| Age | Commit message (Expand) | Author | Files | Lines |
|---|
| 2017-06-02 | 1. Porting Caffe onto ARM Compute Library. | Yao Honggui | 1 | -0/+4 |
| 2015-12-02 | Remove hamming_distance and popcount | Tea | 1 | -22/+0 |
| 2015-06-02 | Add LogLayer | Jeff Donahue | 1 | -0/+10 |
| 2014-10-11 | fix flaky math functions, remove unnecessary instantiations. | Yangqing Jia | 1 | -3/+0 |
| 2014-08-21 | Merge pull request #956 from longjon/clean-signbit | Evan Shelhamer | 1 | -12/+0 |
| 2014-08-20 | specialize cpu_strided_dot before instantiation to fix clang++ build | Evan Shelhamer | 1 | -11/+11 |
| 2014-08-20 | clean up cpu signbit definition | Jonathan L Long | 1 | -12/+0 |
| 2014-08-18 | add caffe_cpu_strided_dot for strided dot products | Jonathan L Long | 1 | -4/+17 |
| 2014-08-14 | Added absolute value layer, useful for implementation of siamese networks! | Alireza Shafaei | 1 | -1/+10 |
| 2014-08-12 | Fix caffe/alt_fn lint errors. | Jeff Donahue | 1 | -2/+3 |
| 2014-08-06 | LICENSE governs the whole project so strip file headers | Evan Shelhamer | 1 | -2/+0 |
| 2014-07-29 | fix some namespace with std::signbit | yajiedesign | 1 | -0/+12 |
| 2014-07-17 | collect CUDA includes and calls, separate from CPU-only mode, leave out | Evan Shelhamer | 1 | -131/+4 |
| 2014-07-10 | Replace cudaMemcpy with caffe_gpu_memcpy in SyncedMemory per @longjon | Kai Li | 1 | -6/+2 |
| 2014-07-10 | Check the GPU mode to decide which memcpy to use | Kai Li | 1 | -6/+6 |
| 2014-07-10 | Avoid using cudaMemcpy for memcpy when there is no GPU and CUDA driver | Kai Li | 1 | -2/+10 |
| 2014-07-03 | reduce caffe_copy to instantiations, split off caffe_memcpy for void* | Evan Shelhamer | 1 | -23/+9 |
| 2014-07-03 | do all caffe_copy() as UVA mem copy, and drop caffe_gpu_copy() | Evan Shelhamer | 1 | -8/+13 |
| 2014-06-27 | Check that pointers are different before copying in caffe_copy and caffe_gpu_... | Sergio | 1 | -4/+12 |
| 2014-05-24 | merge caffe_set definitions; define for int as well | Jeff Donahue | 1 | -13/+6 |
| 2014-05-24 | make a Blob<unsigned int> and use in dropout layer | Jeff Donahue | 1 | -0/+20 |
| 2014-04-22 | cleanup data_layer, add prefetch_rng_ field to it and use instead of | Jeff Donahue | 1 | -0/+4 |
| 2014-04-18 | pass caffe rng ref into variate_generator constructor instead of having | Jeff Donahue | 1 | -6/+3 |
| 2014-04-08 | make RNG function outputs the last argument per Google C++ style guidelines | Jeff Donahue | 1 | -15/+15 |
| 2014-04-08 | make RNG function names more similar to other caffe math function names | Jeff Donahue | 1 | -9/+9 |
| 2014-04-08 | call caffe_set_rng at the end of each vRng function to maintain state | Jeff Donahue | 1 | -18/+16 |
| 2014-04-08 | add LRN within map layer and dependencies (eltwise product and power) | Jeff Donahue | 1 | -0/+36 |
| 2014-03-29 | Rename caffe_hamming_distance into caffe_cpu_hamming_distance | Kai Li | 1 | -2/+2 |
| 2014-03-23 | Rename signbit in macros to sgnbit to avoid conflicts with std::signbit | Kai Li | 1 | -1/+1 |
| 2014-03-23 | Add signbit math func, simplify GPU defs & instantiations with a macro | Kai Li | 1 | -0/+1 |
| 2014-03-23 | Add and test non-in-place scale math functions for CPU and GPU | Kai Li | 1 | -0/+28 |
| 2014-03-23 | Use macro to simplify element wise cpu math functions | Kai Li | 1 | -11/+2 |
| 2014-03-23 | Add and test element wise abs math functions for CPU and GPU | Kai Li | 1 | -0/+6 |
| 2014-03-23 | Instantiate caffe_cpu_sign for float and double | Kai Li | 1 | -0/+6 |
| 2014-03-23 | Add and test sum of absolute values math functions for CPU and GPU | Kai Li | 1 | -0/+20 |
| 2014-03-22 | Set copyright to BVLC and contributors. | Evan Shelhamer | 1 | -3/+1 |
| 2014-03-22 | Hide boost rng behind facade for osx compatibility | Evan Shelhamer | 1 | -9/+8 |
| 2014-03-21 | lint | Evan Shelhamer | 1 | -2/+3 |
| 2014-03-21 | clean up residual mkl comments and code | Evan Shelhamer | 1 | -17/+3 |
| 2014-03-21 | major refactoring allow coexistence of MKL and non-MKL cases | Rowland Depp | 1 | -130/+20 |
| 2014-03-21 | fix bernoulli generator bug | Jeff Donahue | 1 | -3/+2 |
| 2014-03-21 | change all Rng's to use variate_generator for consistency | Jeff Donahue | 1 | -5/+11 |
| 2014-03-21 | use boost variate_generator to pass tests w/ boost 1.46 (Gaussian filler | Jeff Donahue | 1 | -2/+5 |
| 2014-03-21 | make uniform distribution usage compatible with boost 1.46 | Jeff Donahue | 1 | -1/+1 |
| 2014-03-21 | nextafter templates off one type | Alejandro Dubrovsky | 1 | -1/+1 |
| 2014-03-21 | Fix math funcs, add tests, change Eigen Map to unaligned for lrn_layer | Kai Li | 1 | -122/+200 |
| 2014-03-21 | Fixed uniform distribution upper bound to be inclusive | Kai Li | 1 | -2/+13 |
| 2014-03-21 | compile caffe without MKL (dependency replaced by boost::random, Eigen3) | Rodrigo Benenson | 1 | -25/+128 |
| 2014-03-19 | Add __builtin_popcount* based fast Hamming distance math function | Kai Li | 1 | -0/+23 |
| 2013-10-01 | misc update... | Yangqing Jia | 1 | -0/+12 |
