Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2015-09-17 | Separate IO dependencies | Tea | 3 | -1/+28 | |
OpenCV, LMDB, LevelDB and Snappy are made optional via switches (USE_OPENCV, USE_LMDB, USE_LEVELDB) available for Make and CMake builds. Since Snappy is a LevelDB dependency, its use is determined by USE_LEVELDB. HDF5 is left bundled because it is used for serializing weights and solverstates. | |||||
2015-09-01 | Merge pull request #3010 from darrengarvey/fixup-memory-leak-siamese | Jeff Donahue | 1 | -1/+1 | |
Fix memory leak in convert_mnist_siamese_data. | |||||
2015-09-02 | cifar10: Fix examples by setting snapshot_format. | Darren Garvey | 5 | -0/+5 | |
Commit 4227828a set the default binary format from HDF5 to BINARYPROTO to fix #2885. This broke the cifar10 examples which relied on this default. This commit specifies the snapshot_format explicitly since the rest of the example relies on this being HDF5. | |||||
2015-09-02 | Fix memory leak in convert_mnist_siamese_data. | Darren Garvey | 1 | -1/+1 | |
This fixes a memory leak by using delete[] rather than plain delete. | |||||
2015-09-01 | Cleanup: Fixup capitalisation of Caffe_POSTFIX. | Darren Garvey | 1 | -1/+1 | |
Replaces CAffe_POSTFIX -> Caffe_POSTFIX. | |||||
2015-08-20 | Use input_shape instead of input_dim in examples | Luke Yeager | 6 | -24/+36 | |
2015-08-14 | Make classification.bin support models with less than 5 classes | Felix Abecassis | 1 | -0/+2 | |
The example program would crash if the number of classes was less than 5, since it was still attempting to get the top 5 predictions. Close #2585 | |||||
2015-08-14 | Adam solver | PatWie | 2 | -0/+29 | |
This commit implements the Adam solver by Kingma et. al for CPU and GPU. All solver parameters are defined in the caffe.proto. This also adds an example for the MNIST dataset. | |||||
2015-08-11 | Merge pull request #2891 from fyu/fix-caffenetpy | Jon Long | 1 | -1/+1 | |
fix examples/pycaffe/caffenet.py import | |||||
2015-08-10 | Clean up and modernize AdaDelta code; add learning rate support; add ↵ | Matthias Plappert | 2 | -0/+4 | |
additional test cases | |||||
2015-08-10 | Updated AdaDelta for modern Caffe; reduced iterations on multi-iter tests | Kevin Bache | 1 | -1/+1 | |
2015-08-10 | Implement AdaDelta; add test cases; add mnist examples | Mohamed Omran | 3 | -0/+43 | |
2015-08-09 | from __future__ imports must occur at the beginning of the file | Fisher Yu | 1 | -1/+1 | |
2015-08-08 | Implement RMSProp Solver | Eren Golge | 2 | -0/+30 | |
Implement RMSProp solver and cleaned up to adjust to new solver interface that uses accumulated gradients and refactored regularization. | |||||
2015-08-07 | Merge pull request #2836 from erictzeng/hdf5_snapshot | Jeff Donahue | 3 | -4/+4 | |
Snapshot model weights/solver state to HDF5 files | |||||
2015-08-07 | Update example bash scripts to expect .h5, new extensions in .gitignore | Eric Tzeng | 3 | -4/+4 | |
2015-08-08 | add [] to "delete pixels". | Tian Zhi | 1 | -1/+1 | |
see https://isocpp.org/wiki/faq/freestore-mgmt#delete-array-built-ins. | |||||
2015-07-16 | [examples] fix link to point to new tutorial notebook | Evan Shelhamer | 1 | -1/+1 | |
2015-07-12 | Merge pull request #2739 from AdamStelmaszczyk/patch-2 | Jon Long | 1 | -2/+1 | |
One command less in CIFAR10 documentation | |||||
2015-07-12 | examples/imagenet: fix broken link | Gleb Mazovetskiy | 1 | -1/+1 | |
2015-07-10 | One command less | AdamStelmaszczyk | 1 | -2/+1 | |
Also more readable and compatible with format of instructions for MNIST https://github.com/BVLC/caffe/tree/master/examples/mnist | |||||
2015-07-08 | Making the net_spec python3 compatible | philkr | 1 | -2/+3 | |
2015-06-30 | [examples] add Euclidean loss PythonLayer | Evan Shelhamer | 2 | -0/+97 | |
2015-06-30 | [examples] sequence and revise notebooks | Evan Shelhamer | 19 | -26009/+22296 | |
