Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2014-07-11 | [docs] shelhamer's minor suggestions | Sergey Karayev | 1 | -1/+1 | |
2014-07-11 | [docs] moved example md’s to examples/**/md’s and added script to gather | Sergey Karayev | 7 | -6/+555 | |
them for publication | |||||
2014-07-11 | host materials on dl.caffe.berkeleyvision.org | Evan Shelhamer | 2 | -2/+2 | |
2014-05-22 | release v1 model defs + weights | Evan Shelhamer | 5 | -351/+301 | |
- Caffe reference ImageNet model - AlexNet Note that one can upgrade the weights locally by `upgrade_net_proto_binary.bin` to avoid re-downloading. | |||||
2014-05-20 | Back-merge changes in master | Evan Shelhamer | 6 | -0/+886 | |
* master: bundle presentation in gh-pages for now... fix typo pointed out by @yinxusen note support for non-MKL installation in dev include pretrained snapshot and performance details Document AlexNet model, include download script define AlexNet architecture polished ignore | |||||
2014-05-20 | update notebook examples with new wrapper usage, re-organize | Evan Shelhamer | 4 | -536/+637 | |
2014-05-09 | make solver_mode an enum with CPU and GPU -- fully backwards compatible | Jeff Donahue | 7 | -15/+16 | |
with old 0/1 style | |||||
2014-05-06 | note bug in cifar10 full with CPU computation | Jeff Donahue | 1 | -0/+5 | |
2014-04-18 | fix examples path in mnist leveldb sh | Evan Shelhamer | 1 | -1/+1 | |
2014-04-15 | mnist_autoencoder_solver cleanup | Jeff Donahue | 1 | -3/+2 | |
2014-04-15 | make solver able to compute and display test loss | Jeff Donahue | 2 | -20/+1 | |
2014-04-15 | mnist autoencoder test proto bugfix: add sigmoid layer before loss | Jeff Donahue | 1 | -4/+6 | |
2014-04-15 | enable DataLayer to output unlabeled data | Jeff Donahue | 2 | -2/+0 | |
2014-04-15 | add mnist autoencoder example necessities (sigmoid cross entropy loss | Jeff Donahue | 4 | -0/+418 | |
layer, sparse gaussian filler) | |||||
2014-04-15 | Document AlexNet model, include download script | Evan Shelhamer | 1 | -0/+28 | |
2014-04-15 | define AlexNet architecture | Evan Shelhamer | 5 | -0/+858 | |
Swap order of lrn and max pooling layers to reflect Krizhevsky architecture. Initialize biases to 0.1 where Krizhevsky had 1, as training by initialization with 1 has flat loss. | |||||
2014-04-15 | rename lenet dir to mnist | Jeff Donahue | 7 | -0/+0 | |
2014-04-09 | Back-merge docs and example image changes from `master` to `dev` | Evan Shelhamer | 2 | -29/+31 | |
2014-04-08 | re-time imagenet example on k20, instead of my laptop | Evan Shelhamer | 1 | -6/+6 | |
2014-04-08 | Drop Lena image in favor of a cute cat photo | Evan Shelhamer | 3 | -47/+42 | |
Social progress. | |||||
2014-04-08 | replace old cifar full with within channel LRN (per cuda-convnet | Jeff Donahue | 9 | -458/+12 | |
layers-18pct) -- slightly slower (5000 iters now takes 6:57; took 6:43 previously), but slightly more accurate (exactly 82% test accuracy; got 81.65% before) | |||||
2014-04-08 | merge LRNMapLayer into LRNLayer with norm_region proto field | Jeff Donahue | 7 | -33/+37 | |
2014-04-08 | fix some param bugs | Jeff Donahue | 3 | -6/+5 | |
2014-04-08 | add cifar example using LRN_MAP (just like the cuda-convnet layers-18pct | Jeff Donahue | 6 | -0/+452 | |
architecture) instead of LRN | |||||
2014-04-07 | Back-merge documentation and fixes | Evan Shelhamer | 2 | -2/+2 | |
