Paddle 自己配置yolov4_mobilenet_v3配置权重以及训练损失的问题

nx7onnlm  于 2021-11-30  发布在  Java
关注(0)|答案(5)|浏览(433)

配置权重配置的https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar 这个是对的吗?还想问这串地址自己写的时候该怎么填,paddle默认的模型库能出来这个url地址吗?训练损失在训练了近5000iter损失还有几百,这是正常现象吗?还是我哪里配置错了

ki1q1bka

ki1q1bka1#

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IssueAI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 APIFAQGithub Issue and AI community to get the answer.Have a nice day!

nom7f22z

nom7f22z2#

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。

i2loujxw

i2loujxw3#

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.

qkf9rpyu

qkf9rpyu4#

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
6uxekuva

6uxekuva5#

请问你是使用的单卡训练还是多卡训练?

相关问题