network/double_towerasd.py

import torch
import dashscope
from http import HTTPStatus
from dashscope import TextEmbedding
from torch import nn
import torch.optim as optim
import pandas as pd
import numpy as np
dashscope.api_key = 'sk-44ccc9ab5e754eddb545cade12b632cf'
cache = {}
answerCache = []


def getem(question):
    global cache
    if question in cache.keys():
        return cache[question]
    resp = TextEmbedding.call(model=TextEmbedding.Models.text_embedding_v1,
                              input=question,
                              text_type='query')
    if resp.status_code == HTTPStatus.OK:
        cache[question] = resp['output']['embeddings'][0]['embedding']
        return resp['output']['embeddings'][0]['embedding']




# 创建模型实例
model = ConvNet()

# 定义损失函数和优化器
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

train = []
test = []
dataall = pd.read_csv('data.csv')
dataall = dataall.iloc[:, 1:4]

dataall = dataall.sample(frac=1)
train = dataall.iloc[0:300]
train = train.reset_index(drop=True)
test = dataall.iloc[300:]
test = test.reset_index(drop=True)
nlossLast = 0
for i in range(10):
    nloss = 0
    for k in range(len(train)):
        va = getem(train.iloc[k]['question'])
        vb = getem(train.iloc[k]['answer'])
        if train.iloc[k]['answer'] not in answerCache:
            answerCache.append(train.iloc[k]['answer'])
        va = torch.Tensor(va).reshape([1, 1, 1536])
        vb = torch.Tensor(vb).reshape([1, 1, 1536])
        output = model(va, vb)
        # 计算损失
        if train.iloc[k]['label'] == 1:
            loss = criterion(output,
                             torch.tensor(1).float())
        else:
            loss = criterion(output,
                             torch.tensor(0).float())
        # 反向传播并更新权重
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        nloss += loss
        if k % 50 == 0:
            print(i, k, 'done')
    print('one loop done', nloss/len(train))


p = 0
for i in range(len(test)):
    va = getem(test.iloc[i]['question'])
    Scores = np.zeros(len(answerCache))
    for j in range(len(answerCache)):
        vb = getem(answerCache[j])
        vaa = torch.Tensor(va).reshape([1, 1, len(va)])
        vbb = torch.Tensor(vb).reshape([1, 1, len(vb)])
        output = model(vaa, vbb)
        Scores[j] = output
    for k in range(2):
        if test.iloc[i]['label'] == 1:
            vc = test.iloc[i]['answer']
        else:
            vc = ''
        tt = Scores.argmax()
        if Scores[tt] > 0.5:
            vb = answerCache[tt]
            Scores[tt] = -1
        else:
            vb = ''
        if vb == vc:
            p += 1
            break
print(p/len(test))