GithubHelp home page GithubHelp logo

Comments (13)

dengly avatar dengly commented on May 22, 2024

python train.py --type mvocs 的 epochs是300
python train.py --type smvocs 的 epochs是100

from mobile-yolov5-pruning-distillation.

Syencil avatar Syencil commented on May 22, 2024

这描述给的信息太少了 尝试单步debug吧 我这边流程是没问题

from mobile-yolov5-pruning-distillation.

dengly avatar dengly commented on May 22, 2024

这描述给的信息太少了 尝试单步debug吧 我这边流程是没问题

确认一下我这样的操作是否正常

from mobile-yolov5-pruning-distillation.

dengly avatar dengly commented on May 22, 2024

这个是我执行的脚步

# 训练 Baseline
python train.py --type mvocs

# 稀疏 sparse learning
python3 train.py --type smvocs

# 剪枝 Pruning
python3 pruning.py -t 0.1

# 微调 finetune
python3 train.py --type fsmvocs

# 蒸馏 Distillation
python3 train.py --type dmvocs

from mobile-yolov5-pruning-distillation.

dengly avatar dengly commented on May 22, 2024

我修改了 cfg、data、weights、epochs、batch_size

from mobile-yolov5-pruning-distillation.

dengly avatar dengly commented on May 22, 2024

baseline用的模型是 mobilenet_v2-b0353104.pth,后续的都是上一次训练得到的best模型,到pruning这步就这样了。我尝试重新训练看看是否正常

from mobile-yolov5-pruning-distillation.

TongShuo-Demon avatar TongShuo-Demon commented on May 22, 2024

这个是我执行的脚步

# 训练 Baseline
python train.py --type mvocs

# 稀疏 sparse learning
python3 train.py --type smvocs

# 剪枝 Pruning
python3 pruning.py -t 0.1

# 微调 finetune
python3 train.py --type fsmvocs

# 蒸馏 Distillation
python3 train.py --type dmvocs

能问问您关于这个数据集放置的问题吗

from mobile-yolov5-pruning-distillation.

Syencil avatar Syencil commented on May 22, 2024

走debug吧 看是哪个位置错了

from mobile-yolov5-pruning-distillation.

dengly avatar dengly commented on May 22, 2024

定位的执行bn_analyze方法的plt.hist(bn_val, bins=101, align="mid", log=True, range=(0, 1.0))报错

from mobile-yolov5-pruning-distillation.

Syencil avatar Syencil commented on May 22, 2024

如果是服务器terminal应该不带显示功能吧 plt的问题

from mobile-yolov5-pruning-distillation.

dengly avatar dengly commented on May 22, 2024

定位到是matplotlib.pyplot相关方法调用报错,我注掉后使用IDEA运行正常,但是通过终端执行还是会报段错误。

from mobile-yolov5-pruning-distillation.

dengly avatar dengly commented on May 22, 2024

如果是服务器terminal应该不带显示功能吧 plt的问题

我用的是深度的系统,deepin v20

from mobile-yolov5-pruning-distillation.

TongShuo-Demon avatar TongShuo-Demon commented on May 22, 2024

test.py文件使用剪枝后的模型会报错,报错信息如下:
Traceback (most recent call last):
File "/home/demon/PycharmProjects/mobile-yolov5-pruning-distillation/test.py", line 357, in
test(opt.data,
File "/home/demon/PycharmProjects/mobile-yolov5-pruning-distillation/test.py", line 89, in test
names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
File "/home/demon/anaconda3/envs/pytorch_gpu/lib/python3.8/site-packages/torch/nn/modules/module.py", line 771, in getattr
raise ModuleAttributeError("'{}' object has no attribute '{}'".format(
torch.nn.modules.module.ModuleAttributeError: 'Model' object has no attribute 'module'

from mobile-yolov5-pruning-distillation.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.