diff --git a/data_extractor/code/infer_on_pdf.py b/data_extractor/code/infer_on_pdf.py index 089a7a8..e2a654c 100644 --- a/data_extractor/code/infer_on_pdf.py +++ b/data_extractor/code/infer_on_pdf.py @@ -1,7 +1,7 @@ import argparse import requests import os -import config_path +import utils.config_path as config_path import json import yaml import csv diff --git a/data_extractor/code/kpi_inference_data_pipeline/requirements.txt b/data_extractor/code/kpi_inference_data_pipeline/requirements.txt deleted file mode 100644 index 7854fbc..0000000 --- a/data_extractor/code/kpi_inference_data_pipeline/requirements.txt +++ /dev/null @@ -1,6 +0,0 @@ -fuzzywuzzy==0.18.0 -python-Levenshtein==0.12.0 -jupyter -tqdm==4.48.0 -xlrd==1.2.0 -pandas==1.0.5 diff --git a/data_extractor/code/model_pipeline/Dockerfile b/data_extractor/code/model_pipeline/Dockerfile index 1489cae..4f9cc6b 100644 --- a/data_extractor/code/model_pipeline/Dockerfile +++ b/data_extractor/code/model_pipeline/Dockerfile @@ -1,6 +1,6 @@ -ARG PYTORCH="1.6.0" -ARG CUDA="10.1" -ARG CUDNN="7" +ARG PYTORCH="1.11.0" +ARG CUDA="11.3" +ARG CUDNN="8" FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel ENV TORCH_CUDA_ARCH_LIST="3.7 6.0 6.1 7.0+PTX" @@ -9,10 +9,10 @@ RUN mkdir -p /.cache RUN chmod -R 777 /.cache RUN apt-key del 3bf863cc -RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub +RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub RUN apt-key del 7fa2af80 -RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub +RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu2004/x86_64/7fa2af80.pub RUN apt-get update RUN apt-get install -y unzip vim git wget @@ -26,9 +26,6 @@ RUN chmod -R 777 /app/code ENV SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL=True -WORKDIR /app/code/kpi_inference_data_pipeline -RUN pip install -e . - WORKDIR /app/code/model_pipeline RUN pip install -e . diff --git a/data_extractor/code/model_pipeline/requirements.txt b/data_extractor/code/model_pipeline/requirements.txt index 314bdc2..74c0974 100644 --- a/data_extractor/code/model_pipeline/requirements.txt +++ b/data_extractor/code/model_pipeline/requirements.txt @@ -1,19 +1,18 @@ -traitlets==5.4 -requests==2.26.0 -jinja2==3.0 -ipython==7.23.1 -urllib3==1.26.7 -gdown==3.11.1 -tqdm==4.48.0 -xlrd==1.2.0 +traitlets +requests +gdown +tqdm +xlrd pandas==1.0.5 -farm==0.5.0 -optuna==2.0.0 -Werkzeug==2.2.2 -Flask==2.2.5 -pyspellchecker==0.5.5 -spacy==2.3.2 -MarkupSafe==2.0.1 -boto3==1.18.15 -scikit-learn==0.24.1 -protobuf==3.20.0 +farm +optuna +Werkzeug==0.16.1 +Flask==1.1.4 +pyspellchecker +spacy +MarkupSafe +boto3 +scikit-learn +protobuf +fuzzywuzzy +python-Levenshtein