# AlexNet Input Size: 224 or 227?

**URL:** <https://discuss.pytorch.org/t/alexnet-input-size-224-or-227/41272>\
**Category:** vision\
**Created:** [March 30, 2019, 4:42pm UTC](https://discuss.pytorch.org/t/alexnet-input-size-224-or-227/41272 "2019-03-30T16:42:31Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![zhanwenchen](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/zhanwenchen/32/10362_2.png) [@zhanwenchen](https://discuss.pytorch.org/u/zhanwenchen)\
**Post date:** [March 30, 2019, 4:42pm UTC](https://discuss.pytorch.org/t/alexnet-input-size-224-or-227/41272/1 "2019-03-30T16:42:31Z")

</div>

When I looked at the [source code for vision/AlexNet](https://github.com/pytorch/vision/blob/master/torchvision/models/alexnet.py), I’m not sure whether the implementation assumes a 227 or 224 input size, because if you did use 227, the output of the first conv layer should be (227-11+2x2)/4 + 1 = 56 even. This would not have made much sense for the first pooling layer, which would produce an output size of (56 - 3) / 2 + 1 = 27.5.

One possible understanding is that the pool1 output is then floored, but this account differs from [this Medium article](https://medium.com/@smallfishbigsea/a-walk-through-of-alexnet-6cbd137a5637), which suggests that in fact, conv1’s input may in fact be 224, and that the conv1 output is thus floored: (224 - 11 + 2x2) / 4 + 1 = 55.25, so that the pool1 output produces an integer without flooring: (55 - 3) / 2 + 1 = 27. Can someone please comment assertively whether the input should actually be 224 or 227? I believe this may be important for users who need this information to resize their images correctly.

---

<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:** [March 30, 2019, 8:34pm UTC](https://discuss.pytorch.org/t/alexnet-input-size-224-or-227/41272/2 "2019-03-30T20:34:44Z")

</div>

As described in [the docs](https://pytorch.org/docs/stable/torchvision/models.html), the input size should be at least `224x224` and as far as I know this size was used for training as shown [here](https://github.com/pytorch/examples/blob/b142c4bde84b7d6e2d61fd063f902621d014291d/imagenet/main.py#L204).

> All pre-trained models expect input images normalized in the same way, i.e. mini-batches of 3-channel RGB images of shape (3 x H x W), where H and W are expected to be at least 224.

---

<div class="post-metadata">

**Author:** ![mattgoh](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/mattgoh/32/49508_2.png) [@mattgoh](https://discuss.pytorch.org/u/mattgoh)\
**Post date:** [May 11, 2022, 5:45pm UTC](https://discuss.pytorch.org/t/alexnet-input-size-224-or-227/41272/3 "2022-05-11T17:45:11Z")

</div>

There are several sources that point out the same discrepancy. The video transcript [here](https://www.coursera.org/lecture/convolutional-neural-networks/classic-networks-MmYe2) (I believe from Andrew Ng) states:

> So, AlexNet input starts with 227 by 227 by 3 images. And if you read the paper, the paper refers to 224 by 224 by 3 images. But if you look at the numbers, I think that the numbers make sense only of actually 227 by 227.

In the Caffe file `deploy.prototxt`, the input dim is indicated to be 227x227:

```auto
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }
}

```

There are other sources (from searching the web) that reference this discrepancy, and work through the calculations to support the claim.

As a side note, the AlexNet paper states that random cropping was used, whereas the PyTorch docs [here](https://pytorch.org/hub/pytorch_vision_alexnet/) use `CenterCrop` as an example