Paddlex训练自己的PP-DocLayout-L模型，模型没注册

[LoveSimons]

描述问题

paddlex.utils.errors.others.UnsupportedParamError: 'PP-DocLayout-L' is not a registered model name.

复现

1. 您是否已经正常运行我们提供的教程？
   就是使用官方的例子

2. 您是否在教程的基础上修改代码内容？还请您提供运行的代码

3. 您使用的数据集是？
   det_layout_examples

4. 请提供您出现的报错信息及相关log
   python main.py -c paddlex/configs/modules/layout_detection/PP-DocLayout-L.yaml
   -o Global.mode=train
   -o Global.dataset_dir=./dataset/det_layout_examples
   /usr/local/lib/python3.10/dist-packages/requests/init.py:113: RequestsDependencyWarning: urllib3 (2.5.0) or chardet (7.2.0)/charset_normalizer (3.4.3) doesn't match a supported version!
   warnings.warn(
   Checking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.
   Traceback (most recent call last):
   File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/repo_apis/base/config.py", line 30, in _create_config
   model_info = get_registered_model_info(model_name)
   File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/repo_apis/base/register.py", line 78, in query
   return self._table[prim_key]
   KeyError: 'PP-DocLayout-L'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/utils/result_saver.py", line 28, in wrap
result = func(self, *args, **kwargs)
File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/engine.py", line 41, in run
self._model.train()
File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/model.py", line 120, in train
trainer = build_trainer(self._config)
File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/modules/base/trainer.py", line 44, in build_trainer
return BaseTrainer.get(model_name)(config)
File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/modules/base/trainer.py", line 66, in init
self.pdx_config, self.pdx_model = build_model(
File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/modules/base/build_model.py", line 31, in build_model
config = Config(model_name, config_path)
File "/home/PaddleOCR_project/PaddleX-release-3.4/paddlex/repo_apis/base/config.py", line 32, in _create_config
raise UnsupportedParamError(
paddlex.utils.errors.others.UnsupportedParamError: 'PP-DocLayout-L' is not a registered model name.

环境

1. 请提供您使用的PaddlePaddle和PaddleX的版本号
   ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddle_3.1.0-gpu-cuda11.8-cudnn8.9
2. 请提供您使用的操作系统信息，如Linux/Windows/MacOS
   Linux
3. 请问您使用的Python版本是？
   Python 3.10.12
4. 请问您使用的CUDA/cuDNN的版本号是？
   cuda：11.8，cudnn：8.9

[liuwake]

You probably didn't install it completely! #5045

[LoveSimons]

You probably didn't install it completely! #5045
1、采用ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.3.11-paddlepaddle3.2.0-gpu-cuda11.8-cudnn8.9-trt8.6镜像也是报相同的错误
2、使用paddlex 版本3.1.1或者3.4.2也不行
3、能否提供一个稳定的docker镜像地址以及paddlex版本

[liuwake]

• I guess you haven't used the correct repo location. It should be ~/paddleX, where the version is V3.3.11, which is consistent with the version of PaddleX installed in the image (tag paddlex3.3.11-paddlepaddle3.2.0-gpu-cuda11.8-cudnn8.9-trt8.6).
• docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.3.11-paddlepaddle3.2.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash's log:

