Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2020-02-10 | Packaging: add a spec file for Tizen buildtizen | Tae-Young Chung | 2 | -0/+82 | |
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com> | |||||
2020-02-10 | Updated Intel's branch descriptionupstream/master | Cyprien Noel | 1 | -1/+1 | |
2020-02-10 | Updated Intel's branch description | Cyprien Noel | 1 | -1/+1 | |
2020-02-10 | Merge pull request #6499 from xerus/python_gpu | Przemysław Dolata | 2 | -2/+2 | |
python: Set gpu device id before setting gpu mode | |||||
2020-02-10 | Merge pull request #6461 from open-cv/patch_1 | Przemysław Dolata | 10 | -20/+20 | |
fix typos and add passing by reference | |||||
2020-02-10 | Merge branch 'master' into patch_1 | Przemysław Dolata | 27 | -7/+388 | |
2020-01-23 | python: Set gpu device id before setting gpu mode | Pavel Grunt | 2 | -2/+2 | |
Otherwise caffe allocates some memory on GPU#0 | |||||
2020-01-23 | Merge pull request #6455 from lengly/patch-1 | Przemysław Dolata | 1 | -1/+1 | |
Fix typo in inner_product_layer.cpp | |||||
2020-01-23 | Merge pull request #6346 from jerryz123/HDF5_config | Przemysław Dolata | 16 | -1/+79 | |
Added USE_HDF5 flag to build | |||||
2020-01-23 | Update inner_product_layer.cpp | Yuda Liu | 1 | -1/+1 | |
2020-01-23 | Merge pull request #6320 from Noiredd/clip | Przemysław Dolata | 8 | -1/+284 | |
Clip layer - resurrection | |||||
2020-01-23 | Cherry-picked USE_HDF5 from Android branch | Jerry Zhao | 16 | -1/+79 | |
2020-01-23 | Clip layer documentation | Przemysław Dolata | 2 | -0/+21 | |
2020-01-23 | test case fix for Clip layer gradient | Noiredd | 3 | -3/+33 | |
minor lint fixes | |||||
2020-01-23 | Merge pull request #6282 from Noiredd/pooling-mode | Przemysław Dolata | 3 | -4/+24 | |
PoolingLayer customizable output shape rounding mode | |||||
2020-01-23 | Add clip layer | Harm Berntsen | 6 | -1/+233 | |
2020-01-23 | fix typos and some minor fixes. | Kuang Fangjun | 10 | -20/+20 | |
2020-01-23 | Merge pull request #6238 from mitar/manual-sgd | Evan Shelhamer | 6 | -15/+32 | |
[pycaffe] expose interface for manual, step-by-step optimization | |||||
2020-01-23 | PoolingLayer customizable output shape rounding mode | Noiredd | 3 | -4/+24 | |
2020-01-23 | [pycaffe] test solver update | Valentin Tolmer | 1 | -0/+11 | |
2020-01-23 | [pycaffe] expose mutable solver parameter, base lr, and effective lr | Mitar | 2 | -9/+12 | |
`solver.lr` is the effective learning rate in use while `solver.base_lr` is the configured learning rate at initialization. the solver parameter is now editable for setting fields that are in use throughout the lifetime of the solver, such as the maximum iteration. | |||||
2020-01-23 | increment iteration during update, not step | Mitar | 2 | -4/+4 | |
with update exposed it is important to increment the iteration when an update is made, whether by step or update alone. more fundementally, it's the update that defines an iterationa, so this is a natural place for the increment. | |||||
2020-01-23 | [pycaffe] expose solver update to do manual solving | Mitar | 3 | -2/+5 | |
a sketch of `solver.step()` done out manually: 1. `solver.net.forward()` 2. `solver.net.backward()` 3. `solver.net.apply_update()` 4. `solver.net.clear_param_diffs()` | |||||
2020-01-23 | Merge pull request #6390 from open-cv/fix-6389 | Evan Shelhamer | 1 | -2/+2 | |
drop unnecessary cast fix issue #6389 | |||||
2020-01-23 | fix issue #6389 | Kuang Fangjun | 1 | -2/+2 | |
2020-01-23 | Merge pull request #6388 from open-cv/fix-6387 | Evan Shelhamer | 1 | -2/+2 | |
fix missing syncedmem constness fix issue #6387 | |||||
2020-01-23 | Merge pull request #6219 from uhfband/fix-caffe_pb2-module | Przemysław Dolata | 2 | -2/+2 | |
Fix incorrect namespace for pycaffe submodule caffe_pb2 | |||||
2020-01-23 | fix issue #6387. | Kuang Fangjun | 1 | -2/+2 | |
