使用flask在heroku bert pytorch模型上部署：错误：_pickle.UnpicklingError：无效的加载键，'v'

Posted 2023-02-16

【中文标题】使用flask在heroku bert pytorch模型上部署：错误：_pickle.UnpicklingError：无效的加载键，\'v\'

【英文标题】：Deploying on heroku bert pytorch model using flask: ERROR: _pickle.UnpicklingError: invalid load key, 'v'使用flask在heroku bert pytorch模型上部署：错误：_pickle.UnpicklingError：无效的加载键，'v'

【发布时间】：2020-09-05 02:48:33

【问题描述】：

尝试在 Heroku 上部署 bert 模型。

import torch
import transformers
import numpy as np
from flask import Flask, render_template, request
from model import DISTILBERTBaseUncased

MAX_LEN = 320
TOKENIZER = transformers.DistilBertTokenizer.from_pretrained(
    "distilbert-base-uncased", do_lower_case=True
)
DEVICE = "cpu"
MODEL = DISTILBERTBaseUncased()
MODEL.load_state_dict(torch.load("weight.bin"))
MODEL.to(DEVICE)
MODEL.eval()

app = Flask(__name__)


def sentence_prediction(sentence):
    tokenizer = TOKENIZER
    max_len = MAX_LEN
    comment = str(sentence)
    comment = " ".join(comment.split())

    inputs = tokenizer.encode_plus(
        comment,
        None,
        add_special_tokens=True,
        max_length=max_len,
        pad_to_max_length=True,
    )

    ids = inputs["input_ids"]
    mask = inputs["attention_mask"]

    ids = torch.tensor(ids, dtype=torch.long).unsqueeze(0)
    mask = torch.tensor(mask, dtype=torch.long).unsqueeze(0)

    ids = ids.to(DEVICE, dtype=torch.long)
    mask = mask.to(DEVICE, dtype=torch.long)

    outputs = MODEL(ids=ids, mask=mask)

    outputs = torch.sigmoid(outputs).cpu().detach().numpy()
    return outputs[0][0]


@app.route("/")
def index_page():
    return render_template("index.html")


@app.route("/model")
def models():
    return render_template("model.html")


@app.route("/predict", methods=["POST", "GET"])
def predict():
    if request.method == "POST":
        sentence = request.form.get("text")
        Toxic_prediction = sentence_prediction(sentence)
        return render_template(
            "index.html", prediction_text=np.round((Toxic_prediction * 100), 2)
        )
    return render_template("index.html", prediction_text="")


if __name__ == "__main__":
    app.run(debug=True)

错误

MODEL.load_state_dict(torch.load("weight.bin"))

2020-05-18T06:32:32.134536+00:00 app[web.1]：文件“/app/.heroku/python/lib/python3.7/site-packages/torch/serialization.py”，第 593 行，加载中

2020-05-18T06:32:32.134536+00:00 app[web.1]: return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)

2020-05-18T06:32:32.134536+00:00 app[web.1]：文件“/app/.heroku/python/lib/python3.7/site-packages/torch/serialization.py”， _legacy_load 中的第 763 行

2020-05-18T06:32:32.134537+00:00 app[web.1]: magic_number = pickle_module.load(f, **pickle_load_args)

2020-05-18T06:32:32.134537+00:00 app[web.1]: _pickle.UnpicklingError: invalid load key, 'v'。

代码在本地运行良好。 Heroku 部署方式为 Github weight.bin 大小为 255 MB flask API 在 localhost 中运行良好

【参考方案1】：

检查错误 1.MODEL.load_state_dict(torch.load("weight.bin")) --> 你应该在下面使用或正确检查字母。

model.load_state_dict(torch.load(model_state_dict))

2._pickle.UnpicklingError：无效的加载键，'v'。 --> 我认为您的环境中没有安装 git-lfs。安装后，再试一次。

【讨论】：

谢谢，@humber 我已经在我的环境中安装了 git-lfs。我已经浏览了这个链接elements.heroku.com/buildpacks/raxod502/…。它对我有帮助。