root@WK-E3:~/PaddleX# ls
LICENSE  README.md  README_en.md  api_examples  deploy  docs  install_pdx.py  main.py  mkdocs.yml  overrides  paddlex  paddlex.egg-info  setup.py
root@WK-E3:~/PaddleX# pwd
/root/PaddleX
root@WK-E3:~/PaddleX# cat /etc/os-release 
PRETTY_NAME="Ubuntu 22.04.5 LTS"
NAME="Ubuntu"
VERSION_ID="22.04"
VERSION="22.04.5 LTS (Jammy Jellyfish)"
VERSION_CODENAME=jammy
ID=ubuntu
ID_LIKE=debian
HOME_URL="https://www.ubuntu.com/"
SUPPORT_URL="https://help.ubuntu.com/"
BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
UBUNTU_CODENAME=jammy
root@WK-E3:~/PaddleX# df -h
Filesystem      Size  Used Avail Use% Mounted on
overlay         203G  179G   15G  93% /
tmpfs            64M     0   64M   0% /dev
shm             8.0G     0  8.0G   0% /dev/shm
/dev/sda2       203G  179G   15G  93% /usr/bin/nvidia-smi
tmpfs           4.0K  4.0K     0 100% /run/nvidia-ctk-hook071b5691-69c5-4749-a20d-db3dd08f9266
tmpfs           7.8G     0  7.8G   0% /proc/acpi
tmpfs           7.8G     0  7.8G   0% /proc/asound
tmpfs           7.8G     0  7.8G   0% /proc/scsi
tmpfs           7.8G     0  7.8G   0% /sys/devices/virtual/powercap
tmpfs           7.8G     0  7.8G   0% /sys/firmware
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu0/thermal_throttle
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu1/thermal_throttle
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu2/thermal_throttle
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu3/thermal_throttle
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu4/thermal_throttle
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu5/thermal_throttle
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu6/thermal_throttle
tmpfs           7.8G     0  7.8G   0% /sys/devices/system/cpu/cpu7/thermal_throttle
root@WK-E3:~/PaddleX# git status
HEAD detached at v3.3.11

[liuwake]

I just tested it on a virtual machine with an NVIDIA T4, you can also try the commands in the log below.

click to open/close the log

➜  /workspace git:(master) ✗ docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.3.11-paddlepaddle3.2.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
Unable to find image 'ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.3.11-paddlepaddle3.2.0-gpu-cuda11.8-cudnn8.9-trt8.6' locally
paddlex3.3.11-paddlepaddle3.2.0-gpu-cuda11.8-cudnn8.9-trt8.6: Pulling from paddlex/paddlex
43f89b94cd7d: Pulling fs layer 
5e3b7ee77381: Pulling fs layer 
5bd037f007fd: Pulling fs layer 
4cda774ad2ec: Waiting 
775f22adee62: Waiting 
263fc748118f: Pull complete 
16c36d0187d0: Pull complete 
e7a56570655c: Pull complete 
507fc9045cba: Pull complete 
23b7d8e07c16: Pull complete 
922ac8fcb889: Pull complete 
68075f2beca1: Pull complete 
77903c550e33: Pull complete 
4f4fb700ef54: Pull complete 
1b25f290dcfc: Pull complete 
5088e88ff309: Pull complete 
f3598f6caca1: Pull complete 
fbbe52feab6e: Pull complete 
c9e399a0835f: Pull complete 
84d4d5821d16: Pull complete 
c4973d088e09: Pull complete 
8dbccfa75db3: Pull complete 
a69058544a3d: Pull complete 
214e2e9532f6: Pull complete 
8fea29303322: Pull complete 
3cf49095b75b: Pull complete 
acdb2d0d54cf: Pull complete 
883119cf90b0: Pull complete 
e34b32e53d6d: Pull complete 
477457e90e2b: Pull complete 
719a1474e36e: Pull complete 
9f66d3360e20: Pull complete 
e53d03a59747: Pull complete 
3b0d2e0a70ac: Pull complete 
b82917d4a53a: Pull complete 
ba16b858fef8: Pull complete 
d8ecdd13f0a4: Pull complete 
a16b9ad2fba9: Pull complete 
c2f3aed1da1a: Pull complete 
6cdbb655e45f: Pull complete 
bef9894a9177: Pull complete 
f08768a2cced: Pull complete 
Digest: sha256:5db6ad0a43265952b0d2cf71dc9e066fa004510be019a00dee7992d223e0bcb2
Status: Downloaded newer image for ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.3.11-paddlepaddle3.2.0-gpu-cuda11.8-cudnn8.9-trt8.6

==========
== CUDA ==
==========

CUDA Version 11.8.0

Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.

