# Pre-trained ResNet50 as featurizer and predictor

**URL:** <https://discuss.pytorch.org/t/pre-trained-resnet50-as-featurizer-and-predictor/42873>\
**Category:** vision\
**Created:** [April 17, 2019, 8:12pm UTC](https://discuss.pytorch.org/t/pre-trained-resnet50-as-featurizer-and-predictor/42873 "2019-04-17T20:12:03Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![pramod.srinivasan](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/pramod.srinivasan/32/21707_2.png) [@pramod.srinivasan](https://discuss.pytorch.org/u/pramod.srinivasan)\
**Post date:** [April 17, 2019, 8:12pm UTC](https://discuss.pytorch.org/t/pre-trained-resnet50-as-featurizer-and-predictor/42873/1 "2019-04-17T20:12:03Z")

</div>

I wanted to access the intermediate outputs of ResNet50, so I created my own class:

```auto
class ResNetFeat(nn.Module):
  def __init__ (self):
    super(ResNetFeat, self). __init__ ()
    resnet50_pretrained = models.resnet50(pretrained=True)
    conv_modules = list(resnet50_pretrained.children())[:-2] #all layers expect Adaptive AvgPool2D and FC
    pool_fc_modules = list(resnet50_pretrained.children())[-2:] #layers Adaptive AvgPool2D and FC
    self.model_conv = nn.Sequential(*conv_modules)
    self.pool_fc = nn.Sequential(*pool_fc_modules)
  
  def forward(self, image):
    feat = self.model_conv(image)
    print(feat.shape)
    pred = self.pool_fc(feat)
    return feat, pred

```

When I test this code:

```auto
x_image = torch.randn(1, 3, 224, 224)

featurizer = ResNetFeat()
feat, pred = featurizer(x_image)
print(feat.shape, pred.shape)

```

I get the following error –  
`RuntimeError: size mismatch, m1: [2048 x 1], m2: [2048 x 1000] at /pytorch/aten/src/TH/generic/THTensorMath.cpp:940`

---

<div class="post-metadata">

**Author:** ![sbelharbi](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/f475e1/32.png) [@sbelharbi](https://discuss.pytorch.org/u/sbelharbi)\
**Post date:** [April 17, 2019, 8:34pm UTC](https://discuss.pytorch.org/t/pre-trained-resnet50-as-featurizer-and-predictor/42873/2 "2019-04-17T20:34:33Z")

</div>

your `self.pool_fc(feat)` contains two global operations: pooling, and an fc layer.

```python
Sequential(
  (0): AvgPool2d(kernel_size=7, stride=1, padding=0)
  (1): Linear(in_features=2048, out_features=1000, bias=True)
)

```

The latter needs the pooled features to be flattened first.  
Here something to work with:

```python
import torch
import torchvision.models as models
import torch.nn as nn

class ResNetFeat(nn.Module):
    def __init__ (self):
        super(ResNetFeat, self). __init__ ()
        resnet50_pretrained = models.resnet50(pretrained=True)
        conv_modules = list(resnet50_pretrained.children())[:-2] # all layers expect Adaptive AvgPool2D and FC
        pool_modules = [list(resnet50_pretrained.children())[-2]] # layers Adaptive AvgPool2D: there is only one.
        fc_modules = [list(resnet50_pretrained.children())[-1]] # fc modules (1 only)
        self.model_conv = nn.Sequential(*conv_modules)
        self.pool = nn.Sequential(*pool_modules)
        self.fc = nn.Sequential(*fc_modules)

    def forward(self, image):
        feat2d = self.model_conv(image)
        print(feat2d.shape)
        featedpooled = self.pool(feat2d)
        # flatten the feature before feeding the fc.
        featdense = featedpooled.view(featedpooled.size(0), -1)
        pred = self.fc(featdense)
        return featdense, pred

if __name__ == " __main__":
    x_image = torch.randn(1, 3, 224, 224)
    featurizer = ResNetFeat()
    feat, pred = featurizer(x_image)
    print(feat.shape, pred.shape)

```

Output:

```python
torch.Size([1, 2048, 7, 7])
torch.Size([1, 2048]) torch.Size([1, 1000])

```