93f72d25af
update inference code for onnx
2019-08-15 15:27:51 +08:00
eb7bd93fef
sample of ONNX (verified on Torch1.2.0)
2019-08-15 15:09:41 +08:00
2c1e2822fa
Initial version
2019-08-13 17:08:52 +08:00
1b4995c639
Merge branch 'master' into dev/wutlin
2019-08-13 16:03:48 +08:00
58ad563a23
Add encoding cache and lazy-train mechanism ( #50 )
...
* Add new config about knowledge distillation for query binary classifier
* remove inferenced result in knowledge distillation for query binary classifier
* Add AUC.py in tools folder
* Add test_data_path into conf_kdqbc_bilstmattn_cnn.json
* Modify AUC.py
* Rename AUC.py into calculate_AUC.py
* Modify test&calculate AUC commands for Knowledge Distillation for Query Binary Classifier
* Add cpu_thread_num parameter in conf.training_params
* Rename cpu_thread_num into cpu_num_workers
* update comments in ModelConf.py
* Add cup_num_workers in model_zoo/advanced/conf.json
* Add the description of cpu_num_workers in Tutorial.md
* Update inference speed of compressed model
* Add ProcessorsScheduler Class
* Add license in ProcessorScheduler.py
* use lazy loading instead of one-off loading
* Remove Debug Info in problem.py
* use open instead of codecs.open
* update the inference of build dictionary for classification
* add md5 function in common_utils.py
* add merge_encode_* function
* update typo
* update typo
* reorg the logical flow in train.py
* remove dummy comments in problem.py
* add encoding cache mechanism
* add lazy-load mechanism for training phase
* enumerate problem types in problem.py
* remove data_encoding.py
* add lazy load train logic
* Modify comment and remove debug code
* Judge if test_path exists
* fix parameter missing when use char embedding
* merge master
* add file_column_num in problem.py
* merge add_encoding_cache branch
* add SST-2 in .gitignore
* merge master
* use steps_per_validation instead of valid_times_per_epoch
* Fix Learning Rate decay logic bug
* add log of calculating md5 of training data
* fix multi-gpu char_emb OOM problem & add char leval fix_lengths
* Modify batch_num_to_show_results in multi-gpu
* Modify batch_num_to_show_results
* delete deepcopy in get_batches
* add new parameters chunk_size and max_building_lines in conf and update tutorials
2019-08-02 20:59:00 +08:00
db26940fb6
delete Gating and HistogramMapping ( #76 )
2019-07-22 17:49:50 +08:00
1b805656ef
Dev/shining ( #75 )
...
* add text matching compression & delete regression
* modify the Tutorial.md
* modify the Tutorial.md
* add teacher model name
* modify tutorial.md
* fix transform params2tensors problem
* add softmax output layer for slot tagging
* add slot_tagging metrics
* modify make word emb matrix
* Delete dev.tsv
* Delete test.tsv
* Delete train.tsv
* delate conll data
* Update Contributing.md
* Update tools
* Update README.md
* Update Contributing.md
* Update README.md
* Update autotest.sh
* update get_results.py
* fix sequence tagging workflow
* add model type judgement for optimizer
* delete full atis dataset and unuseful config filee
* add slot_tagging sample data
* fix load embedding slow problem
* fix Char embedding CNN problem
* add lower token when load embedding matrix
* add word level length for char emb
* Update Conv
* Add ARCI & ARCII module and Modify Conv block
* Update to the same as master
* update Linear layer
* Add block - Calculate Distance of Two Vectors
* update tutorial_zh_CN
2019-07-19 06:26:29 +08:00
5e86455dca
Update Tutorial.md
2019-07-18 11:15:05 +08:00
e690ed6e91
add prediction mode in README ( #73 )
2019-07-09 13:52:00 -07:00
e79bf00ed2
change demo video
2019-06-30 22:23:28 +08:00
655477662c
add demo video
2019-06-30 22:20:24 +08:00
c33fd0b531
make pic bigger
2019-06-29 17:08:05 +08:00
98680b90a4
add model building graph
2019-06-29 17:06:10 +08:00
c7aa933716
add model building graph
2019-06-29 17:03:32 +08:00
644ae96a04
expand block contribution in Contributing.md ( #71 )
2019-06-28 16:59:30 +08:00
676c8283bd
add interactive prediction and register block ( #70 )
2019-06-28 16:58:33 +08:00
47008bb4d6
Modify sequence labeling tutorial ( #69 )
...
