Commit Graph

71 Commits

Author SHA1 Message Date
20170200aa Add api poetry script 2021-07-06 19:52:35 +02:00
b0503e8f1c Rename src folder to locimend 2021-07-06 19:51:51 +02:00
6cd9445e17 Remove batch size from the Input layer 2021-07-06 19:04:53 +02:00
acd231e633 Update trained model 2021-07-06 19:03:02 +02:00
5c9e2f4712 Add the async CLI execution of the inference 2021-07-06 19:01:50 +02:00
ab4a098289 Change last layers units to the number of bases 2021-07-06 18:01:06 +02:00
fba3c5318b Await prediction and print it in the caller 2021-07-06 17:56:43 +02:00
3ded0744b3 Bump nixpkgs revision 2021-07-06 07:29:29 +02:00
403fa23106 Serve model via REST API 2021-07-06 06:21:32 +02:00
f91abfe43d Remove deprecated Jupyter notebook 2021-07-06 04:06:23 +02:00
d0220ab1f0 Add AUC metric to model 2021-07-06 03:52:36 +02:00
c24f528484 Update trained model and dataset 2021-07-06 03:37:36 +02:00
6dd0d7e0ba Add trained model 2021-07-06 03:07:54 +02:00
1311b9b945 Apply isort to the project 2021-07-06 03:01:43 +02:00
92c6b54966 Implement model inference of sequences 2021-07-06 02:59:37 +02:00
1333a9256b Remove logs directory 2021-07-06 02:12:42 +02:00
eabb7f0285 Change model architecture to a MLP 2021-07-06 01:44:58 +02:00
1a1262b0b1 Pad and mask the sequences in each batch 2021-07-05 19:55:31 +02:00
70363a82a0 Refactor sequence preprocessing 2021-07-05 19:54:48 +02:00
72e3de945a Add type hints to the main module 2021-07-05 03:52:26 +02:00
bcc4f4b4d4 Parse data and label files from CLI arguments 2021-07-05 03:49:14 +02:00
a3780c9761 Move hyperparameters to a class 2021-07-05 03:24:54 +02:00
e07d0dcdbf Change Flatten layer, loss function and add Input 2021-06-26 17:52:20 +02:00
4d67bdac30 Add poetry installation step to README 2021-06-26 04:35:59 +02:00
1237394bb1 Perform one hot encoding on the sequences 2021-06-25 00:05:14 +02:00
e9582d0883 Parallelize dataset transformations 2021-06-24 19:54:19 +02:00
b2f20f2070 Revert "Remove dense Tensor transformation"
This reverts commit 0912600fdc.
2021-06-24 17:10:07 +02:00
c9466baa68 Align altered sequence with the reference sequence 2021-06-23 18:29:16 +02:00
0912600fdc Remove dense Tensor transformation 2021-06-23 18:28:09 +02:00
1e433c123f Remove base counts from the dataset 2021-06-16 13:02:49 +02:00
a2ae7bbe11 Add the Jupyter notebook 2021-06-15 01:00:45 +02:00
7a568f4f98 Create logs directory 2021-06-15 00:38:09 +02:00
7029b64906 Refactor the casting function using a loop 2021-06-15 00:22:55 +02:00
379303b440 Cast the parsed features to int32 2021-06-15 00:18:38 +02:00
d2e5fd0fa3 Build model incrementally 2021-06-14 23:32:49 +02:00
19ed847d12 Convert sequence and label to VarLenFeature 2021-06-14 19:33:42 +02:00
c6d0d5959d Update gitignore 2021-06-10 19:23:05 +02:00
2c07c5975f Add usage instructions 2021-06-10 19:22:41 +02:00
498d93de2a Execute the training loop in the model module 2021-06-10 13:27:55 +02:00
3b2b6c4af9 Remove deprecated org notebook 2021-06-10 13:19:03 +02:00
00e3389f5b Add datasets 2021-06-10 13:18:25 +02:00
08611de8e6 Fix Tensorflow seed assignment 2021-06-07 19:26:21 +02:00
0ce582250d Implement the training loop and metrics evaluation 2021-06-06 00:20:03 +02:00
168a68b50d Update documentation about data splits 2021-06-06 00:13:37 +02:00
8870da8543 Create a validation set 2021-06-06 00:04:18 +02:00
38903c5737 Rename ref_sequence to label 2021-06-06 00:03:15 +02:00
035162bd8d Fix position weight matrix assignment 2021-06-05 20:40:13 +02:00
02d20d4e72 Add reference sequence to each dataset instance 2021-06-05 20:34:59 +02:00
f30fc31c29 Update README 2021-06-04 12:18:44 +02:00
c9de0c8320 Add learning rate and l2 regularizer constants 2021-06-03 18:52:26 +02:00