NewAr

cnn_letters.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb7a8a2aa2b31911683753a2c1ec8ec9e2654b5d022d91bd6f096a2bead31ed
-size 428216
+oid sha256:fff965569b21ebb62dc528fd298d06ce10ad823870d14166a462126ea4337d96
+size 159969280

dowload.py

@@ -2,46 +2,64 @@ 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, 16, kernel_size=3, padding=1)
-        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, padding=1)
-        self.fc1 = nn.Linear(32*7*7, 64)
-        self.fc2 = nn.Linear(64, 26)
+        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.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 = self.fc2(x)
+        x = F.relu(self.fc2(x))
+        x = F.relu(self.fc3(x))
+        x = self.fc4(x)
         return x
-
-model = CNN()
+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
+from PIL import Image
+from torchvision import transforms
 #get you image 
-#img = Image.open("my_letter.png").convert("L")
+img = Image.open("my_letter.png").convert("L")
 
-#transform = transforms.Compose([
-#    transforms.Resize((28,28)),
-#    transforms.ToTensor(),
-#    transforms.Normalize((0.5,), (0.5,))
-#])
+transform = transforms.Compose([
+    transforms.Resize((64,64)),
+    transforms.ToTensor(),
+    transforms.Normalize((0.5,), (0.5,))
+])
 
-#x = transform(img).unsqueeze(0)
+x = transform(img).unsqueeze(0).to(device)
 
-#with torch.no_grad():
-#    output = model(x)
-#    pred = output.argmax(dim=1)
-#print(f"Predicted class: {pred.item() + 1}")
+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}")