format installation docs, add links Add hdf5 requirements to 10.9 notes, drop cmake (not linked) fix im2col height/width bound check bug (issue #284 identified by @kmatzen) strip confusing confusing comment about shuffling files add /etc/rc.local hint for boot configuration of gpus Include k40 images per day benchmark drop caffe presentation in favor of dropbox link make build_docs.sh script work from anywhere proofread, fix dead link, standardize NVIDIA capitalization Added Link in index.md to perfomance_hardware.md Added Performance and Hardware Tips imagenet fix: ilvsrc -> ilsvrc | |||||
2014-03-31 | Removed fillers from imagenet_deploy | Sergio Guadarrama | 1 | -64/+0 | |
2014-03-28 | imagenet fix: ilvsrc -> ilsvrc | Yangqing Jia | 2 | -2/+2 | |
2014-03-27 | rollback previous commit adding version number to NetParameter -- going | Jeff Donahue | 16 | -21/+1 | |
a different route | |||||
2014-03-27 | add NetParameter required version number as breaking change for | Jeff Donahue | 16 | -1/+21 | |
V0NetParameter | |||||
2014-03-27 | regenerate imagenet_val feature extraction prototxt with missing | Jeff Donahue | 1 | -0/+9 | |
IMAGE_DATA params | |||||
2014-03-27 | upgrade remaining prototxts | Jeff Donahue | 6 | -762/+607 | |
2014-03-27 | convert existing models to new format (used tools/upgrade_net_proto with | Jeff Donahue | 10 | -1236/+1112 | |
no manual editing) | |||||
2014-03-27 | Standardize copyright, add root-level CONTRIBUTORS credit | Evan Shelhamer | 2 | -2/+2 | |
2014-03-25 | removing lena in favor of cat | Sergey Karayev | 2 | -35/+28 | |
2014-03-19 | Back-merge documentation and script fixes | Evan Shelhamer | 2 | -2/+2 | |
fix script path incantation convert css indentation to spaces fix cifar10 leveldb creation path wget without checking certificate for dropbox (dodge complaint on linux) docs: added list of contributors minor style update of docs | |||||
2014-03-19 | fix cifar10 leveldb creation path | Evan Shelhamer | 1 | -1/+1 | |
2014-03-19 | wget without checking certificate for dropbox (dodge complaint on linux) | Evan Shelhamer | 1 | -1/+1 | |
2014-03-19 | Fix to #161 | Sergey Karayev | 2 | -25/+247 | |
- signficantly change the documentation file - link to it from index.md - remove the image resizing script, since (a) it does not work, (b) is obviated by using ImagesLayer - add sample prototxt that uses ImagesLayer. | |||||
2014-03-19 | Merge pull request #161 from kloudkl/simplify_feature_extraction | Sergey Karayev | 1 | -0/+25 | |
Feature extraction, feature binarization and image retrieval examples | |||||
2014-03-19 | file pascal finetuning prototxt examples and fix paths | Evan Shelhamer | 3 | -0/+761 | |
2014-03-19 | Removing feature binarization and image retrieval examples | Kai Li | 2 | -337/+0 | |
2014-03-19 | Move binarize_features, retrieve_images to examples/feauture_extraction | Kai Li | 3 | -0/+362 | |
2014-03-19 | Move extract_features, binarize_features, retrieve_images to tools/ | Kai Li | 3 | -494/+0 | |
2014-03-19 | Save and load data correctly in feat extracion, binarization and IR demo | Kai Li | 3 | -61/+57 | |
2014-03-19 | Change feature binarization threshold to be the mean of all the values | Kai Li | 1 | -57/+53 | |
rather than zero in the feature binarization example | |||||
2014-03-19 | Fix saving real valued feature bug in the feature extraction example | Kai Li | 1 | -7/+3 | |
2014-03-19 | Fix bugs in the image retrieval example | Kai Li | 1 | -84/+36 | |
2014-03-19 | Fix bugs of the feature binarization example | Kai Li | 1 | -46/+37 | |
2014-03-19 | Enhance help, log message & format of the feature extraction example | Kai Li | 1 | -70/+70 | |
2014-03-19 | Fix bugs in the feature extraction example | Kai Li | 1 | -64/+53 | |