import numpy as np
import gradio as gr
import torch

from transformers import pipeline

model = torch.hub.load('pytorch/vision:v0.6.0', 'resnet18', pretrained=True).eval()

# def sepia(input_img):
#     sepia_filter = np.array([
#         [0.393, 0.769, 0.189], 
#         [0.349, 0.686, 0.168], 
#         [0.272, 0.534, 0.131]
#     ])
#     sepia_img = input_img.dot(sepia_filter.T)
#     sepia_img /= sepia_img.max()
#     return sepia_img

# demo = gr.Interface(sepia, gr.Image(), "image")

# Download human-readable labels for ImageNet.
response = requests.get("https://git.io/JJkYN")
labels = response.text.split("\n")

def predict(inp):
  inp = transforms.ToTensor()(inp).unsqueeze(0)
  with torch.no_grad():
    prediction = torch.nn.functional.softmax(model(inp)[0], dim=0)
    confidences = {labels[i]: float(prediction[i]) for i in range(1000)}
  return confidences

gr.Interface(fn=predict,
             inputs=gr.Image(type="pil"),
             outputs=gr.Label(num_top_classes=3),
             examples=["lion.jpg", "cheetah.jpg"]).launch()

demo.launch()