streamitでmachine translationのdemo
以下(model_streamit.py)を作成し、
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer import streamlit as st @st.cache(allow_output_mutation=True) def load_model_tokenizer(): model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M") tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M", src_lang="ja", tgt_lang="en") return model, tokenizer # adding the text that will show in the text box as default default_value = "最後の晩餐に出席した。" def main(): model, tokenizer = load_model_tokenizer() sent = st.text_area("テキストを入力し、Ctrl+Enterで解析結果を表示します。", default_value, height = 275) max_length = st.sidebar.slider("Max Length", min_value = 10, max_value=100, value=50) encoded_ja = tokenizer(sent, return_tensors="pt") generated_tokens = model.generate( **encoded_ja, forced_bos_token_id=tokenizer.get_lang_id("en"), max_length=max_length, ) generated_sequences = tokenizer.decode(generated_tokens[0], skip_special_tokens=True) st.write(generated_sequences) if __name__ == "__main__": main()
実行。
streamlit run model_streamit.py
pythonの最初の環境構築メモ
conda init zsh sh -c "$(curl -fsSL https://raw.github.com/ohmyzsh/ohmyzsh/master/tools/install.sh)" # conda create (GUIで操作しても良い) conda create --name [環境名] python=3.7 --prefix=[prefix] -y conda activate [環境名] jupyter kernelspec list ipython kernel install --user --name=[環境名] --display-name=[環境名] setting.json(remote) { "remote.autoForwardPortsSource": "output" } setting.json(workspace) { "remote.autoForwardPortsSource": "output", "python.pythonPath": "/root/anaconda3/bin/python(pyenv path)" } # kedro new kedro new cd [project名] git init … git push -u origin main conda env update --file environment.yml pip list --format freeze
name: [環境名] channels: - conda-forge - anaconda - default dependencies: - kedro - pre-commit - pytest - pytest-cov - tox - black - yapf - pylint - mypy - pip
絶対パスに変更(zsh)
- reorder-python-imports **/*.py
- absolufy-imports src/**/*.py --application-directories src/
git の subdirectoryをlocalにinstallする方法
pytorch の referenceをinstallする方法を探してたら、これが便利そう
$ svn ls https://github.com/pytorch/vision.git/trunk/references/detection README.md coco_eval.py coco_utils.py engine.py group_by_aspect_ratio.py train.py transforms.py utils.py $ svn ls https://github.com/pytorch/vision.git/trunk/references classification/ detection/ segmentation/ similarity/ video_classification/ $ svn export https://github.com/pytorch/vision.git/trunk/references A references A references/classification A references/classification/README.md A references/classification/train.py A references/classification/train_quantization.py ...
- utils の importができない場合のrename
google colab で動画が再生できなかった。
import base64 import io def play(file_path): video = io.open(file_path, 'r+b').read() encoded = base64.b64encode(video) return(HTML(data='''<video width="320" height="240" controls><source src="data:video/mp4;base64,{0}" type="video/mp4" /></video>'''.format(encoded.decode('ascii'))))
