[FIXED] PyTorch resnet bad tensor dimensions

Issue

I'm trying to setup a face detection/recognition pipeline using Pytorch.

I load the image using opencv

image = cv2.imread('...')

I load the mtcnn face detection and resnet face recognition models

self.mtcnn = MTCNN(keep_all=True, device=self.device)
self.resnet = InceptionResnetV1(pretrained='vggface2').eval()

Then I run detection and recognition

cropped = detector.mtcnn(image)
detector.resnet(cropped.unsqueeze(0))

And get this error

Expected 4-dimensional input for 4-dimensional weight [32, 3, 3, 3], but got 5-dimensional input of size [1, 1, 3, 160, 160] instead

I also tried resizing the image to 512x512 and passing image_size=512 to the MTCNN constructor but I get a similar error.

Solution

I tried removing the unsqueeze and it worked
The guide I was following was using something other than opencv to load the image which probably returned the image as an array/tensor of images

Answered By - areller