File size: 2,633 Bytes
aa08f61 bd5f112 aa08f61 bd5f112 f0efe75 aa08f61 4fc29e5 aa08f61 bd5f112 |
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 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
import numpy as np
import torch
from pathlib import Path
import torch.nn as nn
import torch.nn.functional as F
from PIL import Image
from torchvision import transforms
import gradio as gr
transform = transforms.Compose([
transforms.Resize((28, 28)),
transforms.Grayscale(),
transforms.ToTensor()
])
labels = ["๐ (ศูนย์)", "๑ (หนึ่ง)", "๒ (สอง)", "๓ (สาม)", "๔ (สี่)", "๕ (ห้า)", "๖ (หก)", "๗ (เจ็ด)", "๘ (แปด)", "๙ (เก้า)"]
LABELS = {i:k for i, k in enumerate(labels)} # dictionary of index and label
# Load model using DropoutThaiDigit instead
class DropoutThaiDigit(nn.Module):
def __init__(self):
super(DropoutThaiDigit, self).__init__()
self.fc1 = nn.Linear(28 * 28, 392)
self.fc2 = nn.Linear(392, 196)
self.fc3 = nn.Linear(196, 98)
self.fc4 = nn.Linear(98, 10)
self.dropout = nn.Dropout(0.1)
def forward(self, x):
x = x.view(-1, 28 * 28)
x = self.fc1(x)
x = F.relu(x)
x = self.dropout(x)
x = self.fc2(x)
x = F.relu(x)
x = self.dropout(x)
x = self.fc3(x)
x = F.relu(x)
x = self.dropout(x)
x = self.fc4(x)
return x
model = DropoutThaiDigit()
model.load_state_dict(torch.load("thai_digit_net.pth"))
model.eval()
def predict(img):
"""
Predict function takes image and return top 5 predictions
as a dictionary:
{label: confidence, label: confidence, ...}
"""
if img is None:
return None
img = transform(img) # do not need to use 1 - transform(img) because gradio already do it
probs = model(img).softmax(dim=1).ravel()
probs, indices = torch.topk(probs, 5) # select top 5
probs, indices = probs.tolist(), indices.tolist() # transform to list
confidences = {LABELS[i]: v for i, v in zip(indices, probs)}
return confidences
demo = gr.Interface(
fn=predict,
inputs=gr.Sketchpad(label="Draw Here", brush_radius=5, shape=(120, 120)),
outputs=gr.Label(label="Guess"),
title="Thai Digit Handwritten Classification",
description="ทดลองวาดภาพตัวอักษรเลขไทยลงใน Sketchpad ด้านล่างเพื่อทำนายผลตัวเลข ตั้งแต่ ๐ (ศูนย์) ๑ (หนึ่ง) ๒ (สอง) ๓ (สาม) ๔ (สี่) ๕ (ห้า) ๖ (หก) ๗ (เจ็ด) ๘ (แปด) จนถึง ๙ (เก้า)",
live=True
)
if __name__ == "__main__":
demo.launch()
|