您好，我们已经收到了您的问题，会安排技术人员尽快解答您的问题，请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时，您也可以通过查看官网API文档、常见问题、历史Issue、AI社区来寻求解答。祝您生活愉快～

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API，FAQ，Github Issue and AI community to get the answer.Have a nice day!

可以配置，PaddleDetection 可以解析出来，可以看下你的配置文件是什么，https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/static/configs/yolov4 yolov4的配置可以参考这个。

麻烦您帮我看一下我的配置哪里有问题，我训练了一万二iter，mAP才0.2%…

------------------ 原始邮件 ------------------ 发件人: "PaddlePaddle/Paddle"***@***.***>; 发送时间: 2021年9月9日(星期四) 中午1:44***@***.***>;***@***.******@***.***>; 主题: Re: [PaddlePaddle/Paddle] 自己配置yolov4_mobilenet_v3配置权重以及训练损失的问题 (#35607) 可以配置，PaddleDetection 可以解析出来，可以看下你的配置文件是什么，https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/static/configs/yolov4 yolov4的配置可以参考这个。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

architecture: YOLOv4
use_gpu: true
max_iters: 50000
log_iter: 20
save_dir: output
snapshot_iter: 2000
metric: VOC
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar
weights: output/yolov4_mobilenet_v3_voc/model_final
num_classes: 1
use_fine_grained_loss: false

YOLOv4:
backbone: MobileNetV3
yolo_head: YOLOv4Head

MobileNetV3:
norm_type: sync_bn
norm_decay: 0.
model_name: large
scale: 1.
extra_block_filters: []
feature_maps: [1, 2, 3, 4, 6]

YOLOv4Head:
anchors: [[12, 16], [19, 36], [40, 28], [36, 75], [76, 55],
[72, 146], [142, 110], [192, 243], [459, 401]]
anchor_masks: [[0, 1, 2], [3, 4, 5], [6, 7, 8]]
yolo_loss: YOLOv3Loss
nms:
background_label: -1
keep_top_k: -1
nms_threshold: 0.45
nms_top_k: -1
normalized: true
score_threshold: 0.001
downsample: [8,16,32]
scale_x_y: [1.2, 1.1, 1.05]

YOLOv3Loss:
ignore_thresh: 0.7
label_smooth: false

LearningRate:
base_lr: 0.0001
schedulers:

• !PiecewiseDecay

gamma: 0.1
milestones:

• 400000
• 450000
• !LinearWarmup

start_factor: 0.
steps: 4000

OptimizerBuilder:
clip_grad_by_norm: 10.
optimizer:
momentum: 0.949
type: Momentum
regularizer:
factor: 0.0005
type: L2

• READER*: 'yolov3_reader.yml'

TrainReader:
inputs_def:
fields: ['image', 'gt_bbox', 'gt_class', 'gt_score', 'im_id']
num_max_boxes: 50
dataset:
!VOCDataSet
anno_path: trainval.txt
dataset_dir: dataset/voc
with_background: false
sample_transforms:

• !DecodeImage
  to_rgb: True
• !ColorDistort {}
• !RandomExpand
  fill_value: [123.675, 116.28, 103.53]
• !RandomCrop {}
• !RandomFlipImage
  is_normalized: false
• !NormalizeBox {}
• !PadBox
  num_max_boxes: 50
• !BboxXYXY2XYWH {}
  batch_transforms:

• !RandomShape

sizes: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
random_inter: True

• !NormalizeImage

mean: [0.,0.,0.]
std: [1.,1.,1.]
is_scale: True
is_channel_first: false

• !Permute

to_bgr: false
channel_first: True

Gt2YoloTarget is only used when use_fine_grained_loss set as true,

this operator will be deleted automatically if use_fine_grained_loss

is set as false

• !Gt2YoloTarget

anchor_masks: [[0, 1, 2], [3, 4, 5], [6, 7, 8]]
anchors: [[12, 16], [19, 36], [40, 28],
[36, 75], [76, 55], [72, 146],
[142, 110], [192, 243], [459, 401]]
downsample_ratios: [8, 16, 32]
batch_size: 16
shuffle: true
drop_last: true
worker_num: 8
bufsize: 16
use_process: true
drop_empty: false

EvalReader:
inputs_def:
fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']
num_max_boxes: 90
dataset:
!VOCDataSet
anno_path: test.txt
dataset_dir: dataset/voc
use_default_label: true
with_background: false
sample_transforms:

• !DecodeImage
  to_rgb: True
• !ResizeImage
  target_size: 608
  interp: 1
• !NormalizeImage
  mean: [0., 0., 0.]
  std: [1., 1., 1.]
  is_scale: True
  is_channel_first: false
• !PadBox
  num_max_boxes: 90
• !Permute
  to_bgr: false
  channel_first: True
  batch_size: 16
  drop_empty: false
  worker_num: 8
  bufsize: 16

TestReader:
dataset:
!ImageFolder
use_default_label: true
with_background: false
sample_transforms:

• !DecodeImage
  to_rgb: True
• !ResizeImage
  target_size: 608
  interp: 1
• !NormalizeImage
  mean: [0., 0., 0.]
  std: [1., 1., 1.]
  is_scale: True
  is_channel_first: false
• !Permute
  to_bgr: false
  channel_first: True

请问你是使用的单卡训练还是多卡训练？