Chintan Shah
|
ba880b8230
|
Implementing load and save models and early stopping
|
2019-10-04 17:25:03 -04:00 |
|
Chintan Shah
|
d9f41172dc
|
Implemented eval and function
|
2019-10-04 17:07:38 -04:00 |
|
Chintan Shah
|
20c6aa5862
|
Fixed bugs with refactoring
|
2019-10-04 16:05:52 -04:00 |
|
Chintan Shah
|
2b8d5e6b31
|
Refactored code and moved everything into a DCRNN forward pass
|
2019-10-04 13:02:50 -04:00 |
|
Chintan Shah
|
f41dc442b0
|
Implemented gradient clipping and returning output from training one batch
|
2019-10-03 19:35:54 -04:00 |
Chintan Shah
|
9834b12d5a
|
Cleaned up code, fixed bugs in implementation, seems like it starts training with GRU
|
2019-10-02 22:20:43 -04:00 |
|
Chintan Shah
|
f96a8c0d59
|
Dirty commit - setup model but [GRUCell] not working, tried ParameterList, did not work
|
2019-10-02 18:09:33 -04:00 |
|
Chintan Shah
|
c876cbfba3
|
Setup training loop and logging
|
2019-10-02 17:34:07 -04:00 |
|
Chintan Shah
|
86c4c5704d
|
Implemented single batch forward pass
|
2019-10-01 22:47:59 -04:00 |
|
Chintan Shah
|
69288460b1
|
Simplified encoder decoder model and moved curriculum learning outside
|
2019-10-01 10:07:34 -04:00 |
|
Chintan Shah
|
a1c9af2bad
|
Setup curriculum learning framework
|
2019-09-30 21:58:55 -04:00 |
|
Chintan Shah
|
bdce241a8f
|
Implemented abstract method and changed scheme to do all layers first for each timestep
|
2019-09-30 20:32:31 -04:00 |
|
Chintan Shah
|
0769a3b2e2
|
Implemented seq2seq without DCGRU and curriculum learning
|
2019-09-30 19:14:24 -04:00 |
|
Chintan Shah
|
7349f2ed67
|
Figured out decoder shapes
|
2019-09-30 16:04:03 -04:00 |
|
Chintan Shah
|
6386ac7eb4
|
Implemented encoder using GRUCell instead so that it's easier to swap that with DCGRUCell
|
2019-09-29 17:40:52 -04:00 |
|
Chintan Shah
|
66fb202d21
|
Implemented Encoder with GRU - should swap GRU with DCGRU
|
2019-09-29 12:51:49 -04:00 |
|
Chintan Shah
|
69d6c0e053
|
Add Dockerfile
|
2019-09-07 17:18:31 -04:00 |
Yaguang
|
8c20ca1a9c
|
Adds baseline methods for evaluation.
|
2019-06-18 13:00:24 -07:00 |
|
Yaguang
|
37f0734cb4
|
Update README.md
|
2019-03-18 21:32:57 -07:00 |
|
Yaguang
|
3caf887484
|
Add data example.
|
2019-03-17 11:56:55 -07:00 |
|
Yaguang
|
4344dddc6d
|
Add instructions on using HDF5 with python.
|
2019-03-17 11:43:30 -07:00 |
|
Yaguang
|
81b4626193
|
Remove unused code.
|
2019-01-18 19:00:34 -08:00 |
|
Yaguang
|
734ecbc138
|
Update README.md
|
2019-01-12 12:04:28 -08:00 |
|
Yaguang
|
763eb7af69
|
Add pretrained model on PEMS-BAY.
|
2019-01-10 17:44:07 -08:00 |
|
Yaguang
|
ad36deb794
|
Update README.md
Add more instructions.
|
2019-01-08 11:33:20 -08:00 |
|
liyaguang
|
c8a676604b
|
Add PEMS-BAY configuration.
|
2019-01-08 11:21:22 -08:00 |
|
Yaguang
|
1481b24b1b
|
Update README.md
Fix typo in the Graph Construction script (thanks to Zifeng Kang).
|
2018-12-24 00:47:17 -08:00 |
|
Yaguang
|
ac5321fcf7
|
Update README.md
Add an additional link for data sharing.
|
2018-11-03 11:54:22 -07:00 |
|
Yaguang
|
a8aa1732a9
|
Update README.md
|
2018-10-12 13:30:53 -07:00 |
|
Yaguang
|
d59d44e4f0
|
Code refactor.
|
2018-10-01 17:45:46 -07:00 |
|
Yaguang
|
bbc06b6c0c
|
Add log level support and load_dataset method.
|
2018-10-01 17:45:28 -07:00 |
|
Yaguang
|
88d9fc86d1
|
Update instructions for graph generation.
|
2018-10-01 10:54:56 -07:00 |
|
Yaguang
|
e6645df191
|
Update README.
|
2018-10-01 09:59:47 -07:00 |
|
Yaguang
|
2e4b8c868f
|
Merge pull request #9 from liyaguang/v2
Upgrading to DCRNN v2.
|
2018-10-01 09:56:22 -07:00 |
|
Yaguang
|
9520e6cf85
|
Update pretrained model.
|
2018-10-01 09:47:23 -07:00 |
|
Yaguang
|
e0212cc178
|
Update README and requirements.
|
2018-09-30 22:15:27 -07:00 |
|
Yaguang
|
7e05414d99
|
Combine Val and Test model.
|
2018-09-30 22:14:45 -07:00 |
|
Yaguang
|
5dc36fed7c
|
Refactor DCRNN Model.
|
2018-09-30 21:53:40 -07:00 |
|
Yaguang
|
2f2d748b45
|
Add AMSGrad from https://github.com/taki0112/AMSGrad-Tensorflow for stablized Adam Training.
|
2018-09-30 21:52:20 -07:00 |
|
Yaguang
|
e8d6c08db0
|
Merge log_helper into utils and change logging mechanism.
|
2018-09-26 11:33:21 -07:00 |
|
Yaguang
|
9ec161543b
|
Code refactoring, including data loading, logging, configuration, removing redundant code.
|
2018-09-26 11:19:00 -07:00 |
|
Yaguang
|
80e156c580
|
Update README.md
Add data file name.
|
2018-07-22 18:55:35 +08:00 |
|
Yaguang
|
67bd763b18
|
Update README.md
Add data file name.
|
2018-07-22 18:53:50 +08:00 |
|
Yaguang
|
17927239a7
|
Update the pretrained model and results.
|
2018-06-07 11:18:55 +08:00 |
|
Yaguang
|
e08002d72d
|
Update the seq2seq training logic.
|
2018-06-07 11:16:33 +08:00 |
|
Yaguang
|
562514cc30
|
Add a more data-efficient training data generation method.
|
2018-06-07 10:41:47 +08:00 |
|
Yaguang
|
e93435c598
|
Replace json with yaml for configuration.
|
2018-04-18 11:51:35 -07:00 |
|
Yaguang
|
3e94a0ff0e
|
Adds support for python 3.5 and python 3.6.
|
2018-04-18 11:50:39 -07:00 |
|
Yaguang
|
fcdf62d6de
|
Update reference.
|
2018-03-30 13:42:12 -07:00 |
|
Yaguang
|
90e39f5a4a
|
Update README to include the lat/lon file.
|
2018-03-29 17:58:52 -07:00 |