These commits are when the Protocol Buffers files have changed: (only the last 100 relevant commits are shown)
| Commit: | 2cbc1bb | |
|---|---|---|
| Author: | Evan Shelhamer | |
| Committer: | GitHub | |
Merge pull request #3855 from shaibagon/upgrade_infogain InfogainLoss layer can normalize, ignore, and more
| Commit: | 850ffd8 | |
|---|---|---|
| Author: | Cyprien Noel | |
Remove missed legacy parallel code
| Commit: | 11930f1 | |
|---|---|---|
| Author: | Jonathan R. Williford | |
Clarify batch norm parameter documentation.
| Commit: | 929135b | |
|---|---|---|
| Author: | Evan Shelhamer | |
| Committer: | GitHub | |
Merge pull request #5210 from ftokarev/patches Obsolete reference to `bool solver` in caffe.proto
| Commit: | 3a0b6c6 | |
|---|---|---|
| Author: | Fyodor Tokarev | |
| Committer: | Fyodor Tokarev | |
Update a comment in caffe.proto
| Commit: | 3ba2054 | |
|---|---|---|
| Author: | Cyprien Noel | |
| Committer: | Cyprien Noel | |
Switched multi-GPU to NCCL
| Commit: | 8a65ae3 | |
|---|---|---|
| Author: | Wei Liu | |
add options to display per class AP
The documentation is generated from this commit.
| Commit: | db66432 | |
|---|---|---|
| Author: | Zhou Mo | |
fix many typos by using codespell
| Commit: | b788af6 | |
|---|---|---|
| Author: | Wei Liu | |
Merge branch 'master' into ssd
| Commit: | f487dc1 | |
|---|---|---|
| Author: | Wei Liu | |
Merge branch 'master' into ssd
| Commit: | 3d62e3c | |
|---|---|---|
| Author: | Evan Shelhamer | |
| Committer: | Evan Shelhamer | |
sigmoid cross-entropy loss: normalize loss by different schemes sig-ce loss handles all the same normalizations as the softmax loss; refer to #3296 for more detail. this preserves the default normalization for sig-ce loss: batch size.
| Commit: | 2a2bedf | |
|---|---|---|
| Author: | Wei Liu | |
add option to set prior center offset
| Commit: | 9c26fd7 | |
|---|---|---|
| Author: | Wei Liu | |
add option to save display results to video file
| Commit: | cd53c56 | |
|---|---|---|
| Author: | Wei Liu | |
add option to expand the image
| Commit: | 44e139d | |
|---|---|---|
| Author: | Wei Liu | |
add plateau learning rate
| Commit: | cb40904 | |
|---|---|---|
| Author: | Wei Liu | |
Merge branch 'master' into ssd
| Commit: | c6a070a | |
|---|---|---|
| Author: | Wei Liu | |
Merge branch 'master' into ssd
| Commit: | 0e9ebab | |
|---|---|---|
| Author: | Sanghoon Hong | |
| Committer: | Sanghoon Hong | |
Add "plateau" LR policy for SGD solver
| Commit: | 1427713 | |
|---|---|---|
| Author: | Wei Liu | |
add demo for processing video file
| Commit: | 579d93f | |
|---|---|---|
| Author: | Wei Liu | |
add skip_frame and video file option in VideoDataLayer
| Commit: | b05c992 | |
|---|---|---|
| Author: | Wei Liu | |
add anno_type in AnnotatedDataParameter
| Commit: | 89eace1 | |
|---|---|---|
| Author: | Wei Liu | |
merge master and fix conflict
| Commit: | 8865043 | |
|---|---|---|
| Author: | Wei Liu | |
add color distortion options
| Commit: | bdb9457 | |
|---|---|---|
| Author: | Alican Bozkurt | |
add default value for rms_decay
| Commit: | a53756a | |
|---|---|---|
| Author: | Wei Liu | |
add fix scale for FIT_SMALL_SIZE resize option
| Commit: | a911621 | |
|---|---|---|
| Author: | Wei Liu | |
