- 29 May, 2018 40 commits
-
-
* Change the way to import ONNX model. * Decide ONNX version and change the processing * Check whether onnx has the attribute '__version__'
Takeo Imai committed -
* fix for composed symbol * fix * clean up * fix exception type
Joshua Z. Zhang committed -
* add coreml * fix bool * fix flatten in fullyconnected * fix duplicate flatten * fix syntax * add tutorial * fix mxnet flatten, fix tutorials * fix flatten issue * fix lint
Joshua Z. Zhang committed -
Tianqi Chen committed
-
* [TEST] include coreml tools in docker * upgrade tvm
Tianqi Chen committed -
Tianqi Chen committed
-
* [PASS] FoldScaleAxis * Move FoldAxis to O3 * Set unroll to 0 when ready
Tianqi Chen committed -
* add transform * fix * update doc * Update tvm
Xingjian Shi committed -
Tianqi Chen committed
-
* init onnx finish onnx frontend add onnx tests fix various backup use transformer [Frontend] graph passed add test forward test forward fix doc and lint fix test graph tuple from_onnx now take 2 args, output (sym, params) fix rename fix input names fix multiple fix lint fix lint check * better doc
Joshua Z. Zhang committed -
Tianqi Chen committed
-
Tianqi Chen committed
-
Tianqi Chen committed
-
Tianqi Chen committed
-
* [TUTORIAL] Move mobilenet to tutorial, fix precompute_prune * Some language improvements
Tianqi Chen committed -
* register pool, global_pool; add mobilenet example * tests of pool and global_pool * use new API of runtime module * small fix
Yuwei HU committed -
Tianqi Chen committed
-
Tianqi Chen committed
-
graph backup update finish mxnet converter fix fix various add tests fix add multi networks uses model_zoo fix tests minor fix fix graph fix
Joshua Z. Zhang committed -
Tianqi Chen committed
-
Tianqi Chen committed
-
Tianqi Chen committed
-
* [TOP] Add dense, batchnorm * update tvm
Tianqi Chen committed -
* [RUNTIME][COMPILER] Formal compiler pipeline, runtime wrapper module * more detailed comments
Tianqi Chen committed -
Tianqi Chen committed
-
Tianqi Chen committed
-
* register depthconv, elemwise * use global elemwise schedule for relu
Yuwei HU committed -
Yuwei HU committed
-
* [PASS] PrecomputePrune, add testcase * update comment
Tianqi Chen committed -
Tianqi Chen committed
-
* [TOP] level4 except argmax/min, correct split * [DOCS] Add doc generator for top
Tianqi Chen committed -
* [TOP] complete level2 * [TOP] add split
Tianqi Chen committed -
Tianqi Chen committed
-
Tianqi Chen committed
-
tqchen committed
-
tqchen committed
-
* [ATTR/SYMBOL] Expose op_name attr to python * fix xcode
Tianqi Chen committed -
* Change TShape::index_t to int64_t * Add comment * Make Tuple::Save&Load dtype generic * trigger update * Fix lint * Fix comment * Change index_t to dim_t * Remove legacy index_t
ziheng committed -
* Imbalance version of shared pool during plan memory * Bug fix for no shared_pool case * Auto search and updated shared mem pool * Cleanup unused code * Cleanup logging code * Add unit test for shared storage * Remove shared pool in PlanMemory. Fix lint warnings * Fix lint warnings * Use reference instead of ptrs
Haibin Lin committed -
Eric Junyuan Xie committed
-