CODEWITHSUNDEEP
pytorchresnettransfer-learning
Hasipasi
Hasipasi

Reputation: 3

Reading test images for resnet18

I am trying to read an image file and classify and image. My model is resnet18 I trained it previously and planning to use a different .py script to classify a list of images. This is my network:

PATH = './net.pth'
model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 16)
model_ft.load_state_dict(torch.load(PATH))
model_ft.eval()

And I am trying to read Images this way:

imsize = 256
loader = transforms.Compose([transforms.Scale(imsize), transforms.ToTensor()])
def image_loader(image_name):
    #load image, returns cuda tensor
    image = Image.open(image_name)
    image = loader(image).float()
    image = Variable(image, requires_grad=True)
    image = image.unsqueeze(0)
    return image.cuda()  

image = image_loader("dataset/test/9673.png")

model_ft(image)

I am getting this error:

 "Given groups=1, weight of size [64, 3, 7, 7], expected input[1, 4, 676, 256] to have 3 channels, but got 4 channels instead"

I've got recommended to remove the unsqueeze for resnet18, doing that I got the following error:

"Expected 4-dimensional input for 4-dimensional weight [64, 3, 7, 7], but got 3-dimensional input of size [4, 676, 256] instead"

I do not quite understand the problem I am dealing with, how should I read my test set? I'll need to write the class ID-s and the file names into a .txt afterwards.

Upvotes: 0

Views: 1007

Answers (2)

planet_pluto
planet_pluto

Reputation: 782

I think your image input is of the shape: batch_size*4*height*width instead of batch_size*3*height*width. That's why the error. Can you do this and report the shape:

print(image.shape) after the call to image_loader().

Upvotes: 1

Hossein
Hossein

Reputation: 26004

You are using a PNG image which has 4 channels. your network expects 3 channels. Convert to RGB and you should be fine. In your image_loader simply do:

image = Image.open(image_name).convert('RGB')

Upvotes: 1

Related Questions