app ready

.gitignore

@@ -0,0 +1 @@
+__pycache__

app.py

@@ -0,0 +1,28 @@
+import torch
+import gradio as gr
+from model import EmotiClassifier
+
+predictor = EmotiClassifier()
+
+labels = ['angry', 'disgust', 'fear', 'happy', 'neutral', 'sad', 'surprise']
+
+predictor.load_state_dict(torch.load('emoticlassifier-64acc-1_250loss.pth'))
+
+def classify(image):
+    
+    torch_image = torch.Tensor(image)
+    torch_image = torch_image.view(1, 1, torch_image.shape[0], torch_image.shape[1])
+    
+    
+    pred = predictor(torch_image)
+    
+    label = torch.argmax(pred)
+    
+    pred_class = label.item()
+
+    return labels[pred_class]
+
+webcam = gr.Image(source='webcam',  streaming=True, shape=(48, 48), image_mode='L')
+
+interface = gr.Interface(fn=classify, inputs=webcam, outputs='text', live=True)
+interface.launch();

emoticlassifier-64acc-1_250loss.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4074b9fff06fd41c2bfd66a7db94fd9e88238b4e1c8b26b92f56069b87f5fa1f
+size 1743353

model.py

@@ -0,0 +1,72 @@
+import torch
+import torch.nn as nn
+
+class EmotiClassifier(nn.Module):
+    def __init__(self):
+        super().__init__()
+        
+       
+        self.l1 = nn.Sequential(
+            
+            nn.Conv2d(1, 32, 3),
+            nn.ReLU(),
+            nn.BatchNorm2d(32),
+            nn.MaxPool2d(2),
+            nn.Dropout(0.2),
+            
+            nn.Conv2d(32,64, 3),
+            nn.ReLU(),
+            nn.BatchNorm2d(64),
+            nn.MaxPool2d(2),
+            nn.Dropout(0.2),
+            
+            
+            
+            nn.Conv2d(64,128, 3),
+            nn.ReLU(),
+            nn.BatchNorm2d(128),
+            nn.MaxPool2d(2),
+            nn.Dropout(0.2),
+            
+            nn.Conv2d(128,256, 3),
+            nn.ReLU(),
+            nn.BatchNorm2d(256),
+            nn.MaxPool2d(2),
+            nn.Dropout(0.2),
+        )
+        
+       
+        self.fc = nn.Sequential(
+            nn.Linear(256, 128),
+            nn.ReLU(),
+            nn.Linear(128, 64),
+            nn.ReLU(),
+            nn.Linear(64, 32),
+            nn.ReLU(),
+            nn.Linear(32, 7),
+        )
+        
+        
+        self.loss = nn.CrossEntropyLoss();
+
+        
+    
+    def forward(self, x):
+        out = self.l1(x);
+        out = out.view(-1, 256);
+        out = self.fc(out);
+        
+        return out
+    
+    def predict(self, x):
+        self.eval();
+        with torch.no_grad():
+            out = self.forward(x);
+        
+        return out;
+
+    
+        
+
+        
+

requirements.txt

@@ -0,0 +1 @@
+torch