caffe
https://github.com/bvlc/caffe
C++
Caffe: a fast open framework for deep learning.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
C++ not yet supported69 Subscribers
View all SubscribersAdd a CodeTriage badge to caffe
Help out
- Issues
- Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: C:/Users/Administrator/Desktop/研究方向/caffe-master/models/carnet/train_val.prototxt *** Check failure stack trace: ***
- Why fc layer can direct connect pooling layer(max)?
- This is in fact an issue: large enough inputs exceed the maximum size of a blob and cannot be processed. Unless the problem truly calls for the full size to solve it, you could slice up the input into several smaller inputs to process separately.
- This is in fact an issue: large enough inputs exceed the maximum size of a blob and cannot be processed. Unless the problem truly calls for the full size to solve it, you could slice up the input into several smaller inputs to process separately.
- dataframe sort api is not available
- Same setup - different training loss (outcome)
- [Mean subtraction]Is there any difference in training networks with npy or `mean_values`
- Significant Performance reduction in latest OpenCL branch
- .build_release/lib/libcaffe.so:对‘__cudaPushCallConfiguration’未定义的引用
- add read_mean function in caffe.io for python interface
- Docs
- C++ not yet supported