root@b1f574a379c6:~/PaddleX# wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/det_layout_examples.tar -P ./dataset
tar -xf ./dataset/det_layout_examples.tar -C ./dataset/
python main.py -c paddlex/configs/modules/layout_detection/PP-DocLayout-L.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/det_layout_examples

sed -i 's/device: gpu:0,1,2,3/device: gpu/' paddlex/configs/modules/layout_detection/PP-DocLayout-L.yaml 

python main.py -c paddlex/configs/modules/layout_detection/PP-DocLayout-L.yaml \
    -o Global.mode=train \
    -o Global.dataset_dir=./dataset/det_layout_examples
--2026-03-21 16:14:38--  https://paddle-model-ecology.bj.bcebos.com/paddlex/data/det_layout_examples.tar
Resolving paddle-model-ecology.bj.bcebos.com (paddle-model-ecology.bj.bcebos.com)... 36.110.192.67, 36.110.192.178
Connecting to paddle-model-ecology.bj.bcebos.com (paddle-model-ecology.bj.bcebos.com)|36.110.192.67|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 41809920 (40M) [application/octet-stream]
Saving to: './dataset/det_layout_examples.tar'

det_layout_examples.tar   100%[=====================================>]  39.87M  11.1MB/s    in 12s     

2026-03-21 16:14:50 (3.42 MB/s) - './dataset/det_layout_examples.tar' saved [41809920/41809920]

Checking connectivity to the model hosters, this may take a while. To bypass this check, set `DISABLE_MODEL_SOURCE_CHECK` to `True`.
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Check dataset passed !
Checking connectivity to the model hosters, this may take a while. To bypass this check, set `DISABLE_MODEL_SOURCE_CHECK` to `True`.
['/usr/bin/python', 'tools/train.py', '--eval', '--config', '/root/.paddlex/tmp23v0c7uc/detmodel_PP-DocLayout-L.yml', '--use_vdl', 'True', '--vdl_log_dir', '/root/PaddleX/output']

