tingsongyu / ghostnet_cifar10 Goto Github PK
View Code? Open in Web Editor NEWghostnet_cifar10
ghostnet_cifar10
运行python bin/02_main.py -gpu 1 0 -arc vgg16 -replace_conv进行训练提示:Traceback (most recent call last): File "bin/02_main.py", line 17, in from models.ghost_net import GhostModule ModuleNotFoundError: No module named 'models.ghost_net', 在models文件夹里面存在ghost_net,这是什么原因呢?
Hi Mr. Yu,
Thank you for your marvelous work!
Could you make a tutorial in detail about how to train with custom datasets?
可不可以在提供下百度模型连接的网盘,非常感谢
将data内的数据替换成自己的数据集
Have you modified the 1st conv layer to Ghost module? We did not touch the 1st conv in our experiments.
Hello, how to test the model ? May you provide the test code?
Thank you very much.
请问在bin/02_main.py中用ghostnet替换卷积层时用到的replace_conv()定义在哪里了呢?
Traceback (most recent call last):
File "bin/04_fmap_vis.py", line 48, in
model.load_state_dict(state_dict_cpu)
File "/home/ysq/文档/ghostnet_cifar10-master/venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1406, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for VGG:
Missing key(s) in state_dict: "features.0.primary_conv.0.weight", "features.0.primary_conv.1.weight", "features.0.primary_conv.1.bias", "features.0.primary_conv.1.running_mean", "features.0.primary_conv.1.running_var", "features.0.cheap_operation.0.weight", "features.0.cheap_operation.1.weight", "features.0.cheap_operation.1.bias", "features.0.cheap_operation.1.running_mean", "features.0.cheap_operation.1.running_var", "features.1.weight", "features.1.bias", "features.1.running_mean", "features.1.running_var", "features.3.primary_conv.0.weight", "features.3.primary_conv.1.weight", "features.3.primary_conv.1.bias", "features.3.primary_conv.1.running_mean", "features.3.primary_conv.1.running_var", "features.3.cheap_operation.0.weight", "features.3.cheap_operation.1.weight", "features.3.cheap_operation.1.bias", "features.3.cheap_operation.1.running_mean", "features.3.cheap_operation.1.running_var", "features.4.weight", "features.4.bias", "features.4.running_mean", "features.4.running_var", "features.7.primary_conv.0.weight", "features.7.primary_conv.1.weight", "features.7.primary_conv.1.bias", "features.7.primary_conv.1.running_mean", "features.7.primary_conv.1.running_var", "features.7.cheap_operation.0.weight", "features.7.cheap_operation.1.weight", "features.7.cheap_operation.1.bias", "features.7.cheap_operation.1.running_mean", "features.7.cheap_operation.1.running_var", "features.8.weight", "features.8.bias", "features.8.running_mean", "features.8.running_var", "features.10.primary_conv.0.weight", "features.10.primary_conv.1.weight", "features.10.primary_conv.1.bias", "features.10.primary_conv.1.running_mean", "features.10.primary_conv.1.running_var", "features.10.cheap_operation.0.weight", "features.10.cheap_operation.1.weight", "features.10.cheap_operation.1.bias", "features.10.cheap_operation.1.running_mean", "features.10.cheap_operation.1.running_var", "features.11.weight", "features.11.bias", "features.11.running_mean", "features.11.running_var", "features.14.primary_conv.0.weight", "features.14.primary_conv.1.weight", "features.14.primary_conv.1.bias", "features.14.primary_conv.1.running_mean", "features.14.primary_conv.1.running_var", "features.14.cheap_operation.0.weight", "features.14.cheap_operation.1.weight", "features.14.cheap_operation.1.bias", "features.14.cheap_operation.1.running_mean", "features.14.cheap_operation.1.running_var", "features.15.weight", "features.15.bias", "features.15.running_mean", "features.15.running_var", "features.17.primary_conv.0.weight", "features.17.primary_conv.1.weight", "features.17.primary_conv.1.bias", "features.17.primary_conv.1.running_mean", "features.17.primary_conv.1.running_var", "features.17.cheap_operation.0.weight", "features.17.cheap_operation.1.weight", "features.17.cheap_operation.1.bias", "features.17.cheap_operation.1.running_mean", "features.17.cheap_operation.1.running_var", "features.18.weight", "features.18.bias", "features.18.running_mean", "features.18.running_var", "features.20.primary_conv.0.weight", "features.20.primary_conv.1.weight", "features.20.primary_conv.1.bias", "features.20.primary_conv.1.running_mean", "features.20.primary_conv.1.running_var", "features.20.cheap_operation.0.weight", "features.20.cheap_operation.1.weight", "features.20.cheap_operation.1.bias", "features.20.cheap_operation.1.running_mean", "features.20.cheap_operation.1.running_var", "features.21.weight", "features.21.bias", "features.21.running_mean", "features.21.running_var", "features.24.primary_conv.0.weight", "features.24.primary_conv.1.weight", "features.24.primary_conv.1.bias", "features.24.primary_conv.1.running_mean", "features.24.primary_conv.1.running_var", "features.24.cheap_operation.0.weight", "features.24.cheap_operation.1.weight", "features.24.cheap_operation.1.bias", "features.24.cheap_operation.1.running_mean", "features.24.cheap_operation.1.running_var", "features.25.weight", "features.25.bias", "features.25.running_mean", "features.25.running_var", "features.27.primary_conv.0.weight", "features.27.primary_conv.1.weight", "features.27.primary_conv.1.bias", "features.27.primary_conv.1.running_mean", "features.27.primary_conv.1.running_var", "features.27.cheap_operation.0.weight", "features.27.cheap_operation.1.weight", "features.27.cheap_operation.1.bias", "features.27.cheap_operation.1.running_mean", "features.27.cheap_operation.1.running_var", "features.28.weight", "features.28.bias", "features.28.running_mean", "features.28.running_var", "features.30.primary_conv.0.weight", "features.30.primary_conv.1.weight", "features.30.primary_conv.1.bias", "features.30.primary_conv.1.running_mean", "features.30.primary_conv.1.running_var", "features.30.cheap_operation.0.weight", "features.30.cheap_operation.1.weight", "features.30.cheap_operation.1.bias", "features.30.cheap_operation.1.running_mean", "features.30.cheap_operation.1.running_var", "features.31.weight", "features.31.bias", "features.31.running_mean", "features.31.running_var", "features.34.primary_conv.0.weight", "features.34.primary_conv.1.weight", "features.34.primary_conv.1.bias", "features.34.primary_conv.1.running_mean", "features.34.primary_conv.1.running_var", "features.34.cheap_operation.0.weight", "features.34.cheap_operation.1.weight", "features.34.cheap_operation.1.bias", "features.34.cheap_operation.1.running_mean", "features.34.cheap_operation.1.running_var", "features.35.weight", "features.35.bias", "features.35.running_mean", "features.35.running_var", "features.37.primary_conv.0.weight", "features.37.primary_conv.1.weight", "features.37.primary_conv.1.bias", "features.37.primary_conv.1.running_mean", "features.37.primary_conv.1.running_var", "features.37.cheap_operation.0.weight", "features.37.cheap_operation.1.weight", "features.37.cheap_operation.1.bias", "features.37.cheap_operation.1.running_mean", "features.37.cheap_operation.1.running_var", "features.38.weight", "features.38.bias", "features.38.running_mean", "features.38.running_var", "features.40.primary_conv.0.weight", "features.40.primary_conv.1.weight", "features.40.primary_conv.1.bias", "features.40.primary_conv.1.running_mean", "features.40.primary_conv.1.running_var", "features.40.cheap_operation.0.weight", "features.40.cheap_operation.1.weight", "features.40.cheap_operation.1.bias", "features.40.cheap_operation.1.running_mean", "features.40.cheap_operation.1.running_var", "features.41.weight", "features.41.bias", "features.41.running_mean", "features.41.running_var", "classifier.weight", "classifier.bias".
Unexpected key(s) in state_dict: "".
执行python bin/04_fmap_vis.py 生成时间戳的events.out文件报错
在04_fmap_vis.py文件中的路径已经改成自己最新训练保存的pkl文件
path_checkpoint = os.path.join(BASE_DIR, "..", "results", "09-24_11-11", "checkpoint_best.pkl")
Ghost-ResNet-56 的 flops 比 ResNet-56 少了近一半,为什么我在用测试集测试时ResNet-56花费的时间更少一些呢?
还是flops少,推理速度不一定会快?
请问ghost-vgg版本什么时候放出来
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.