summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2020-01-23Updated Intel's branch descriptionHEADmasterCyprien Noel1-1/+1
2020-01-23Updated Intel's branch descriptionCyprien Noel1-1/+1
2020-01-23Merge pull request #6499 from xerus/python_gpuPrzemysław Dolata2-2/+2
python: Set gpu device id before setting gpu mode
2020-01-23python: Set gpu device id before setting gpu modePavel Grunt2-2/+2
Otherwise caffe allocates some memory on GPU#0
2020-01-23Merge pull request #6461 from open-cv/patch_1Przemysław Dolata10-21/+20
fix typos and add passing by reference
2020-01-23Merge branch 'master' into patch_1Przemysław Dolata27-7/+387
2020-01-23Merge pull request #6455 from lengly/patch-1Przemysław Dolata1-1/+1
Fix typo in inner_product_layer.cpp
2020-01-23Merge pull request #6346 from jerryz123/HDF5_configPrzemysław Dolata16-1/+79
Added USE_HDF5 flag to build
2020-01-23Update inner_product_layer.cppYuda Liu1-1/+1
2020-01-23Merge pull request #6320 from Noiredd/clipPrzemysław Dolata8-1/+284
Clip layer - resurrection
2020-01-23Cherry-picked USE_HDF5 from Android branchJerry Zhao16-1/+79
2020-01-23Clip layer documentationPrzemysław Dolata2-0/+21
2020-01-23test case fix for Clip layer gradientNoiredd3-3/+33
minor lint fixes
2020-01-23Merge pull request #6282 from Noiredd/pooling-modePrzemysław Dolata3-4/+24
PoolingLayer customizable output shape rounding mode
2020-01-23Add clip layerHarm Berntsen6-1/+233
2020-01-23Merge pull request #6238 from mitar/manual-sgdEvan Shelhamer6-15/+32
[pycaffe] expose interface for manual, step-by-step optimization
2020-01-23fix typos and some minor fixes.Kuang Fangjun10-20/+20
2020-01-23PoolingLayer customizable output shape rounding modeNoiredd3-4/+24
2020-01-23[pycaffe] test solver updateValentin Tolmer1-0/+11
2020-01-23[pycaffe] expose mutable solver parameter, base lr, and effective lrMitar2-9/+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.
2020-01-23increment iteration during update, not stepMitar2-4/+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 solvingMitar3-2/+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()`
2020-01-23Merge pull request #6390 from open-cv/fix-6389Evan Shelhamer1-2/+2
drop unnecessary cast fix issue #6389
2020-01-23fix issue #6389Kuang Fangjun1-2/+2
2020-01-23Merge pull request #6388 from open-cv/fix-6387Evan Shelhamer1-2/+2
fix missing syncedmem constness fix issue #6387
2020-01-23Merge pull request #6219 from uhfband/fix-caffe_pb2-modulePrzemysław Dolata2-2/+2
Fix incorrect namespace for pycaffe submodule caffe_pb2
2020-01-23fix issue #6387.Kuang Fangjun1-2/+2
2020-01-23Merge pull request #6342 from Noiredd/gauss-fill-test-fixPrzemysław Dolata1-4/+4
Gaussian filler tests adjustments
2020-01-23tweaked Gaussian filler tests for less false failsPrzemysław Dolata1-4/+4
2020-01-23Revised guidelines for GitHub issues (#6327)Przemysław Dolata2-18/+75
revised guidelines for GitHub issues and caffe-users posts
2020-01-23Fix cmake < v3.7 compatibility in Cuda.cmake (#6338)Viktor Richter1-2/+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
2020-01-23Merge pull request #6336 from Coderx7/masterPrzemysław Dolata1-2/+2
Minor correction concerning compilation compatibility with CUDA 9.0 (see #6237)
2020-01-23Minor correction concerning compilation compatibility with CUDA 9.0Seyyed Hossein Hasanpour1-2/+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)
2020-01-23Merge pull request #6237 from jasjuang/masterPrzemysław Dolata1-0/+6
Make caffe compile through cmake with CUDA 9.1
2020-01-23Merge pull request #6277 from twmht/dev_issue_6268Przemysław Dolata1-0/+5
check Embed index in debug mode
2020-01-23Added Swish layer (#6002)Mikhail Antonenka5-1/+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
2020-01-23Merge pull request #6286 from Noiredd/bilinear-filler-fixPrzemysław Dolata1-15/+29
BilinearFiller tests refactored
2020-01-23bilinear filter test refactorNoiredd1-15/+29
2020-01-23Merge pull request #6278 from Noiredd/filler-fixPrzemysław Dolata2-76/+339
1D blob handling in MSRA/Xavier fillers + new filler tests
2020-01-23Filler testing overhaulNoiredd1-72/+331
2020-01-23Add lr_mult label to the network graph in draw_net.py (#6273)nic252-38/+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.
2020-01-231D blob handling in MSRA/Xavier fillersNoiredd1-4/+8
2018-03-23check embed index in debug modetwmht1-0/+5
2018-02-26Merge pull request #6249 from Noiredd/legacy-toolsupstream/master-freezePrzemysław Dolata5-35/+0
Remove legacy tools
2018-02-23Remove legacy toolsNoiredd5-35/+0
2018-02-21Merge pull request #6104 from YaYaB/master_bvlcPrzemysław Dolata1-0/+7
Check solver gamma and stepsize to avoid unexplained core dump
2018-02-20Merge pull request #5149 from yanchen036/masterPrzemysław Dolata2-2/+2
fix extension extraction in matchExt
2018-02-20Merge pull request #6176 from qu1j0t3/simplify-pip-cmdPrzemysław Dolata1-1/+1
Simplify pip requirements installation
2018-02-20Merge pull request #6240 from knsong/masterPrzemysław Dolata1-6/+8
Fix filler compatibility for ND convolution
2018-02-17Fix compatibility for ND convolutionknsong1-6/+8
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-20 05:02:18 +0000