File size: 1,987 Bytes
e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a e236cbb 4564d0a |
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 |
import torch
import torch.nn as nn
import torch.nn.functional as F
from safetensors.torch import load_file
from PIL import Image
from torchvision import transforms
import string
torch.set_num_threads(20)
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Conv2d(1,64,kernel_size=3,padding=1)
self.conv2 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
self.conv3 = nn.Conv2d(128, 256, kernel_size=3, padding=1)
self.conv4 = nn.Conv2d(256, 512, kernel_size=3, padding=1)
self.conv5 = nn.Conv2d(512, 1024, kernel_size=3, padding=1)
self.fc1 = nn.Linear(1024*8*8, 512)
self.fc2 = nn.Linear(512, 256)
self.fc3 = nn.Linear(256, 128)
self.fc4 = nn.Linear(128, 26)
def forward(self, x):
x = F.relu(self.conv1(x))
x = F.max_pool2d(x,2)
x = F.relu(self.conv2(x))
x = F.max_pool2d(x, 2)
x = F.relu(self.conv3(x))
x = F.max_pool2d(x, 2)
x = F.relu(self.conv4(x))
x = F.relu(self.conv5(x))
x = x.view(x.size(0), -1)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.relu(self.fc3(x))
x = self.fc4(x)
return x
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = CNN().to(device)
weights_dict = load_file("cnn_letters.safetensors")
model.load_state_dict(weights_dict)
model.eval()
#using
from PIL import Image
from torchvision import transforms
#get you image
img = Image.open("my_letter.png").convert("L")
transform = transforms.Compose([
transforms.Resize((64,64)),
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
x = transform(img).unsqueeze(0).to(device)
with torch.no_grad():
output = model(x)
pred_idx = output.argmax(dim=1).item()
letters = list(string.ascii_uppercase)
pred_letter = letters[pred_idx]
print(f"Predicted class: {pred_idx + 1}, Letter: {pred_letter}") |