add resize parameter in detection output/evaluate layer
| Commit: | 708a6ca | |
|---|---|---|
| Author: | Wei Liu | |
add options to provide img_size and step in PriorBoxLayer
| Commit: | c35c2db | |
|---|---|---|
| Author: | Wei Liu | |
change default value
| Commit: | 768ce93 | |
|---|---|---|
| Author: | Wei Liu | |
merge master and speed up nms
| Commit: | 621130a | |
|---|---|---|
| Author: | Wei Liu | |
refactor MineHardExample function and add use_prior_for_nms option
| Commit: | 032b10b | |
|---|---|---|
| Author: | Wei Liu | |
add OHEM method
| Commit: | 59d48f2 | |
|---|---|---|
| Author: | Wei Liu | |
add CORNER_SIZE code_type
| Commit: | 084b630 | |
|---|---|---|
| Author: | Wei Liu | |
add ignore_cross_boundary_bbox option
| Commit: | c3cc3df | |
|---|---|---|
| Author: | Wei Liu | |
add multiple scales for PriorBoxLayer
| Commit: | 5f2d845 | |
|---|---|---|
| Author: | Jeff Donahue | |
| Committer: | Jeff Donahue | |
Add RecurrentLayer: an abstract superclass for other recurrent layer types
| Commit: | c419f85 | |
|---|---|---|
| Author: | Jonathan L Long | |
| Committer: | Jonathan L Long | |
add parameter layer for learning any bottom
| Commit: | 859cf6e | |
|---|---|---|
| Author: | Kun Wang | |
Fix an error in the example of ReshapeParameter. * this small mistake may confuse newer.
| Commit: | f87f9ac | |
|---|---|---|
| Author: | Wei Liu | |
rebase master
| Commit: | 77cde9c | |
|---|---|---|
| Author: | Jeff Donahue | |
| Committer: | Jeff Donahue | |
Net: setting `propagate_down: true` forces backprop
| Commit: | 251ed5a | |
|---|---|---|
| Author: | Wei Liu | |
add webcam demo
| Commit: | 337b075 | |
|---|---|---|
| Author: | shai | |
upgrading InfogainLoss layer: (1) incorporating Softmax layer to make the gradeint computation robust, much like SoftmaxWithLoss layer (see: http://stackoverflow.com/a/34917052/1714410 for more information). (2) supporting loss along axis
| Commit: | 3dd74cd | |
|---|---|---|
| Author: | Wei Liu | |
speed up nms and generate output for COCO
| Commit: | 519a320 | |
|---|---|---|
| Author: | Wei Liu | |
add map_object_to_agnostic to enable learning object proposal
| Commit: | 64e78bd | |
|---|---|---|
| Author: | Jonathan L Long | |
| Committer: | max argus | |
add CropLayer: crop blob to another blob's dimensions with offsets configure offset(s) through proto definition.
| Commit: | 952fd17 | |
|---|---|---|
| Author: | max argus | |
| Committer: | max argus | |
Extend Crop to N-D, changed CropParameter.
| Commit: | ca9fa49 | |
|---|---|---|
| Author: | max argus | |
| Committer: | max argus | |
Crop: fixes, tests and negative axis indexing.
| Commit: | 31a9640 | |
|---|---|---|
| Author: | Wei Liu | |
enable different choice of encoding the prior variance
| Commit: | d2ffca7 | |
|---|---|---|
| Author: | Wei Liu | |
make variance repeated in PriorBoxLayer
| Commit: | 984e302 | |
|---|---|---|
| Author: | Wei Liu | |
merge master
| Commit: | bddd04b | |
|---|---|---|
| Author: | Evan Shelhamer | |
| Committer: | Evan Shelhamer | |
deprecate input fields and upgrade automagically
| Commit: | 00598ca | |
|---|---|---|
| Author: | Evan Shelhamer | |
| Committer: | Evan Shelhamer | |
add InputLayer for Net input Create an input layer to replace oddball Net `input` fields.
