# How to Calculate Accuracy against MSELoss function

**URL:** <https://discuss.pytorch.org/t/how-to-calculate-accuracy-against-mseloss-function/67644>\
**Category:** Uncategorized\
**Created:** [January 25, 2020, 7:51pm UTC](https://discuss.pytorch.org/t/how-to-calculate-accuracy-against-mseloss-function/67644 "2020-01-25T19:51:43Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Shariq\_Ali](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/shariq_ali/32/9995_2.png) [@Shariq\_Ali](https://discuss.pytorch.org/u/Shariq_Ali)\
**Post date:** [January 25, 2020, 7:51pm UTC](https://discuss.pytorch.org/t/how-to-calculate-accuracy-against-mseloss-function/67644/1 "2020-01-25T19:51:43Z")

</div>

Hello. I am new on machine learning and pytorch. ? I am doing segmentation and using the MSEloss function for calculating loss but i want to find the accuracy as well. I have tried different example but didn’t find it. Please help me following is my code and the shapes.

for data, target in train\_loader:

```
    data = data.to(device) 
    target = target.to(device=device, dtype=torch.int64)

    input_var = Variable(data.float())
    target_var = Variable(target.float())

    optimizer.zero_grad()
    output = model(input_var)
    loss = criterion(output, target_var)
    dice = dice_coef(output,target)

    loss.backward()
    optimizer.step()

    train_loss += loss.item()*data.size(0)
    train_metric = dice*data.size(0)

```

Shapes:  
target\_var torch.Size([2, 3, 512, 512])  
oututput torch.Size([2, 3, 512, 512])

---

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [January 25, 2020, 10:13pm UTC](https://discuss.pytorch.org/t/how-to-calculate-accuracy-against-mseloss-function/67644/2 "2020-01-25T22:13:26Z")

</div>

Would [this approach](https://discuss.pytorch.org/t/calculate-train-accuracy-of-the-model-in-segmentation-task/33581/13) from your other post help?