2020-01-23 | Merge pull request #6342 from Noiredd/gauss-fill-test-fix | Przemysław Dolata | 1 | -4/+4 | |
Gaussian filler tests adjustments | |||||
2020-01-23 | tweaked Gaussian filler tests for less false fails | Przemysław Dolata | 1 | -4/+4 | |
2020-01-23 | Revised guidelines for GitHub issues (#6327) | Przemysław Dolata | 2 | -18/+75 | |
revised guidelines for GitHub issues and caffe-users posts | |||||
2020-01-23 | Fix cmake < v3.7 compatibility in Cuda.cmake (#6338) | Viktor Richter | 1 | -2/+2 | |
Fix for compatibility with CMake <3.7 (related conversation under 37e4289) * Fix cmake < v3.7 compatibility in Cuda.cmake * Fix version test variable naming in Cuda.cmake | |||||
2020-01-23 | Merge pull request #6336 from Coderx7/master | Przemysław Dolata | 1 | -2/+2 | |
Minor correction concerning compilation compatibility with CUDA 9.0 (see #6237) | |||||
2020-01-23 | Minor correction concerning compilation compatibility with CUDA 9.0 | Seyyed Hossein Hasanpour | 1 | -2/+2 | |
Since CUDA 9.0 doesn't support sm_20 and sm_21 anymore. This PR allows Caffe to compile with CUDA 9.0 and newer versions successfully. This addresses the discussion concerning [#6237](https://github.com/BVLC/caffe/pull/6237) in [master (#6237)](https://github.com/BVLC/caffe/commit/cb150eca6d593ddb85e53acd05b8dcf709ea8337#diff-2004a3d3e6b4ed2e2812bb0b4b998f18) | |||||
2020-01-23 | Merge pull request #6237 from jasjuang/master | Przemysław Dolata | 1 | -0/+6 | |
Make caffe compile through cmake with CUDA 9.1 | |||||
2020-01-23 | Merge pull request #6277 from twmht/dev_issue_6268 | Przemysław Dolata | 1 | -0/+5 | |
check Embed index in debug mode | |||||
2020-01-23 | Added Swish layer (#6002) | Mikhail Antonenka | 5 | -1/+308 | |
* added swish layer (cpu) * swish layer: added tests * swish layer: optimized backpropogation * swish layer: added cuda implementation * swish layer: added beta parameter * swish layer: incorporated sigmoid layer * swish layer: fix comment of last added parameter * swish layer: added REGISTER_LAYER_CLASS | |||||
2020-01-23 | Merge pull request #6286 from Noiredd/bilinear-filler-fix | Przemysław Dolata | 1 | -15/+29 | |
BilinearFiller tests refactored | |||||
2020-01-23 | bilinear filter test refactor | Noiredd | 1 | -15/+29 | |
2020-01-23 | Merge pull request #6278 from Noiredd/filler-fix | Przemysław Dolata | 2 | -76/+339 | |
1D blob handling in MSRA/Xavier fillers + new filler tests | |||||
2020-01-23 | Filler testing overhaul | Noiredd | 1 | -72/+331 | |
2020-01-23 | Add lr_mult label to the network graph in draw_net.py (#6273) | nic25 | 2 | -38/+112 | |
draw_net.py refactoring and optional LR visualization * refactoring `get_layer_label` rewrote the function body to make it more streamlined. does not affect inputs and outputs * optionally visualize LR when drawing the network adds an option to `python/draw_net.py` that allows to visualize information about the learning rate multiplier (if relevant) when drawing the network's graph. | |||||
2020-01-23 | 1D blob handling in MSRA/Xavier fillers | Noiredd | 1 | -4/+8 | |
2018-03-23 | check embed index in debug mode | twmht | 1 | -0/+5 | |
2018-02-26 | Merge pull request #6249 from Noiredd/legacy-toolsupstream/master-freeze | Przemysław Dolata | 5 | -35/+0 | |
Remove legacy tools | |||||
2018-02-23 | Remove legacy tools | Noiredd | 5 | -35/+0 | |
2018-02-21 | Merge pull request #6104 from YaYaB/master_bvlc | Przemysław Dolata | 1 | -0/+7 | |
Check solver gamma and stepsize to avoid unexplained core dump | |||||
2018-02-20 | Merge pull request #5149 from yanchen036/master | Przemysław Dolata | 2 | -2/+2 | |
fix extension extraction in matchExt | |||||
2018-02-20 | Merge pull request #6176 from qu1j0t3/simplify-pip-cmd | Przemysław Dolata | 1 | -1/+1 | |
Simplify pip requirements installation | |||||
2018-02-20 | Merge pull request #6240 from knsong/master | Przemysław Dolata | 1 | -6/+8 | |
Fix filler compatibility for ND convolution |