| Commit: | 06cb2f4 | |
|---|---|---|
| Author: | Wei Liu | |
add more normalization to MultiBoxLoss
| Commit: | 86f9e78 | |
|---|---|---|
| Author: | Wei Liu | |
add logistic conf loss type
| Commit: | 4e2173c | |
|---|---|---|
| Author: | Wei Liu | |
add keep_top_k in DetectionOutputLayer
| Commit: | 8f847fa | |
|---|---|---|
| Author: | Youssef Kashef | |
| Committer: | Youssef Kashef | |
tranpose parameter added to IP layer to support tied weights in an autoencoder. Arguments to matrix multiplication function are conditioned on this parameter, no actual transposing takes place. test ip gradient computation with transpose on
| Commit: | a729366 | |
|---|---|---|
| Author: | Wei Liu | |
add sampler and related functions
| Commit: | ba9e3f7 | |
|---|---|---|
| Author: | Wei Liu | |
add support when evaluating on partial test data
| Commit: | a336f3e | |
|---|---|---|
| Author: | Wei Liu | |
add code_type
| Commit: | 3b7f1a7 | |
|---|---|---|
| Author: | Wei Liu | |
add variance and make max_size optional
| Commit: | c2a8dc8 | |
|---|---|---|
| Author: | Wei Liu | |
add neg_overlap for selecting hard negatives
| Commit: | 48ad4cc | |
|---|---|---|
| Author: | Wei Liu | |
do negative mining based on scores instead of overlap
| Commit: | 3342f99 | |
|---|---|---|
| Author: | Wei Liu | |
change type of size from int to float
| Commit: | 3afdc26 | |
|---|---|---|
| Author: | Wei Liu | |
add do_neg_mining in MultiBoxLossLayer
| Commit: | 32ae638 | |
|---|---|---|
| Author: | Wei Liu | |
add name_size_file in DetectionEvaluationLayer
| Commit: | 70cd366 | |
|---|---|---|
| Author: | Wei Liu | |
add SmoothL1LossLayer from Ross Girshick's Fast R-CNN
| Commit: | 5f0643d | |
|---|---|---|
| Author: | Wei Liu | |
add MaxIntegral ap_version to match VOC2012/ILSVRC AP
| Commit: | 2426d4e | |
|---|---|---|
| Author: | Wei Liu | |
add difficult property for bbox annotation
| Commit: | 89380f1 | |
|---|---|---|
| Author: | Wei Liu | |
set lr_mult to 0 instead of using fix_scale in NormalizeLayer to not learn scale parameter
| Commit: | a24f832 | |
|---|---|---|
| Author: | Wei Liu | |
add num_classes in DetectionEvaluateLayer
| Commit: | b5419e3 | |
|---|---|---|
| Author: | Wei Liu | |
add SaveOutputParameter in DetectionOutputLayer
| Commit: | 900dee1 | |
|---|---|---|
| Author: | Wei Liu | |
add NormalizeLayer from fcn branch
| Commit: | 1ae883b | |
|---|---|---|
| Author: | Wei Liu | |
add change in proto for normalize option
| Commit: | e8415b1 | |
|---|---|---|
| Author: | Wei Liu | |
add TestDetection
| Commit: | 288493d | |
|---|---|---|
| Author: | Wei Liu | |
add DetectionEvaluateLayer with test
| Commit: | 4427dac | |
|---|---|---|
| Author: | Wei Liu | |
add DetectionOutputLayer with test
| Commit: | 8c488b6 | |
|---|---|---|
| Author: | Wei Liu | |
add ApplyNMS and GetConfidenceScores to bbox_util
| Commit: | 608d0aa | |
|---|---|---|
| Author: | Wei Liu | |
fix merge upstream conflict
| Commit: | a894b40 | |
|---|---|---|
| Author: | Wei Liu | |
fix several bugs in MultiBoxLossLayer
| Commit: | b68695d | |
|---|---|---|
| Author: | Wei Liu | |
add PermuteLayer
| Commit: | 2b762b0 | |
|---|---|---|
| Author: | Wei Liu | |
fix merge upstream conflict
| Commit: | 0816907 | |
|---|---|---|
| Author: | Jeff Donahue | |
| Committer: | Jeff Donahue | |
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 }`. BiasLayer and ScaleLayer each take 1 or 2 bottoms, with the output having the same shape as the first. The second input -- either another bottom or a learned parameter -- will have its axes (virtually) broadcast and tiled to have the same shape as the first, after which elementwise addition (Bias) or multiplication (Scale) is performed.
