Isaac Godfried isaacmg
isaacmg
/ crossformer.json
Created
January 16, 2024 04:39
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "model_name": "Crossformer", | |
| "use_decoder": true, | |
| "model_type": "PyTorch", | |
| "model_params": { | |
| "n_time_series": 4, | |
| "forecast_history":6, | |
| "forecast_length": 4, | |
| "seg_len": 6 | |
| }, |
isaacmg
/ example.yaml
Created
February 5, 2021 18:27
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| wandb_version: 1 | |
| GCS: | |
| desc: null | |
| value: true | |
| _wandb: | |
| desc: null | |
| value: | |
| cli_version: 0.10.17 | |
| framework: torch |
isaacmg
/ model_xc_stash.py
Created
August 9, 2020 23:02
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import torch | |
| class TransformerXCBasic(torch.nn.Module): | |
| """ Transformer model """ | |
| def __init__(self, n_time_series, out_seq_len, device, d_model=128, dropout=.5, n_head=8): | |
| super(TransformerXCBasic, self).__init__() | |
| self.input_dim = n_time_series | |
| self.n_head = n_head |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| model = model_class.from_pretrained(self.args.model_path, | |
| config=config, | |
| # SpERT model parameters | |
| cls_token=self._tokenizer.convert_tokens_to_ids('[CLS]'), | |
| relation_types=input_reader.relation_type_count - 1, | |
| entity_types=input_reader.entity_type_count, | |
| max_pairs=self.args.max_pairs, | |
| prop_drop=self.args.prop_drop, | |
| size_embedding=self.args.size_embedding, | |
| freeze_transformer=self.args.freeze_transformer) |
isaacmg
/ defining_columns.py
Created
April 14, 2020 02:19
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| _column_definition = [ | |
| ('id', DataTypes.REAL_VALUED, InputTypes.ID), | |
| ('hours_from_start', DataTypes.REAL_VALUED, InputTypes.TIME), | |
| ('power_usage', DataTypes.REAL_VALUED, InputTypes.TARGET), | |
| ('hour', DataTypes.REAL_VALUED, InputTypes.KNOWN_INPUT), | |
| ('day_of_week', DataTypes.REAL_VALUED, InputTypes.KNOWN_INPUT), | |
| ('hours_from_start', DataTypes.REAL_VALUED, InputTypes.KNOWN_INPUT), | |
| ('categorical_id', DataTypes.CATEGORICAL, InputTypes.STATIC_INPUT), | |
| ] |
isaacmg
/ ade_eval.conf
Last active
April 5, 2020 18:52
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| label = conll04_eval | |
| model_type = spert | |
| model_path = data/models/ade | |
| tokenizer_path = data/models/ade | |
| dataset_path = data/datasets/ade/ade_split_0_test.json | |
| types_path = data/datasets/ade/ade_types.json | |
| eval_batch_size = 1 | |
| rel_filter_threshold = 0.4 | |
| size_embedding = 25 | |
| prop_drop = 0.1 |
isaacmg
/ eval_ade.conf
Created
April 5, 2020 18:50
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| label = ade_eval | |
| model_type = spert | |
| model_path = data/models/ade | |
| tokenizer_path = data/models/ade | |
| dataset_path = data/datasets/conll04/conll04_test.json | |
| types_path = data/datasets/conll04/conll04_types.json | |
| eval_batch_size = 1 | |
| rel_filter_threshold = 0.4 | |
| size_embedding = 25 | |
| prop_drop = 0.1 |
isaacmg
/ train_epoch_loop.py
Last active
February 11, 2020 18:03
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def train_epoch_loop(data_loader:DataLoader, opt:torch.optim, model:PyTorchForecast, takes_target:bool, forward_params={}) | |
| i = 0 | |
| running_loss = 0.0 | |
| for src, trg in data_loader: | |
| opt.zero_grad() | |
| # Convert to CPU/GPU/TPU | |
| src = src.to(model.device) | |
| trg = trg.to(model.device) | |
| # TODO figure how to avoid | |
| if takes_target: |
isaacmg
/ Dockerfile
Last active
February 10, 2020 21:20
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| FROM pytorch/pytorch:1.4-cuda10.1-cudnn7-devel | |
| COPY requirements.txt /tmp/ | |
| RUN pip install -r /tmp/requirements.txt | |
| ARG url | |
| RUN git clone -n https://github.com/example/example_repo | |
| RUN git checkout 543231 |
isaacmg
/ meta_model.py
Created
February 10, 2020 19:06
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| @TrainerBase.register('metatrainer') | |
| class MetaTrainer(Trainer): | |
| def __init__(self, | |
| model: Model, | |
| meta_model: MetaModel, | |
| optimizer: torch.optim.Optimizer, | |
| iterator: DataIterator, | |
| train_datasets: List[Iterable[Instance]], | |
| validation_datasets: Optional[Iterable[Instance]] = None, |
NewerOlder