File size: 1,205 Bytes
56473a6 2c852c2 56473a6 dc07155 56473a6 dc07155 56473a6 dc07155 56473a6 dc07155 56473a6 dc07155 56473a6 39fa7a9 56473a6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 |
import requests
import gradio as gr
import torch
from timm import create_model
from timm.data import resolve_data_config
from timm.data.transforms_factory import create_transform
# url for accesing the image DB
IMAGENET_1k_URL = "https://storage.googleapis.com/bit_models/ilsvrc2012_wordnet_lemmas.txt"
# fetching labels from the URL
LABELS = requests.get(IMAGENET_1k_URL).text.strip().split('\n')
#using a pretrained resnet50 model
model = create_model('resnet50',pretrained=True)
transform = create_transform(**resolve_data_config({},model=model))
# we do not need to train model , hence using model.eval() to use it only for inference
model.eval()
# declaring the main fn. for returning the prediction from our model
# we use softmax, to take probabilities of the outputs.
def predict(img):
img = img.convert('RGB')
img = transform(img).unsqueeze(0)
with torch.no_grad():
out= model(img)
probability = torch.nn.functional.softmax(out[0],dim=0)
values, indices = torch.topk(probability,k=5)
return {LABELS[i]: v.item() for i,v in zip(indices,values)}
iface = gr.Interface(fn=predict, inputs=gr.inputs.Image(type='pil'), outputs="label").launch()
iface.launch()
|