# A littile question about pytorch training parameters

**URL:** <https://discuss.pytorch.org/t/a-littile-question-about-pytorch-training-parameters/75312>\
**Category:** Uncategorized\
**Created:** [April 4, 2020, 7:43am UTC](https://discuss.pytorch.org/t/a-littile-question-about-pytorch-training-parameters/75312 "2020-04-04T07:43:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jiengup](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/jiengup/32/22324_2.png) [@jiengup](https://discuss.pytorch.org/u/jiengup)\
**Post date:** [April 4, 2020, 7:43am UTC](https://discuss.pytorch.org/t/a-littile-question-about-pytorch-training-parameters/75312/1 "2020-04-04T07:43:20Z")

</div>

I’m learning pytorch and DL, I’m training a classifier on a image dataset. I have splited train dataset and validation dataset and I compelete traning on training set like this:

```auto
model = Classifier().cuda()
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
num_epoch = 30
for epoch in range(num_epoch):
    ...

```

After that, I want to merge training set and validation set to get a bigger dataset and train more 30 epochs.  
Could I code like this?:

```auto
train_val_x = np.concatenate((train_x, val_x), axis=0)
train_val_y = np.concatenate((train_y, val_y), axis=0)
train_val_set = ImgDataset(train_val_x, train_val_y, train_transform)
train_val_loader = DataLoader(train_val_set, batch_size=batch_size, shuffle=True)
model_best = Classifier().cuda()
loss = nn.CrossEntropyLoss() # 因為是 classification task，所以 loss 使用 CrossEntropyLoss
optimizer = torch.optim.Adam(model_best.parameters(), lr=0.001) # optimizer 使用 Adam
num_epoch = 30
for epoch in range(num_epoch):
    ...

```

Or should I use the formmer var **model** instead of **model\_best**  
Actually my question is that in pytorch, **model.Module.parameter()** method can remain my pre-train parameters as static?  
Thanks a lot. ^.^