- combine classification + filter visualization - order by classification, learning LeNet, brewing logreg, and fine-tuning to flickr style - improve flow of content in classification + filter visualization - include solver needed for learning LeNet - edit notebook descriptions for site catalogue | |||||
2015-06-30 | [examples] flickr fine-tuning notebook | Yangqing Jia | 2 | -0/+959 | |
2015-06-30 | [examples] draft Python solving example | Jonathan L Long | 1 | -0/+5148 | |
2015-06-30 | [examples] caffenet python spec | Jonathan L Long | 1 | -0/+54 | |
2015-06-15 | typo: "a fixed steps" to "at fixed steps" | Aaron Schumacher | 1 | -1/+1 | |
fixing in the correct place as per @shelhamer's advice from #2602 | |||||
2015-05-31 | Merge pull request #2064 from drohit92/patch-1 | Evan Shelhamer | 1 | -2/+2 | |
[docs] fix solverstate filename in ImageNet example | |||||
2015-05-31 | Merge pull request #2400 from cnDelbert/master | Evan Shelhamer | 1 | -1/+1 | |
Correct the REPO_DIRNAME in `examples/web_demo/app.py` | |||||
2015-05-30 | Merge pull request #2498 from flx42/cpp_classification_example | Evan Shelhamer | 2 | -0/+332 | |
Add a simple C++ classification example | |||||
2015-05-29 | Add a simple C++ classification example | Felix Abecassis | 2 | -0/+332 | |
Closes #2487 Example usage: ./build/examples/cpp_classification/classification.bin \ models/bvlc_reference_caffenet/deploy.prototxt \ models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel \ data/ilsvrc12/imagenet_mean.binaryproto \ data/ilsvrc12/synset_words.txt \ examples/images/cat.jpg | |||||
2015-05-29 | [example] fix path for diff in net surgery | TorosFanny | 1 | -2/+86 | |
2015-05-18 | Update IPython Notebooks to version 4 | Sebastián Ramírez | 6 | -3476/+39807 | |
2015-05-14 | Merge pull request #2201 from jeffdonahue/tutorial-fixes | Evan Shelhamer | 2 | -54/+62 | |
Update docs for ND blobs (#1970) and layer type is a string (#1694) | |||||
2015-05-14 | Update docs for ND blobs (#1970) and layer type is a string (#1694) | Jeff Donahue | 2 | -54/+62 | |
2015-04-30 | Correct the REPO_DIRNAME | Delbert | 1 | -1/+1 | |
2015-04-27 | Import Pandas in HDF5 IPython notebook. Fix for issue BVLC/caffe#2247 | Sebastián Ramírez | 1 | -0/+1 | |
2015-04-24 | Merge pull request #2352 from pgao/rcnn-fix | Jon Long | 1 | -1/+1 | |
Fix RCNN model fetching script | |||||
2015-04-24 | Fix RCNN model fetching script | PETER_GAO | 1 | -1/+1 | |
2015-04-08 | Changing Image import to be imported from PIL. | e3 | 1 | -1/+1 | |
2015-03-24 | Add note in example about installing scikit-learn | Luke Yeager | 1 | -1/+2 | |
2015-03-08 | [example] pycaffe classification downloads the model automatically | Evan Shelhamer | 1 | -4/+9 | |
2015-03-08 | [example] warm-start web demo | Evan Shelhamer | 1 | -1/+2 | |
call forward to warm-start the demo so the first request isn't slow. | |||||
2015-03-08 | [example] revise hdf5 classification | Evan Shelhamer | 5 | -576/+702 | |
- add a little explanation - solve from Python and the command line - time scikit-learn and caffe - fix test iterations (number of instances / batch size) | |||||
2015-03-08 | [example] revise net surgery + add designer filters | Evan Shelhamer | 3 | -142/+272 | |
- N-D blob parameter dimensions - add filtering section to net surgery example - make Gaussian blur and Sobel edge kernels - alter biases - do flat assignment instead of reshape and explain memory layout - make dir for surgery files | |||||
2015-03-08 | [example] revise filter visualization | Evan Shelhamer | 1 | -45/+64 | |
- download CaffeNet if it isn't there - switch to caffe.Net - reshape net for single input - explain param, bias indexing - update output for N-D blobs | |||||
2015-03-08 | [pycaffe] align web demo with #1728 and #1902 | Evan Shelhamer | 1 | -5/+9 | |
2015-03-07 | Update readme.md | Rohit Durvasula | 1 | -2/+2 | |
In the resume training option.. the name of the solver state changed to 'caffenet_train_iter_10000.solverstate' | |||||
2015-03-06 | Merge pull request #1987 from tnarihi/fix-siam-example | Evan Shelhamer | 1 | -12/+8 | |
[docs] fix siamese ipynb example |