Log path: /root/PaddleX/output/train.log 

[03/21 16:15:04] ppdet.utils.checkpoint INFO: Skipping import of the encryption module.
======================= Modified FLAGS detected =======================
FLAGS(name='FLAGS_cusolver_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/cusolver/lib', default_value='')
FLAGS(name='FLAGS_enable_pir_in_executor', current_value=True, default_value=False)
FLAGS(name='FLAGS_cupti_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/cuda_cupti/lib', default_value='')
FLAGS(name='FLAGS_cublas_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/cublas/lib', default_value='')
FLAGS(name='FLAGS_cusparse_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/cusparse/lib', default_value='')
FLAGS(name='FLAGS_cuda_cccl_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/cuda_cccl/include/', default_value='')
FLAGS(name='FLAGS_curand_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/curand/lib', default_value='')
FLAGS(name='FLAGS_nccl_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/nccl/lib', default_value='')
FLAGS(name='FLAGS_cudnn_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia/cudnn/lib', default_value='')
FLAGS(name='FLAGS_nvidia_package_dir', current_value='/usr/local/lib/python3.10/dist-packages/paddle/../nvidia', default_value='')
=======================================================================
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
[03/21 16:15:04] ppdet.data.source.coco INFO: Load [90 samples valid, 0 samples invalid] in file /root/PaddleX/dataset/det_layout_examples/annotations/instance_train.json.
W0321 16:15:04.929369   123 gpu_resources.cc:114] Please NOTE: device: 0, GPU Compute Capability: 7.5, Driver API Version: 13.0, Runtime API Version: 11.8
use cuda ms_deformable_attn op!
[03/21 16:15:05] ppdet.utils.download INFO: Downloading PP-DocLayout-L_pretrained.pdparams from https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-DocLayout-L_pretrained.pdparams
100%|██████████| 128688/128688 [00:13<00:00, 9583.91KB/s] 
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23] in pretrained weight transformer.dec_score_head.0.bias is unmatched with the shape [11] in model transformer.dec_score_head.0.bias. And the weight transformer.dec_score_head.0.bias will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [256, 23] in pretrained weight transformer.dec_score_head.0.weight is unmatched with the shape [256, 11] in model transformer.dec_score_head.0.weight. And the weight transformer.dec_score_head.0.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23] in pretrained weight transformer.dec_score_head.1.bias is unmatched with the shape [11] in model transformer.dec_score_head.1.bias. And the weight transformer.dec_score_head.1.bias will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [256, 23] in pretrained weight transformer.dec_score_head.1.weight is unmatched with the shape [256, 11] in model transformer.dec_score_head.1.weight. And the weight transformer.dec_score_head.1.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23] in pretrained weight transformer.dec_score_head.2.bias is unmatched with the shape [11] in model transformer.dec_score_head.2.bias. And the weight transformer.dec_score_head.2.bias will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [256, 23] in pretrained weight transformer.dec_score_head.2.weight is unmatched with the shape [256, 11] in model transformer.dec_score_head.2.weight. And the weight transformer.dec_score_head.2.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23] in pretrained weight transformer.dec_score_head.3.bias is unmatched with the shape [11] in model transformer.dec_score_head.3.bias. And the weight transformer.dec_score_head.3.bias will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [256, 23] in pretrained weight transformer.dec_score_head.3.weight is unmatched with the shape [256, 11] in model transformer.dec_score_head.3.weight. And the weight transformer.dec_score_head.3.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23] in pretrained weight transformer.dec_score_head.4.bias is unmatched with the shape [11] in model transformer.dec_score_head.4.bias. And the weight transformer.dec_score_head.4.bias will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [256, 23] in pretrained weight transformer.dec_score_head.4.weight is unmatched with the shape [256, 11] in model transformer.dec_score_head.4.weight. And the weight transformer.dec_score_head.4.