Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2015-12-01 | dismantle layer headers | Evan Shelhamer | 1 | -1/+1 | |
No more monolithic includes: split layers into their own headers for modular inclusion and build. | |||||
2015-11-06 | Fix ArgMaxLayer::Reshape for any num of bottom axes | Tim Meinhardt | 1 | -1/+3 | |
2015-10-21 | Clean redundant/unnecessary headers | Kang Kim | 1 | -2/+1 | |
2015-09-25 | Implement ArgMaxLayerTest for axis param | Tim Meinhardt | 1 | -13/+15 | |
2015-09-25 | Implement ArgMaxLayer forward_cpu and reshape for axis param | Tim Meinhardt | 1 | -15/+38 | |
2015-09-25 | Add argmax_param axis | Tim Meinhardt | 1 | -5/+17 | |
2015-02-05 | Layer type is a string | Jeff Donahue | 1 | -1/+1 | |
2014-10-13 | move registration code to corresponding cpp files. | Yangqing Jia | 1 | -0/+1 | |
2014-09-19 | fix types of (Layer)SetUp, Reshape, Forward, and Backward calls | Jonathan L Long | 1 | -8/+8 | |
Using the type vector<Blob<Dtype*>* for outputs allows modification of the vector itself, while it is only okay to modify the blobs pointed to by the elements of the vector. Switching the types to const vector<Blob<Dtype>*>& makes them more correct. | |||||
2014-09-18 | split off Reshape for common layers | Jonathan L Long | 1 | -0/+5 | |
2014-08-13 | Generalize loss by allowing any top blob to be used as a loss in which | Jeff Donahue | 1 | -4/+2 | |
its elements are summed with a scalar coefficient. Forward for layers no longer returns a loss; instead all loss layers must have top blobs. Existing loss layers are given a top blob automatically by Net::Init, with an associated top_loss_weight of 1 (set in LossLayer::FurtherSetUp). Due to the increased amount of common SetUp logic, the SetUp interface is modified such that all subclasses should normally override FurtherSetUp only, which is called by SetUp. | |||||
2014-08-06 | LICENSE governs the whole project so strip file headers | Evan Shelhamer | 1 | -2/+0 | |
2014-07-20 | remove unused includes in AccuracyLayer and ArgMaxLayer | Jonathan L Long | 1 | -2/+0 | |
2014-07-20 | Fix style issues in accuracy & argmax layer | Kai Li | 1 | -15/+8 | |
2014-07-20 | Limit the comparison functions to have file scope | Kai Li | 1 | -1/+1 | |
2014-07-20 | Move compararing function from common_layers to argmax_layer | Kai Li | 1 | -1/+9 | |
2014-07-20 | Use std::partial_sort in the ArgMaxLayer as suggested by @shuokay | Kai Li | 1 | -2/+3 | |
2014-07-20 | Simplify the top-k argmax layer using std::sort | Kai Li | 1 | -30/+8 | |
2014-07-20 | Extend the ArgMaxLayer to output top k results | Kai Li | 1 | -13/+41 | |
2014-06-20 | remove erroneous comment in ArgMaxLayer | Jonathan L Long | 1 | -1/+0 | |
2014-06-08 | layers declare their names and number of input/output blobs, and don't | Jeff Donahue | 1 | -2/+1 | |
check top/bottom blob counts explicitly in SetUp; instead call base Layer::SetUp. | |||||
2014-05-20 | Fixed lint errors due to ArgmaxLayer | Sergey Karayev | 1 | -6/+5 | |
2014-05-20 | Added FLT_MAX to argmax layer | Sergio Guadarrama | 1 | -2/+1 | |
2014-05-20 | Added ArgMax Layer | Sergio Guadarrama | 1 | -0/+59 | |
Conflicts: src/caffe/proto/caffe.proto |