# Implementation of the multiclass case for precision metric

**URL:** <https://discuss.pytorch.org/t/implementation-of-the-multiclass-case-for-precision-metric/139655>\
**Category:** ignite\
**Created:** [December 17, 2021, 7:52pm UTC](https://discuss.pytorch.org/t/implementation-of-the-multiclass-case-for-precision-metric/139655 "2021-12-17T19:52:17Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![jamba\_juice](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/jamba_juice/32/45030_2.png) [@jamba\_juice](https://discuss.pytorch.org/u/jamba_juice)\
**Post date:** [December 17, 2021, 7:52pm UTC](https://discuss.pytorch.org/t/implementation-of-the-multiclass-case-for-precision-metric/139655/1 "2021-12-17T19:52:17Z")

</div>

Hi, I wanted to try the example of the multiclass case for precision metric from the ignite library with Average=True. I used the exact same values and code but still got an error. I was interested to test out different cases and binary & multilabel seem to work, but the multiclass case is not working as it should work like in the docs.

```auto
import torch
from ignite.engine import Engine
from ignite.metrics import Precision
def process_function(engine, data):
  return data[0][0], data[0][1]
default_evaluator = Engine(process_function)

metric = Precision(average=True)
metric.attach(default_evaluator, "precision")
y_true = torch.Tensor([2, 0, 2, 1, 0, 1]).long()
y_pred = torch.Tensor([
    [0.0266, 0.1719, 0.3055],
    [0.6886, 0.3978, 0.8176],
    [0.9230, 0.0197, 0.8395],
    [0.1785, 0.2670, 0.6084],
    [0.8448, 0.7177, 0.7288],
    [0.7748, 0.9542, 0.8573],
])
state = default_evaluator.run([[y_pred, y_true]])
print(state.metrics["precision"])

```

This is the error I get:

 ![image](https://discuss.pytorch.org/uploads/default/original/3X/2/f/2fdcb4c85ba5986d5b114c130c2a67008fc69fbb.png)

**In the docs link below, you can find the same code block for the multiclass case, and they get the precision as 0.6111…**

> **[Precision — PyTorch-Ignite v0.4.13 Documentation](https://pytorch.org/ignite/master/generated/ignite.metrics.precision.Precision.html)**
>
> High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

I would be very grateful if someone could point out where I was going wrong, or if I need to do something else to test the multiclass case for precision.

Thank you!

---

<div class="post-metadata">

**Author:** ![vfdev-5](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/vfdev-5/32/3535_2.png) [@vfdev-5](https://discuss.pytorch.org/u/vfdev-5)\
**Post date:** [December 17, 2021, 8:19pm UTC](https://discuss.pytorch.org/t/implementation-of-the-multiclass-case-for-precision-metric/139655/2 "2021-12-17T20:19:46Z")

</div>

Thanks for pointing out potential issues with our documentation and doctests!  
In your example, the definition of `default_evaluator` should be different. For our doctests it is defined here:  
[https://github.com/pytorch/ignite/blob/5c5837ac2528e9e9f1451dfbceacfc0deb86fe56/docs/source/conf.py#L349-L352](https://github.com/pytorch/ignite/blob/5c5837ac2528e9e9f1451dfbceacfc0deb86fe56/docs/source/conf.py#L349-L352)

```python
def eval_step(engine, batch):
    return batch

default_evaluator = Engine(eval_step)

```

Complete example is the following:

```python
import torch
from ignite.metrics import Precision
from ignite.engine import Engine

def eval_step(engine, batch):
    return batch

default_evaluator = Engine(eval_step)

metric = Precision(average=True)
metric.attach(default_evaluator, "precision")
y_true = torch.Tensor([2, 0, 2, 1, 0, 1]).long()
y_pred = torch.Tensor([
[0.0266, 0.1719, 0.3055],
[0.6886, 0.3978, 0.8176],
[0.9230, 0.0197, 0.8395],
[0.1785, 0.2670, 0.6084],
[0.8448, 0.7177, 0.7288],
[0.7748, 0.9542, 0.8573],
])
state = default_evaluator.run([[y_pred, y_true]])
print(state.metrics["precision"])
> 0.6111111

```

Hope this helps

---

<div class="post-metadata">

**Author:** ![sdesrozis](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sdesrozis/32/24628_2.png) [@sdesrozis](https://discuss.pytorch.org/u/sdesrozis)\
**Post date:** [December 17, 2021, 9:02pm UTC](https://discuss.pytorch.org/t/implementation-of-the-multiclass-case-for-precision-metric/139655/3 "2021-12-17T21:02:03Z")

</div>

Hi, thanks for the question.

The error comes from the `process_function` function you used in the `Engine`. In this very simple example, the output of this function feeds directly into the metric as a demonstration. Note that `data[0]` is `y_pred`. It means that `data[0][0]` is `[0.0266, 0.1719, 0.3055]` and `data[0][0]` is `[0.6886, 0.3978, 0.8176]`. This can’t be correctly used in the metric.

---

<div class="post-metadata">

**Author:** ![jamba\_juice](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/jamba_juice/32/45030_2.png) [@jamba\_juice](https://discuss.pytorch.org/u/jamba_juice)\
**Post date:** [January 10, 2022, 7:07am UTC](https://discuss.pytorch.org/t/implementation-of-the-multiclass-case-for-precision-metric/139655/4 "2022-01-10T07:07:12Z")

</div>

Thank you so much for the reply!

---

<div class="post-metadata">

**Author:** ![jamba\_juice](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/jamba_juice/32/45030_2.png) [@jamba\_juice](https://discuss.pytorch.org/u/jamba_juice)\
**Post date:** [January 10, 2022, 7:08am UTC](https://discuss.pytorch.org/t/implementation-of-the-multiclass-case-for-precision-metric/139655/5 "2022-01-10T07:08:05Z")

</div>

Thank you! I understand why it was giving an error.