norm_cfg = dict(type="BN", requires_grad=True)
model = dict(
type="EncoderDecoder",
pretrained="open-mmlab://resnet50_v1c",
backbone=dict(
type="ResNetV1c",
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 1, 1),
strides=(1, 2, 2, 2),
norm_cfg=norm_cfg,
norm_eval=False,
style="pytorch",
contract_dilation=True,
),
neck=dict(
type="FPN", in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=4
),
decode_head=dict(
type="FPNHead",
in_channels=[256, 256, 256, 256],
in_index=[0, 1, 2, 3],
feature_strides=[4, 8, 16, 32],
channels=128,
dropout_ratio=0.1,
num_classes={{cookiecutter.num_classes}},
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0),
),
)
train_cfg = dict() # type: ignore
test_cfg = dict(mode="whole")
load_from = "/media/VA/pretrained_weights/mmseg/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth"