# Pretrained VGG-Face model **URL:** \ **Category:** vision\ **Created:** [November 1, 2017, 4:02pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383 "2017-11-01T16:02:02Z")\ **Posts on this page:** 12\ **Page:** 1
**Author:** ![pvskand](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/p/3be4f8/32.png) [@pvskand](https://discuss.pytorch.org/u/pvskand)\ **Post date:** [November 1, 2017, 4:02pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/1 "2017-11-01T16:02:02Z")
I have searched for vgg-face pretrained model in pytorch, but couldn’t find it. Is there a github repo for the pretrained model of vgg-face in pytorch? ---
**Author:** ![shashankvkt](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/shashankvkt/32/6958_2.png) [@shashankvkt](https://discuss.pytorch.org/u/shashankvkt)\ **Post date:** [July 27, 2018, 3:32pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/2 "2018-07-27T15:32:00Z")
Hi! I hope it’s not too late. I had found this link pertaining to details regarding vgg-face model along with its weights in the link below. Scroll down to the vgg-face section and download your requirements. [http://www.robots.ox.ac.uk/~albanie/pytorch-models.html](http://www.robots.ox.ac.uk/~albanie/pytorch-models.html) Hope this helps. ---
**Author:** ![pvskand](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/p/3be4f8/32.png) [@pvskand](https://discuss.pytorch.org/u/pvskand)\ **Post date:** [July 27, 2018, 3:47pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/3 "2018-07-27T15:47:58Z")
Thank you @shashankvkt. ---
**Author:** ![cydonia999](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/cydonia999/32/4138_2.png) [@cydonia999](https://discuss.pytorch.org/u/cydonia999)\ **Post date:** [August 16, 2018, 5:34am UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/4 "2018-08-16T05:34:11Z")
I hope this also helps. > **[cydonia999/VGGFace2-pytorch](https://github.com/cydonia999/VGGFace2-pytorch)** > > VGGFace2-pytorch - PyTorch Face Recognizer based on 'VGGFace2: A dataset for recognising faces across pose and age' ---
**Author:** ![shinx](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/shinx/32/14808_2.png) [@shinx](https://discuss.pytorch.org/u/shinx)\ **Post date:** [October 25, 2019, 7:07am UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/5 "2019-10-25T07:07:55Z")
> Hi! I hope it’s not too late. > I had found this link pertaining to details regarding vgg-face model along with its weights in the link below. Scroll down to the vgg-face section and download your requirements. > > [http://www.robots.ox.ac.uk/~albanie/pytorch-models.html](http://www.robots.ox.ac.uk/~albanie/pytorch-models.html) > > Hope this helps. Hi, is this loadable in the VGG16 torchvision model ? ---
**Author:** ![shashankvkt](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/shashankvkt/32/6958_2.png) [@shashankvkt](https://discuss.pytorch.org/u/shashankvkt)\ **Post date:** [October 26, 2019, 4:03pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/6 "2019-10-26T16:03:26Z")
I dont think its available as torchvision model. You still have to load the pretrained weights manually. ---
**Author:** ![shinx](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/shinx/32/14808_2.png) [@shinx](https://discuss.pytorch.org/u/shinx)\ **Post date:** [October 30, 2019, 1:02pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/7 "2019-10-30T13:02:55Z")
I managed to load them manually thanks for your response. ---
**Author:** ![shinx](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/shinx/32/14808_2.png) [@shinx](https://discuss.pytorch.org/u/shinx)\ **Post date:** [November 7, 2019, 4:33pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/8 "2019-11-07T16:33:33Z")
```auto def compose_transforms(meta, resize=256, center_crop=True, override_meta_imsize=False): """ Compose preprocessing transforms for model The imported models use a range of different preprocessing options, depending on how they were originally trained. Models trained in MatConvNet typically require input images that have been scaled to [0,255], rather than the [0,1] range favoured by PyTorch. Args: meta (dict): model preprocessing requirements resize (int) [256]: resize the input image to this size center_crop (bool) [True]: whether to center crop the image override_meta_imsize (bool) [False]: if true, use the value of `resize` to select the image input size, rather than the properties contained in meta (this option only applies when center cropping is not used. Return: (transforms.Compose): Composition of preprocessing transforms """ normalize = transforms.Normalize(mean=meta['mean'], std=meta['std']) im_size = meta['imageSize'] assert im_size[0] == im_size[1], 'expected square image size' if center_crop: transform_list = [transforms.Resize(resize), transforms.CenterCrop(size=(im_size[0], im_size[1]))] else: if override_meta_imsize: im_size = (resize, resize) transform_list = [transforms.Resize(size=(im_size[0], im_size[1]))] transform_list += [transforms.ToTensor()] if meta['std'] == [1, 1, 1]: # common amongst mcn models transform_list += [lambda x: x * 255.0] transform_list.append(normalize) return transforms.Compose(transform_list) ``` The model is using the above preprocessing function. What are the transforms actually applied [here](https://github.com/albanie/pytorch-benchmarks/blob/081e82eb43439ce2821622a6e3d627877caed67a/utils/benchmark_helpers.py#L11) ? Also why is the following transform used ? ```auto if meta['std'] == [1, 1, 1]: # common amongst mcn models transform_list += [lambda x: x * 255.0] ``` ---
**Author:** ![apollack](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/87869e/32.png) [@apollack](https://discuss.pytorch.org/u/apollack)\ **Post date:** [March 13, 2020, 2:27pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/9 "2020-03-13T14:27:15Z")
Hello, I’ve been trying to use the ResNet50 model from the author site, and downloaded the model/weights. My main use of this is to pass in a batch of images and extract a feature map. I was able to do this successfully with the original pytorch implementation, however, when I do the same setup, I’m thrown an error because of the batch and because of the dimensions. I tried tracing back to see if I could adjust, but I’m unable to find anywhere to work on this. Any ideas? I’m initially using images of shape [B,C,H,W]=[8,3,256,256]. I know ResNet is supposed to be 224x224 but 256 was working, and needed for the size feature map I’m requiring. It seems like part of the issue might be handling batches itself? Here is the error: ```auto Traceback (most recent call last): File "C:/Users/a-pollack/Projects/de_ident/de_ident.py", line 27, in gen_losses, dis_losses, gen, dis = train_net(num_epochs=5, batch_size=8, lr=1e-4, betas=(0.5, 0.99)) File "C:\Users\a-pollack\Projects\de_ident\train.py", line 122, in train_net z_raw, m, z_masked = gen(data[0]) File "C:\Users\a-pollack\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "C:\Users\a-pollack\Projects\de_ident\generator.py", line 75, in forward face_descriptor = fd_conv2(x) File "C:\Users\a-pollack\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "C:\Users\a-pollack\Projects\de_ident\generator_utils.py", line 54, in forward x = self.features(x) File "C:\Users\a-pollack\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "C:\Users\a-pollack\Anaconda3\lib\site-packages\torch\nn\modules\container.py", line 92, in forward input = module(input) File "C:\Users\a-pollack\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "C:\Users\a-pollack\Anaconda3\lib\site-packages\torch\nn\modules\conv.py", line 345, in forward return self.conv2d_forward(input, self.weight) File "C:\Users\a-pollack\Anaconda3\lib\site-packages\torch\nn\modules\conv.py", line 342, in conv2d_forward self.padding, self.dilation, self.groups) RuntimeError: Given groups=1, weight of size 256 64 1 1, expected input[8, 256, 64, 64] to have 64 channels, but got 256 channels instead ``` ---
**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 14, 2020, 3:39am UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/10 "2020-03-14T03:39:20Z")
The error points to a wrong number of input channels to this particular convolution. This might be caused by a wrong reshape or by mixing up layers. ---
**Author:** ![maro95](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/maro95/32/12026_2.png) [@maro95](https://discuss.pytorch.org/u/maro95)\ **Post date:** [March 25, 2020, 12:11pm UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/11 "2020-03-25T12:11:32Z")
Do we provide images in RGB or BGR format for VGGFace2 resnet50 model? It doesn’t say anything except that model is trained using the Caffe framework and Caffe uses a BGR color channel scheme for reading image files. It also says that mean image vector is _[131.0912, 103.8827, 91.4953]_ but if see values we can conclude that this mean image vector is in RGB format (there is more red than blue in face images). Does anybody know fo sure what is the truth? ---
**Author:** ![shashankvkt](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/shashankvkt/32/6958_2.png) [@shashankvkt](https://discuss.pytorch.org/u/shashankvkt)\ **Post date:** [April 1, 2020, 12:15am UTC](https://discuss.pytorch.org/t/pretrained-vgg-face-model/9383/12 "2020-04-01T00:15:30Z")
You are right. I use PIL to read images which is generally in RGB format. In case you use opencv to read images, please consider converting BGR to RGB.