Document feedback

Question document fragment

When a question document fragment contains a formula, it is displayed as a space.

Submission type

issue

It's a little complicated...

I'd like to ask someone.

PR

Just a small problem.

I can fix it online!

Please select the submission type

Problem type

Specifications and Common Mistakes

- Specifications and Common Mistakes:

- Misspellings or punctuation mistakes,incorrect formulas, abnormal display.

- Incorrect links, empty cells, or wrong formats.

- Chinese characters in English context.

- Minor inconsistencies between the UI and descriptions.

- Low writing fluency that does not affect understanding.

- Incorrect version numbers, including software package names and version numbers on the UI.

Usability

- Usability:

- Incorrect or missing key steps.

- Missing main function descriptions, keyword explanation, necessary prerequisites, or precautions.

- Ambiguous descriptions, unclear reference, or contradictory context.

- Unclear logic, such as missing classifications, items, and steps.

Correctness

- Correctness:

- Technical principles, function descriptions, supported platforms, parameter types, or exceptions inconsistent with that of software implementation.

- Incorrect schematic or architecture diagrams.

- Incorrect commands or command parameters.

- Incorrect code.

- Commands inconsistent with the functions.

- Wrong screenshots.

- Sample code running error, or running results inconsistent with the expectation.

Risk Warnings

- Risk Warnings:

- Lack of risk warnings for operations that may damage the system or important data.

Content Compliance

- Content Compliance:

- Contents that may violate applicable laws and regulations or geo-cultural context-sensitive words and expressions.

- Copyright infringement.

Please select the type of question

Problem description

Describe the bug so that we can quickly locate the problem.

Submit

Document feedback

mindformers.core.PromptAccMetric

class mindformers.core.PromptAccMetric

Computes the prompt acc of each entity. The prompt acc is the accuracy of text classification base on building prompt. The accurate index is the index of the prompt which has the minimum perplexity.

1. Build the prompt for this metric is described as follows:

   这是关于**体育**的文章：$passage
   这是关于**文化**的文章：$passage
   

2. Computes perplexity of each generated context based on prompt. Perplexity is a measurement about how well a probability distribution or a model predicts a sample. A low perplexity indicates the model can predict the sample well. The function is shown as follows:

   $$PP(W)=P(w_1{w}_2...w_N{)}^{-\frac{1}{N}}=\sqrt[N]{\frac{1}{P(w_1{w}_2...w_N)}}$$

   Where $w$ represents words in corpus.

3. Compute classification result by choosing the index of the prompt which has the minimum perplexity.

4. Count the number of correctly classified and the total number of samples and compute the acc as follows:

   $$\text{accuracy}=\frac{\text{correct\_sample\_nums}}{\text{total\_sample\_nums}}$$

Examples

>>> import numpy as np
>>> from mindspore import Tensor
>>> from mindformers.core.metric.metric import PromptAccMetric
>>> logtis = Tensor(np.array([[[[0.2, 0.5], [0.3, 0.1], [0.9, 0.6]]]]))
>>> input_ids = Tensor(np.array([[15, 16, 17]]))
>>> labels = Tensor(np.array([[1, 0, 1]]))
>>> mask = Tensor(np.array([[1, 1, 1]]))
>>> metric = PromptAccMetric()
>>> metric.clear()
>>> metric.update(logtis, input_ids, mask, labels)
>>> result = metric.eval()
>>> print(result)
Current data num is 1, total acc num is 1.0, ACC is 1.000
Acc: 1.000, total_acc_num: 1.0, total_num: 1
{'Acc': 1.0}