| Commit: | ec04197 | |
|---|---|---|
| Author: | Dmytro Mishkin | |
| Committer: | Jeff Donahue | |
Add ChannelwiseAffine for batch norm
| Commit: | 91676b3 | |
|---|---|---|
| Author: | Wei Liu | |
put label_map_file in AnnotatedDataParameter
| Commit: | a7ac8bc | |
|---|---|---|
| Author: | Evan Shelhamer | |
Merge pull request #3388 from mohomran/exponential_linear_units Exponential Linear Units
| Commit: | bc15f86 | |
|---|---|---|
| Author: | Wei Liu | |
add MultiBoxLossLayer and bbox_util
| Commit: | 4a0c8a1 | |
|---|---|---|
| Author: | Wei Liu | |
add PriorBoxLayer which generates priors from a layer
| Commit: | 016c460 | |
|---|---|---|
| Author: | Wei Liu | |
add LabelMap and tools for create DB to store AnnotatedDatum
| Commit: | de1342f | |
|---|---|---|
| Author: | Wei Liu | |
Add AnnotatedDataLayer
| Commit: | 3e3e9ce | |
|---|---|---|
| Author: | Jonathan L Long | |
| Committer: | Jonathan L Long | |
add short description of dilation to caffe.proto
| Commit: | 93bfcb5 | |
|---|---|---|
| Author: | Fisher Yu | |
| Committer: | Jonathan L Long | |
add support for 2D dilated convolution
| Commit: | a668194 | |
|---|---|---|
| Author: | Mohamed Omran | |
| Committer: | Mohamed Omran | |
ELU layer with basic tests
| Commit: | 8b2aa70 | |
|---|---|---|
| Author: | Carl Doersch | |
| Committer: | Carl Doersch | |
Better normalization options for SoftmaxWithLoss layer.
| Commit: | 39f69fb | |
|---|---|---|
| Author: | Jeff Donahue | |
Merge pull request #3229 from cdoersch/batchnorm2 Yet another batch normalization PR
| Commit: | a52ee65 | |
|---|---|---|
| Author: | Carl Doersch | |
| Committer: | Carl Doersch | |
Cleanup batch norm layer, include global stats computation
| Commit: | 0eea815 | |
|---|---|---|
| Author: | Ronghang Hu | |
| Committer: | Ronghang Hu | |
Change solver type to string and provide solver registry
| Commit: | 321720d | |
|---|---|---|
| Author: | Evan Shelhamer | |
Merge pull request #3160 from shelhamer/cudnnV3 Basic cuDNN v3 support
| Commit: | ecac7ff | |
|---|---|---|
| Author: | Simon Layton | |
| Committer: | Evan Shelhamer | |
Initial cuDNN v3 support
| Commit: | 6c02c8b | |
|---|---|---|
| Author: | Tim Meinhardt | |
| Committer: | Tim Meinhardt | |
Add argmax_param axis
| Commit: | 9d8206e | |
|---|---|---|
| Author: | Jeff Donahue | |
| Committer: | Jeff Donahue | |
Im2col and Convolution layers support N spatial axes
| Commit: | 4c2ff16 | |
|---|---|---|
| Author: | Jeff Donahue | |
| Committer: | Jeff Donahue | |
caffe.proto: generalize ConvolutionParameter to N spatial axes