Geoffrey Angus geoffreyangus
geoffreyangus
/ method_3.py
Created
November 21, 2022 21:17
Method 3: Running Inference on Each Module Separately
This file contains 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 json | |
| from pprint import pprint | |
| import pandas as pd | |
| import torch | |
| from ludwig.utils.inference_utils import to_inference_module_input_from_dataframe | |
| preprocessor = torch.jit.load( | |
| f"{EXPERIMENT_DIRECTORY}/torchscript/inference_preprocessor.pt") |
geoffreyangus
/ method_2.py
Created
November 21, 2022 21:17
Method 2: Convert `InferenceModule` Into a Single TorchScript Module
This file contains 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 json | |
| from pprint import pprint | |
| import pandas as pd | |
| import torch | |
| from ludwig.models.inference import InferenceModule | |
| from ludwig.utils.inference_utils import to_inference_module_input_from_dataframe | |
| inference_module = InferenceModule.from_directory( |
geoffreyangus
/ method_1.py
Last active
November 21, 2022 21:16
Method 1: Using the `InferenceModule` Class
This file contains 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 pprint import pprint | |
| import pandas as pd | |
| from ludwig.models.inference import InferenceModule | |
| inference_module = InferenceModule.from_directory( | |
| f"{EXPERIMENT_DIRECTORY}/torchscript") | |
| input_df = pd.read_parquet(f"{DATA_DIRECTORY}/twitter_bots.parquet") | |
| input_sample_df = input_df.head(2) |
geoffreyangus
/ twitter_bots_config.yaml
Last active
November 21, 2022 21:15
Step 0: Twitter Bots Ludwig config
This file contains 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
| input_features: | |
| - name: description | |
| type: text | |
| column: description | |
| - name: default_profile | |
| type: binary | |
| column: default_profile | |
| - name: default_profile_image | |
| type: binary | |
| column: default_profile_image |
geoffreyangus
/ issue2292_mnist.ipynb
Last active
November 8, 2022 19:29
Shows MNIST download, training, and TorchScript export, as well as errors from ONNX export.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
geoffreyangus
/ inference_module_example.ipynb
Created
July 19, 2022 23:42
This Gist demonstrates how to perform inference using a Torchscripted LudwigModel.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
geoffreyangus
/ cloudSettings
Last active
October 27, 2020 17:48
Visual Studio Code Settings Sync Gist
This file contains 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
| {"lastUpload":"2020-10-27T17:48:37.284Z","extensionVersion":"v3.4.3"} |