78 lines
1.2 KiB
YAML
78 lines
1.2 KiB
YAML
task: detection
|
|
|
|
model: RTDETR
|
|
criterion: SetCriterion
|
|
postprocessor: RTDETRPostProcessor
|
|
|
|
|
|
RTDETR:
|
|
backbone: RegNet
|
|
encoder: HybridEncoder
|
|
decoder: RTDETRTransformer
|
|
multi_scale: [480, 512, 544, 576, 608, 640, 640, 640, 672, 704, 736, 768, 800]
|
|
|
|
|
|
RegNet:
|
|
return_idx: [1, 2, 3]
|
|
configuration: RegNetConfig()
|
|
|
|
HybridEncoder:
|
|
in_channels: [192, 512, 1088]
|
|
feat_strides: [8, 16, 32]
|
|
|
|
# intra
|
|
hidden_dim: 256
|
|
use_encoder_idx: [2]
|
|
num_encoder_layers: 1
|
|
nhead: 8
|
|
dim_feedforward: 1024
|
|
dropout: 0.
|
|
enc_act: 'gelu'
|
|
pe_temperature: 10000
|
|
|
|
# cross
|
|
expansion: 1.0
|
|
depth_mult: 1
|
|
act: 'silu'
|
|
|
|
# eval
|
|
eval_spatial_size: [640, 640]
|
|
|
|
|
|
RTDETRTransformer:
|
|
feat_channels: [256, 256, 256]
|
|
feat_strides: [8, 16, 32]
|
|
hidden_dim: 256
|
|
num_levels: 3
|
|
|
|
num_queries: 300
|
|
|
|
num_decoder_layers: 6
|
|
num_denoising: 100
|
|
|
|
eval_idx: -1
|
|
eval_spatial_size: [640, 640]
|
|
|
|
|
|
use_focal_loss: True
|
|
|
|
RTDETRPostProcessor:
|
|
num_top_queries: 300
|
|
|
|
|
|
SetCriterion:
|
|
weight_dict: {loss_vfl: 1, loss_bbox: 5, loss_giou: 2,}
|
|
losses: ['vfl', 'boxes', ]
|
|
alpha: 0.75
|
|
gamma: 2.0
|
|
|
|
matcher:
|
|
type: HungarianMatcher
|
|
weight_dict: {cost_class: 2, cost_bbox: 5, cost_giou: 2}
|
|
# use_focal_loss: True
|
|
alpha: 0.25
|
|
gamma: 2.0
|
|
|
|
|
|
|