-
Notifications
You must be signed in to change notification settings - Fork 395
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.
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
python3 compatibility #10
Closed
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ND convolution with im2col
refine format of switch case statement in solver
- clarify indices by naming *_im for indices in image and *_col for indices in column - mark corresonding im2col + col2im quantities by renaming patch_* -> kernel_* - fix out-of-date names in equivalent col2im loop
future-proof version check for BLAS libraries on OS X fix #3092
Fix broken DeconvolutionLayer GPU backward caused by ND conv typo
LayerSetUp This also eliminates the extra copying of bottom's shape.
[build] check xcode command line tools version >= 6
Fix broken conv/deconv reshaping
checking large then small can mask failure since the smaller shape memory will fit within the larger shape.
Check that output spatial shape varies with input shape while the output num matches the input num.
[test] Test Reshape more rigorously
[examples] fix link to feature visualization notebook
Allow H5T_INTEGER in HDF5 files
Fix generate_sample_data.py
Updated draw.py to make it work under Python 3
TestDataTransformer: fix some memory leaks
Fix loss of last iteration when average_loss > 1
Add a -c to wget so that it continues interrupted downloads
improved to load RGB image as grayscale image
Remove unnecessary CAFFE_TEST_CUDA_PROP declarations
Scale and Bias Layers
Remove incorrect cast of gemm int arg to Dtype in BiasLayer
Net: expose param_display_names_
fixing the database param
The old uses `abspath`, which I think is so harmful: * If I `cp -a` the whole project, `build/tools/caffe` still refer to the old file, until `make clean`, making debugging very hard * For `tar` and `scp`, the soft links can not work unless the target project folder has the same path
use relative paths on making build/tools/ links
Include proto definition in distribute dir
Nicely prints gpu names
…ile extracting libflags from absolute library path with multiple (dots)
bugfix for incorrect behaviour in `caffe_parse_linker_libs`
- smooth l1 loss - roi pooling - expose phase in pycaffe - dropout scaling at test time (needed for MSRA-trained ZF network)
* commit '0dcd397b29507b8314e252e850518c5695efbb83': (223 commits) Fast and Faster R-CNN change set - smooth l1 loss - roi pooling - expose phase in pycaffe - dropout scaling at test time (needed for MSRA-trained ZF network) bugfix for incorrect behaviour in caffe_parse_linker_libs function while extracting libflags from absolute library path with multiple (dots) Nicely prints GPU names use relative paths on making build/tools/ links Remove incorrect cast of gemm int arg to Dtype in BiasLayer Make the two separate build systems clearer in the documentation Update mnist readme.md: scale moved to transform_param Remove unnecessary CAFFE_TEST_CUDA_PROP declarations Prevent in-place computation in ReshapeLayer and FlattenLayer Updated import to make it work with pydotplus show Caffe's version from MatCaffe Separation and generalization of ChannelwiseAffineLayer into BiasLayer and ScaleLayer. The behavior of ChannelwiseAffineLayer can be reproduced by a ScaleLayer with `scale_param { bias_term: true }`. Version 1.0.0-rc3 Add ChannelwiseAffine for batch norm copy proto to distribute directory Add makefile config option for linking Python 3 libraries Workaround for inplace max pooling issue Performance related update of im2col() and col2im() functions CMake python version fix Speeding up the GPU solvers ... Conflicts: python/caffe/pycaffe.py
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Use
six
to support both python2 and python3