An vit classifier for handling noise image like this

0b36d3c4-da8d-4fb1-bc14-a948af35f02e.jpg

It has limitation inbetween clear and noise

from datasets import load_dataset
from PIL import Image
from transformers import ViTImageProcessor, ViTForImageClassification, TrainingArguments, Trainer
import torch
import numpy as np
from datasets import load_metric
import os
import shutil

model_name_or_path = 'lrzjason/noise-classifier'
image_processor = ViTImageProcessor.from_pretrained(model_name_or_path)
model = ViTForImageClassification.from_pretrained(model_name_or_path)

input_dir = ''
file = 'b5b457f4-5b52-4d68-be1b-9a2f557465f6.jpg'
image = Image.open(os.path.join(input_dir, file))

inputs = image_processor(image, return_tensors="pt")
with torch.no_grad():
    logits = model(**inputs).logits

# model predicts one of the 1000 ImageNet classes
predicted_label = logits.argmax(-1).item()
Downloads last month
19
Safetensors
Model size
85.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.