summaryrefslogtreecommitdiff
path: root/models
AgeCommit message (Collapse)AuthorFilesLines
2017-08-26add support acl batch normal,direct conv, local connect, concat layershonggui1-0/+0
2017-07-061. Refine MakefileYe Joey2-0/+560
2. Rewrite the release notes with markdown format 3. Add the missed files in SqueezeNet
2017-01-12minor typoFan Yang1-1/+1
2016-02-25[examples] switch examples + models to Input layersEvan Shelhamer5-30/+25
2015-11-09Switched order of two layers for simpler diff with untuned filepanmari1-7/+7
Untuned file is in models/bvlc_reference_caffenet/train_val.prototxt.
2015-10-13Set CaffeNet train_val test mirroring to falseBrian Chu1-1/+1
2015-08-20Use input_shape instead of input_dim in examplesLuke Yeager5-20/+30
2015-06-30[examples] flickr fine-tuning notebookYangqing Jia1-0/+1
2015-06-02Remove unnecessary filler parameter in the sample modelKibum Bae1-63/+0
In bvlc_googlenet model, unnecessary filler parameters, 'std', were used for Xavier weight fillers.
2015-03-10Remove Gist from BVLC GoogleNetSergio Guadarrama1-1/+0
2015-02-05Upgrade existing nets using upgrade_net_proto_text toolJeff Donahue9-2002/+2668
Restore comments afterwards
2015-02-02fix GoogLeNet license overwritten by back-merge (see #1650)Evan Shelhamer1-4/+2
2015-01-21Back-merge fixes + docsEvan Shelhamer3-12/+6
and other fixes and documentation updates.
2015-01-07BVLC models are for unrestricted use (follow-up to #1650)Evan Shelhamer4-4/+4
2014-12-29[docs] open release of BVLC models for unrestricted useEvan Shelhamer4-12/+4
See BVLC model license details on the model zoo page.
2014-12-21Added credits for training bvlc modelsSergio5-0/+10
2014-12-21Added bvlc_googlenet prototxt and weightsSergio5-0/+4230
2014-12-20Added credits for training bvlc modelsSergio5-0/+10
2014-12-20Added bvlc_googlenet prototxt and weightsSergio5-0/+4228
2014-10-17back-mergeSergey Karayev1-5/+6
2014-10-17Fixing finetune_flickr_style model reported accuracy.Sergey Karayev1-5/+6
2014-10-03bundle pixel mean into CaffeNet as commentsEvan Shelhamer2-348/+16
2014-10-03Fixed crop error and add test_data_transformerSergio Guadarrama1-11/+2
Make lint happy Fix Name conventions
2014-10-03Fix OSX compilation for nvcc with opencvSergio1-2/+11
2014-10-03Added mean_value to specify mean channel substractionSergio1-0/+348
Added example of use to models/bvlc_reference_caffenet/train_val_mean_value.prototxt
2014-09-29[examples] adding class names and deploy version of Flickr Style netSergey Karayev1-0/+310
2014-09-21switch examples to lmdb (except for custom data loaders)Evan Shelhamer2-4/+8
2014-09-04fix fine-tuning example: paths, test acc., and total fine-tuning timeEvan Shelhamer1-1/+1
2014-09-04fix model download advice and prototxt name for fine-tuningEvan Shelhamer1-0/+0
2014-09-04script to upload/update model info as gistSergey Karayev1-0/+1
2014-09-04flickr style fine-tuning model (separated from example read me)Sergey Karayev3-0/+386
2014-09-04Renaming CaffeNet model prototxts and unignoring models/*Sergey Karayev7-2/+2
2014-09-04proofread model zooEvan Shelhamer1-3/+2
2014-09-04[models] adding zoo readme; caffenet, alexnet, and rcnn models in zoo formatSergey Karayev10-0/+1450
2014-03-19file pascal finetuning prototxt examples and fix pathsEvan Shelhamer3-761/+0
2014-03-19some cleanupRoss Girshick3-12/+11
2014-03-19fix pathsRoss Girshick2-2/+2
2014-03-19support for tightest square mode while finetuningRoss Girshick3-1/+3
2014-03-1910x learning rate for fine tuning makes a big differenceRoss Girshick3-9/+9
2014-03-19support for adding padding to windows in the window_data_layerRoss Girshick3-1/+3
2014-03-19Code that was used to finetune with reasonable successRoss Girshick3-5/+5
2014-03-19adjustments to try to match the setup for fine tuning with cuda-convnetRoss Girshick3-11/+11
2014-03-19define pascal finetuning modelsRoss Girshick3-0/+758
2014-03-18drop models/ in favor of examples/Evan Shelhamer3-352/+0
Move the Caffe reference imagenet model and script to fetch it to examples/imagenet. Caffe bundles reference models, but it makes more sense to keep them close to examples.
2014-03-18minor fix to caffe model DL scriptSergey Karayev1-2/+2
2014-03-18Add support for md5 checksum on OS XKai Li1-1/+6
2014-03-18Avoid repeatedly downloading caffe reference imagenet modelKai Li1-2/+16
2014-02-26remove padding layers in imagenet definitionslinmin1-40/+8
2014-02-26harmonize imagenet example, name caffe reference model CaffeNetEvan Shelhamer1-0/+1
2014-02-26everything in its right placeEvan Shelhamer8-935/+8