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23] in pretrained weight transformer.dec_score_head.5.bias is unmatched with the shape [11] in model transformer.dec_score_head.5.bias. And the weight transformer.dec_score_head.5.bias will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [256, 23] in pretrained weight transformer.dec_score_head.5.weight is unmatched with the shape [256, 11] in model transformer.dec_score_head.5.weight. And the weight transformer.dec_score_head.5.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23, 256] in pretrained weight transformer.denoising_class_embed.weight is unmatched with the shape [11, 256] in model transformer.denoising_class_embed.weight. And the weight transformer.denoising_class_embed.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [23] in pretrained weight transformer.enc_score_head.bias is unmatched with the shape [11] in model transformer.enc_score_head.bias. And the weight transformer.enc_score_head.bias will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: The shape [256, 23] in pretrained weight transformer.enc_score_head.weight is unmatched with the shape [256, 11] in model transformer.enc_score_head.weight. And the weight transformer.enc_score_head.weight will not be loaded
[03/21 16:15:19] ppdet.utils.checkpoint INFO: Finish loading model weights: /root/.cache/paddle/weights/PP-DocLayout-L_pretrained.pdparams
W0321 16:15:21.440558   123 gpu_resources.cc:243] WARNING: device: 0. The installed Paddle is compiled with CUDNN 8.9, but CUDNN version in your machine is 8.9, which may cause serious incompatible bug. Please recompile or reinstall Paddle with compatible CUDNN version.
[03/21 16:15:22] ppdet.engine.callbacks INFO: Epoch: [0] [ 0/90] learning_rate: 0.000000 loss_class: 1.111615 loss_bbox: 0.572765 loss_giou: 1.822678 loss_class_aux: 5.157219 loss_bbox_aux: 3.715603 loss_giou_aux: 12.114563 loss_class_dn: 3.100894 loss_bbox_dn: 0.087651 loss_giou_dn: 0.424630 loss_class_aux_dn: 13.913855 loss_bbox_aux_dn: 0.627241 loss_giou_aux_dn: 2.731527 loss: 45.380238 eta: 6:52:19 batch_cost: 2.7488 data_cost: 1.6119 ips: 0.3638 images/s, max_mem_reserved: 1617 MB, max_mem_allocated: 1504 MB
[03/21 16:15:25] ppdet.engine.callbacks INFO: Epoch: [0] [10/90] learning_rate: 0.000010 loss_class: 1.643281 loss_bbox: 0.481373 loss_giou: 1.134519 loss_class_aux: 6.879665 loss_bbox_aux: 4.398883 loss_giou_aux: 8.244202 loss_class_dn: 2.951838 loss_bbox_dn: 0.200228 loss_giou_dn: 0.437132 loss_class_aux_dn: 14.228263 loss_bbox_aux_dn: 1.271684 loss_giou_aux_dn: 2.544119 loss: 45.997862 eta: 1:16:31 batch_cost: 0.2869 data_cost: 0.0007 ips: 3.4859 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:29] ppdet.engine.callbacks INFO: Epoch: [0] [20/90] learning_rate: 0.000020 loss_class: 2.009199 loss_bbox: 0.706018 loss_giou: 0.857642 loss_class_aux: 9.291114 loss_bbox_aux: 5.192491 loss_giou_aux: 6.738941 loss_class_dn: 2.826166 loss_bbox_dn: 0.379483 loss_giou_dn: 0.480263 loss_class_aux_dn: 13.564871 loss_bbox_aux_dn: 2.094603 loss_giou_aux_dn: 2.658021 loss: 48.268028 eta: 1:02:20 batch_cost: 0.3129 data_cost: 0.0008 ips: 3.1961 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:33] ppdet.engine.callbacks INFO: Epoch: [0] [30/90] learning_rate: 0.000030 loss_class: 2.201477 loss_bbox: 0.478392 loss_giou: 0.714998 loss_class_aux: 11.555306 loss_bbox_aux: 3.437716 loss_giou_aux: 5.679903 loss_class_dn: 3.032750 loss_bbox_dn: 0.138536 loss_giou_dn: 0.346094 loss_class_aux_dn: 14.651436 loss_bbox_aux_dn: 1.173243 loss_giou_aux_dn: 2.117421 loss: 44.628531 eta: 0:57:55 batch_cost: 0.3263 data_cost: 0.0009 ips: 3.0645 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:36] ppdet.engine.callbacks INFO: Epoch: [0] [40/90] learning_rate: 0.000040 loss_class: 2.229090 loss_bbox: 0.173090 loss_giou: 0.571521 loss_class_aux: 11.043964 loss_bbox_aux: 2.520337 loss_giou_aux: 5.520443 loss_class_dn: 2.575305 loss_bbox_dn: 0.190201 loss_giou_dn: 0.328726 loss_class_aux_dn: 13.775351 loss_bbox_aux_dn: 1.361255 loss_giou_aux_dn: 2.069546 loss: 47.499804 eta: 0:54:02 batch_cost: 0.2829 data_cost: 0.0007 ips: 3.5348 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:39] ppdet.engine.callbacks INFO: Epoch: [0] [50/90] learning_rate: 0.000050 loss_class: 1.823043 loss_bbox: 0.433065 loss_giou: 0.774667 loss_class_aux: 10.056700 loss_bbox_aux: 3.677701 loss_giou_aux: 6.197308 loss_class_dn: 2.704143 loss_bbox_dn: 0.148964 loss_giou_dn: 0.273296 loss_class_aux_dn: 14.034156 loss_bbox_aux_dn: 0.989512 loss_giou_aux_dn: 1.705506 loss: 42.594671 eta: 0:51:45 batch_cost: 0.2859 data_cost: 0.0007 ips: 3.4976 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:42] ppdet.engine.callbacks INFO: Epoch: [0] [60/90] learning_rate: 0.000060 loss_class: 1.913928 loss_bbox: 0.096257 