Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

运行topformer出现好多warnning #3384

Closed
3 tasks done
loxoo6 opened this issue Jul 18, 2023 · 2 comments
Closed
3 tasks done

运行topformer出现好多warnning #3384

loxoo6 opened this issue Jul 18, 2023 · 2 comments
Assignees
@Asthestarsfalll
Labels
bug Something isn't working

Comments

@loxoo6
Copy link

loxoo6 commented Jul 18, 2023

问题确认 Search before asking

Bug描述 Describe the Bug

2023-07-18 09:20:02 [INFO]
------------Environment Information-------------
platform: Linux-4.15.0-140-generic-x86_64-with-debian-stretch-sid
Python: 3.7.4 (default, Aug 13 2019, 20:35:49) [GCC 7.3.0]
Paddle compiled with cuda: True
NVCC: Build cuda_11.2.r11.2/compiler.29618528_0
cudnn: 8.2
GPUs used: 1
CUDA_VISIBLE_DEVICES: None
GPU: ['GPU 0: Tesla V100-SXM2-32GB']
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~16.04) 7.5.0
PaddleSeg: 2.7.0
PaddlePaddle: 2.3.2
OpenCV: 4.1.1

2023-07-18 09:20:02 [INFO]
---------------Config Information---------------
batch_size: 4
export:
transforms:

  • keep_ratio: true
    size_divisor: 32
    target_size:
    • 2048
    • 512
      type: Resize
  • mean:
    • 0.485
    • 0.456
    • 0.406
      std:
    • 0.229
    • 0.224
    • 0.225
      type: Normalize
      iters: 160000
      loss:
      coef:
  • 1
    types:
  • ignore_index: 255
    type: OhemCrossEntropyLoss
    lr_scheduler:
    end_lr: 0
    learning_rate: 0.0012
    power: 1.0
    type: PolynomialDecay
    warmup_iters: 1500
    warmup_start_lr: 1.0e-06
    model:
    backbone:
    in_channels: 3
    lr_mult: 0.1
    pretrained: https://paddleseg.bj.bcebos.com/dygraph/backbone/topformer_base_imagenet_pretrained.zip
    type: TopTransformer_Base
    num_classes: 3
    type: TopFormer
    optimizer:
    type: AdamW
    weight_decay: 0.01
    train_dataset:
    dataset_root: /home/aistudio/PaddleSeg/data
    img_channels: 3
    mode: train
    num_classes: 3
    train_path: /home/aistudio/PaddleSeg/data/train_list.txt
    transforms:
  • max_scale_factor: 2.0
    min_scale_factor: 0.5
    scale_step_size: 0.25
    type: ResizeStepScaling
  • crop_size:
    • 512
    • 512
      type: RandomPaddingCrop
  • type: RandomHorizontalFlip
  • brightness_range: 0.4
    contrast_range: 0.4
    saturation_range: 0.4
    type: RandomDistort
  • mean:
    • 0.485
    • 0.456
    • 0.406
      std:
    • 0.229
    • 0.224
    • 0.225
      type: Normalize
      type: Dataset
      val_dataset:
      dataset_root: /home/aistudio/PaddleSeg/data
      img_channels: 3
      mode: val
      num_classes: 3
      transforms:
  • keep_ratio: true
    size_divisor: 32
    target_size:
    • 2048
    • 512
      type: Resize
  • mean:
    • 0.485
    • 0.456
    • 0.406
      std:
    • 0.229
    • 0.224
    • 0.225
      type: Normalize
      type: Dataset
      val_path: /home/aistudio/PaddleSeg/data/val_list.txt

W0718 09:20:02.737715 4063 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 11.2, Runtime API Version: 11.2
W0718 09:20:02.737746 4063 gpu_resources.cc:91] device: 0, cuDNN Version: 8.2.
2023-07-18 09:20:03 [INFO] Loading pretrained model from https://paddleseg.bj.bcebos.com/dygraph/backbone/topformer_base_imagenet_pretrained.zip
Connecting to https://paddleseg.bj.bcebos.com/dygraph/backbone/topformer_base_imagenet_pretrained.zip
Downloading topformer_base_imagenet_pretrained.zip
[==================================================] 100.00%
Uncompress topformer_base_imagenet_pretrained.zip
[==================================================] 100.00%
2023-07-18 09:20:04 [WARNING] SIM.1.local_embedding.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.local_embedding.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.local_embedding.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.local_embedding.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.local_embedding.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_embedding.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_embedding.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_embedding.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_embedding.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_embedding.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_act.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_act.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_act.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_act.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.1.global_act.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.local_embedding.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.local_embedding.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.local_embedding.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.local_embedding.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.local_embedding.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_embedding.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_embedding.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_embedding.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_embedding.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_embedding.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_act.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_act.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_act.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_act.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.2.global_act.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.local_embedding.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.local_embedding.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.local_embedding.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.local_embedding.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.local_embedding.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_embedding.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_embedding.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_embedding.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_embedding.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_embedding.bn._variance is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_act.conv.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_act.bn.weight is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_act.bn.bias is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_act.bn._mean is not in pretrained model
2023-07-18 09:20:04 [WARNING] SIM.3.global_act.bn._variance is not in pretrained model
2023-07-18 09:20:04 [INFO] There are 278/323 variables loaded into TopTransformer.
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/nn/layer/norm.py:654: UserWarning: When training, we now always track global mean and variance.
"When training, we now always track global mean and variance.")
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/math_op_patch.py:278: UserWarning: The dtype of left and right variables are not the same, left dtype is paddle.float32, but right dtype is paddle.int64, the right dtype will convert to paddle.float32
format(lhs_dtype, rhs_dtype, lhs_dtype))
2023-07-18 09:20:20 [INFO] [TRAIN] epoch: 1, iter: 10/160000, loss: 1.3124, lr: 0.000008, batch_cost: 1.6149, reader_cost: 1.22058, ips: 2.4770 samples/sec | ETA 71:46:05

复现环境 Environment

paddlepaddle 2.3.2
paddleseg 2.7.0
平台 aistudio

Bug描述确认 Bug description confirmation

  • 我确认已经提供了Bug复现步骤、代码改动说明、以及环境信息，确认问题是可以复现的。I confirm that the bug replication steps, code change instructions, and environment information have been provided, and the problem can be reproduced.

是否愿意提交PR？ Are you willing to submit a PR?

  • 我愿意提交PR！I'd like to help by submitting a PR!
@loxoo6 loxoo6 added the bug Something isn't working label Jul 18, 2023
@Asthestarsfalll
Copy link
Contributor

加载预训练模型时缺少权重的警告属于正常情况。

@ToddBear ToddBear mentioned this issue Jul 20, 2023
Closed
@ToddBear
Copy link
Collaborator

以上回答已经充分解答了问题，如果有新的问题欢迎随时提交issue，或者在此条issue下继续回复～
我们开启了飞桨套件的ISSUE攻关活动，欢迎感兴趣的开发者参加：PaddlePaddle/PaddleOCR#10223

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Asthestarsfalll Asthestarsfalll

Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@ToddBear @Asthestarsfalll @loxoo6