Set threshold resnet18 pytorch

from PIL import Image
import torch
from torchvision import transforms
input_image = Image.open("img/danbooru_resnet1.png") # load an image of your choice
preprocess = transforms.Compose([
    transforms.Resize(360),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.7137, 0.6628, 0.6519], std=[0.2970, 0.3017, 0.2979]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model

if torch.cuda.is_available():
    input_batch = input_batch.to('cuda')
    model.to('cuda')

with torch.no_grad():
    output = model(input_batch)

# The output has unnormalized scores. To get probabilities, you can run a sigmoid on it.
probs = torch.sigmoid(output[0]) # Tensor of shape 6000, with confidence scores over Danbooru's top 6000 tags

# Second part of the code 
# to set a threshold value and to use it 
tmp = probs[probs > thresh]
inds = probs.argsort(descending=True)

Source: github.com

Similar codes

0 vote278 views1 answer
Frogenset ito list pandas
Python
2 votes242 views6 answers
How to merge more than 2 dataframes in python
Python
2 votes249 views3 answers
Condition python
Python
0 vote256 views1 answer
How can I convert dataframe to list with in python without changing its datatype?
Python
83 votes225 views6 answers
Py virtual environment
Python
20 votes241 views1 answer
ParserError: Error tokenizing data. C error: Expected 1 fields in line 87, saw 2
Python
1 vote244 views1 answer
Add one to all elements in list python
Python
0 vote232 views2 answers
Print 2 letter python
Python
0 vote250 views1 answer
Python nearly equal
Python
0 vote290 views1 answer
The webpage at http://127.0.0.1:8000/ might be temporarily down or it may have moved permanently to a new web address. django
Python Django