Spaces:
Sleeping
Sleeping
File size: 1,584 Bytes
831f00d |
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 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
import torch
import torch.nn as nn
import torchvision.transforms as transforms
from PIL import Image
import gradio as gr
class ModifiedLargeNet(nn.Module):
def __init__(self):
super(ModifiedLargeNet, self).__init__()
self.name = "modified_large"
self.fc1 = nn.Linear(128 * 128 * 3, 256)
self.fc2 = nn.Linear(256, 128)
self.fc3 = nn.Linear(128, 3) # 3 classes: Rope, Hammer, Other
def forward(self, x):
x = x.view(-1, 128 * 128 * 3)
x = torch.relu(self.fc1(x))
x = torch.relu(self.fc2(x))
x = self.fc3(x)
return x
model = ModifiedLargeNet()
model.load_state_dict(torch.load("modified_large_net.pt", map_location=torch.device("cpu")))
model.eval()
transform = transforms.Compose([
transforms.Resize((128, 128)),
transforms.ToTensor(),
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
])
def predict(image):
image = transform(image).unsqueeze(0)
with torch.no_grad():
outputs = model(image)
probabilities = torch.softmax(outputs, dim=1).numpy()[0]
classes = ["Rope", "Hammer", "Other"]
return {cls: float(prob) for cls, prob in zip(classes, probabilities)}
interface = gr.Interface(
fn=predict,
inputs=gr.Image(type="pil"),
outputs=gr.Label(num_top_classes=3),
title="Mechanical Tools Classifier",
description="Upload an image of a tool to classify it as 'Rope', 'Hammer', or 'Other'.",
)
if __name__ == "__main__":
interface.launch()
|