loss_giou: 0.197053 loss_class_aux: 14.275694 loss_bbox_aux: 1.574065 loss_giou_aux: 2.256152 loss_class_dn: 1.857390 loss_bbox_dn: 0.423247 loss_giou_dn: 0.434687 loss_class_aux_dn: 10.680800 loss_bbox_aux_dn: 2.454099 loss_giou_aux_dn: 2.361026 loss: 40.610449 eta: 0:49:26 batch_cost: 0.2544 data_cost: 0.0007 ips: 3.9316 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:45] ppdet.engine.callbacks INFO: Epoch: [0] [70/90] learning_rate: 0.000070 loss_class: 1.693841 loss_bbox: 0.506146 loss_giou: 0.491365 loss_class_aux: 11.231901 loss_bbox_aux: 3.671714 loss_giou_aux: 3.977117 loss_class_dn: 1.386910 loss_bbox_dn: 0.212983 loss_giou_dn: 0.291837 loss_class_aux_dn: 8.804747 loss_bbox_aux_dn: 1.887749 loss_giou_aux_dn: 1.755829 loss: 35.916925 eta: 0:48:05 batch_cost: 0.2703 data_cost: 0.0007 ips: 3.6995 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:48] ppdet.engine.callbacks INFO: Epoch: [0] [80/90] learning_rate: 0.000080 loss_class: 2.151815 loss_bbox: 0.394200 loss_giou: 0.654384 loss_class_aux: 11.178319 loss_bbox_aux: 2.936491 loss_giou_aux: 4.981375 loss_class_dn: 2.425395 loss_bbox_dn: 0.149108 loss_giou_dn: 0.224439 loss_class_aux_dn: 12.220545 loss_bbox_aux_dn: 1.033307 loss_giou_aux_dn: 1.478901 loss: 40.214418 eta: 0:46:49 batch_cost: 0.2568 data_cost: 0.0007 ips: 3.8944 images/s, max_mem_reserved: 2209 MB, max_mem_allocated: 2082 MB
[03/21 16:15:52] ppdet.utils.checkpoint INFO: Save checkpoint: /root/PaddleX/output/0
W0321 16:15:55.021495   123 eager_utils.cc:3441] Paddle static graph(PIR) not support input out tensor for now!!!!!
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
[03/21 16:16:01] ppdet.engine INFO: Export inference config file to /root/PaddleX/output/0/inference/inference.yml
[03/21 16:16:01] ppdet.engine INFO: Skipping import of the encryption module.
[03/21 16:16:01] ppdet.engine INFO: Export model and saved in /root/PaddleX/output/0/inference
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
[03/21 16:16:01] ppdet.data.source.coco INFO: Load [20 samples valid, 0 samples invalid] in file /root/PaddleX/dataset/det_layout_examples/annotations/instance_val.json.
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
[03/21 16:16:02] ppdet.engine.callbacks INFO: Eval iter: 0
[03/21 16:16:03] ppdet.metrics.metrics INFO: The bbox result is saved to bbox.json.
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
[03/21 16:16:03] ppdet.metrics.coco_utils INFO: Start evaluate...
Loading and preparing results...
DONE (t=0.03s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=0.27s).
Accumulating evaluation results...
DONE (t=0.08s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.068
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.087
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.070
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.097
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.083
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.134
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.084
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.176
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.193
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.143
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.272
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.210
[03/21 16:16:03] ppdet.engine.callbacks INFO: Total sample number: 20, average FPS: 13.161456046072427
[03/21 16:16:03] ppdet.utils.checkpoint INFO: Already save model info in /root/PaddleX/output/0
[03/21 16:16:03] ppdet.utils.checkpoint INFO: Already save model info in /root/PaddleX/output/best_model
[03/21 16:16:03] ppdet.engine INFO: Best test bbox ap is 0.068.
[03/21 16:16:05] ppdet.utils.checkpoint INFO: Save checkpoint: /root/PaddleX/output/best_model
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
[03/21 16:16:12] ppdet.engine INFO: Export inference config file to /root/PaddleX/output/best_model/inference/inference.yml
[03/21 16:16:12] ppdet.engine INFO: Skipping import of the encryption module.
[03/21 16:16:12] ppdet.engine INFO: Export model and saved in /root/PaddleX/output/best_model/inference
[03/21 16:16:13] ppdet.engine.callbacks INFO: Epoch: [1] [ 0/90] learning_rate: 0.000090 loss_class: 1.451562 loss_bbox: 0.389225 loss_giou: 1.077242 loss_class_aux: 7.303786 loss_bbox_aux: 3.347795 loss_giou_aux: 7.226761 loss_class_dn: 1.657016 loss_bbox_dn: 0.119677 loss_giou_dn: 0.250323 loss_class_aux_dn: 10.162858 loss_bbox_aux_dn: 0.896282 loss_giou_aux_dn: 1.626001 loss: 36.383259 eta: 0:46:20 batch_cost: 0.2887 data_cost: 0.0326 ips: 3.4634 images/s, max_mem_reserved: 2491 MB, max_mem_allocated: 2082 MB