* add sequence labeling in tutorial
* add tag scheme convert script
* add paper link
* modify sequence labeling tutorial
* modify senquence labeling tutorial
2019-06-22 10:10:05 +08:00
3f69dac1ff
add CRF related block and logic ( #67 )
2019-06-19 14:44:07 +08:00
404785ffe6
Add Sequence labeling in Tutorial and tag scheme convert script ( #65 )
...
* add sequence labeling in tutorial
* add tag scheme convert script
* add paper link
2019-06-17 21:15:24 +08:00
9b2adb9a2f
Fix concat in interaction layer. ( #57 )
...
* Add Support for MatchPyramid model
* Modified interaction layer
* change 2d to 2D
* Flatten conflicts solved.
* fix conv2d and pooling2d
* add MatchPyramid score report
* add MatchPyramid score record
* Fix concat in interaction layer.
* merge
* Delete Conv2d.py
* Delete Pooling2d.py
* Delete test.json
* Update .gitignore
2019-06-14 14:15:11 +08:00
a1041f463d
update sequence tagging task workflow ( #62 )
2019-06-05 19:55:43 +08:00
f83ec2823e
add logo in Tutorials.md
2019-06-03 12:12:10 +08:00
83cc753dbd
change logo
2019-06-03 11:59:27 +08:00
22a9816b4a
change logo
2019-05-31 20:06:12 +08:00
a33c086d79
add logo
2019-05-31 20:05:10 +08:00
597a853b69
change wechat
2019-05-31 19:55:49 +08:00
aa03c7a400
update auto_test
2019-05-30 19:51:37 +08:00
917940540a
chmod 775 autotest.sh, chmod 775 dataset/get_glove.sh ( #61 )
2019-05-29 12:31:11 +08:00
516376ebe9
Merge branch 'master' of github.com:Microsoft/NeuronBlocks into dev/wutlin
2019-05-29 12:16:07 +08:00
a4be79706e
Update Contributing.md README ( #58 )
2019-05-28 18:40:51 +08:00
673f57d678
Update README.md
2019-05-28 12:16:18 +08:00
d65fbbc7b4
add autotest files ( #52 )
2019-05-28 12:05:32 +08:00
dee9dfdd12
Fix multi-gpu problem ( #55 )
2019-05-27 19:54:26 +08:00
7ca4ac7c3a
add cpu embedding matrix to optimizer ( #51 )
2019-05-27 14:16:05 +08:00
69c774a502
Improve optimizer
2019-05-24 11:55:40 +08:00
fe0655cc42
Fix embeding fine-tuning problem
2019-05-24 11:08:49 +08:00
5ec5fd2ef0
change qp match result
2019-05-23 23:04:58 +08:00
e90b9f2d4c
update matchpyramid result
2019-05-23 22:53:24 +08:00
a4e7821b7d
Fix import bug
2019-05-23 20:43:06 +08:00
34582ca564
Fix import error of Conv2D and Pooling2D
2019-05-23 20:31:55 +08:00
627d3216c5
Merge branch 'master' of github.com:Microsoft/NeuronBlocks into dev/wutlin
2019-05-23 20:10:00 +08:00
18be70a437
add citation
2019-05-23 19:36:41 +08:00
ba8210cc8c
change README.md
2019-05-23 18:30:14 +08:00
25d0684848
Fix paramter missing when using char embedding
2019-05-23 16:26:41 +08:00
e3d4cd55f9
add language verfication in verify_cache ( #45 )
2019-05-23 13:32:51 +08:00
17d99a6a7c
Add Support for MatchPyramid model ( #41 )
2019-05-23 13:32:05 +08:00
dc013c3355
Reorg logical flow in train ( #37 )
2019-05-23 07:55:17 +08:00
cab8038333
Merge branch 'master' of github.com:Microsoft/NeuronBlocks into dev/wutlin
2019-05-22 17:16:35 +08:00
8c82e17e6b
add Match layer, improve MatchAttention configuration, fix Concat3D bug ( #39 )
2019-05-16 07:58:59 +08:00
c2358dc2a5
Merge branch 'master' of github.com:Microsoft/NeuronBlocks into dev/wutlin
2019-05-15 19:12:51 +08:00
Wutao Lin
Flyer Cheng
boshining
adolphk-yk
L.J. SHOU
ssdf93
woailaosang
ericwtlin