政务中心网站建设方案,无锡手机网站建设方案,可以做兼职的网站有哪些工作室,13个实用平面设计网站前言#xff1a; 昨天我们讲述了怎么利用emotion数据集进行deberta-v3-large大模型的微调#xff0c;那今天我们就来输入一些数据来测试一下#xff0c;看看模型的准确率#xff0c;为了方便起见#xff0c;我直接用测试集的前十条数据 代码#xff1a; from transfor…前言 昨天我们讲述了怎么利用emotion数据集进行deberta-v3-large大模型的微调那今天我们就来输入一些数据来测试一下看看模型的准确率为了方便起见我直接用测试集的前十条数据 代码 from transformers import AutoModelForSequenceClassification,AutoTokenizer import torch import numpytokenizer AutoTokenizer.from_pretrained(deberta-v3-large) model AutoModelForSequenceClassification.from_pretrained(result/checkpoint-500,num_labels6)raw_inputs [im feeling rather rotten so im not very ambitious right now,im updating my blog because i feel shitty,i never make her separate from me because i don t ever want her to feel like i m ashamed with her,i left with my bouquet of red and yellow tulips under my arm feeling slightly more optimistic than when i arrived,i was feeling a little vain when i did this one,i cant walk into a shop anywhere where i do not feel uncomfortable,i felt anger when at the end of a telephone call,i explain why i clung to a relationship with a boy who was in many ways immature and uncommitted despite the excitement i should have been feeling for g etting accepted into the masters program at the university of virginia,i like to have the same breathless feeling as a reader eager to see what will happen next,i jest i feel grumpy tired and pre menstrual which i probably am but then again its only been a week and im about as fit as a walrus on vacation for thesummer ] inputs tokenizer(raw_inputs, paddingTrue, truncationTrue, return_tensorspt) outputs model(**inputs) print(outputs.logits.argmax(-1).numpy())output_tensor torch.softmax(outputs.logits, dim1)numpy.set_printoptions(suppressTrue, precision15) print(output_tensor.detach().numpy()) 标注结果 [0 0 0 1 0 4 3 1 1 3] 测试结果 [0 0 0 1 0 4 4 2 1 3] [[0.99185866 0.0011510316 0.00038844926 0.0026896652 0.00296234010.00094986777][0.9918577 0.0011512033 0.00038886679 0.0026923663 0.00295853150.000951257 ][0.99185807 0.0011446937 0.00038163515 0.0026456509 0.00303544850.00093440723][0.00041773843 0.9972398 0.0014854104 0.0002909223 0.000362315240.00020376328][0.99185014 0.0011451623 0.00038086114 0.0026396883 0.00305240350.00093187904][0.015044774 0.0025362356 0.00041989447 0.015223678 0.950097140.016678285 ][0.11319714 0.030935207 0.007336047 0.3035547 0.475454330.069522515 ][0.0011094044 0.18334262 0.8081213 0.0011003793 0.00072979650.005596481 ][0.0004444314 0.9972433 0.0014491597 0.00028465112 0.000374119760.00020446534][0.00241266 0.00079152075 0.00092184055 0.9924028 0.00241092480.0010602956 ]] 结果对比 除了第七、第八条数据错误外其他的八条数据都是正确的 代码解释 1、raw_inputs用户输入的数据这个地方你可以使用一个while循环然后使用input来与用户进行交互需要注意的是这个必须是一个数组哪怕用户只输入了一句文本。 2、return_tensorspt表示tokenizer返回的是PyTorch格式的数据 3、argmax(-1)将logits属性中的浮点数张量沿着最后一个轴即-1轴进行argmax操作从而找到该张量中最大值所对应的标签编号。 4、softmax(outputs.logits, dim1)dim指沿着哪个维度计算softmax通常指定为1表示对每一行进行softmax操作。如果不指定则默认在最后一维计算softmax。 5、numpy.set_printoptions(suppressTrue, precision15)使用 numpy.set_printoptions() 函数来设置打印选项从而调整打印输出格式。其中suppress 选项可以关闭科学计数法precision 选项可以设置打印精度。