenet_bs32_pil_resize.py',

'../_base_/schedules/imagenet_bs256_epochstep.py',
'../_base_/default_runtime.py'

]

dataset settings

dataset_type = 'ImageNet'
data_preprocessor = dict(

# 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='Resize', scale=224),
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='Resize', scale=224),
dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
dict(type='CenterCrop', crop_size=224),
dict(type='PackInputs'),

]

train_dataloader = dict(
batch_size=32,
num_workers=5,
dataset=dict(
type=dataset_type,
data_root='F:/研究生课程/mission/project/mmpretrain-main/datasets/clahe',
split='train',
pipeline=train_pipeline),
sampler=dict(type='DefaultSampler', shuffle=True),
)

val_dataloader = dict(
batch_size=32,
num_workers=5,
dataset=dict(
type=dataset_type,
data_root='F:/研究生课程/mission/project/mmpretrain-main/datasets/clahe',
split='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

修改模型相关配置

model = dict(
type='ImageClassifier',
backbone=dict(
type='MobileNetV2',
#scale=1.0
#width_mult=1.0
),
neck=None,
head=dict(
type='LinearClsHead',
num_classes=3,
in_channels=1280,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
)
)

修改训练相关配置

lr_config = dict(
policy='step',
step=[30, 60, 90],
gamma=0.1
)
runner = dict(
type='EpochBasedRunner',
max_epochs=100
)