Update app.py

app.py

@@ -1,228 +1,170 @@
-import torch
-import gradio as gr
-import torch.nn as nn
-import torch.nn.functional as F
-from torch.nn import init
-import torchvision.transforms as transforms
-
-'''MobileNetV3 in PyTorch.
-
-See the paper "Inverted Residuals and Linear Bottlenecks:
-Mobile Networks for Classification, Detection and Segmentation" for more details.
-'''
-
-
-
-class hswish(nn.Module):
-    def forward(self, x):
-        out = x * F.relu6(x + 3, inplace=True) / 6
-        return out
-
-
-class hsigmoid(nn.Module):
-    def forward(self, x):
-        out = F.relu6(x + 3, inplace=True) / 6
-        return out
-
-
-class SeModule(nn.Module):
-    def __init__(self, in_size, reduction=4):
-        super(SeModule, self).__init__()
-        self.se = nn.Sequential(
-            nn.AdaptiveAvgPool2d(1),
-            nn.Conv2d(in_size, in_size // reduction, kernel_size=1, stride=1, padding=0, bias=False),
-            nn.BatchNorm2d(in_size // reduction),
-            nn.ReLU(inplace=True),
-            nn.Conv2d(in_size // reduction, in_size, kernel_size=1, stride=1, padding=0, bias=False),
-            nn.BatchNorm2d(in_size),
-            hsigmoid()
-        )
-
-    def forward(self, x):
-        return x * self.se(x)
-
-
-class Block(nn.Module):
-    '''expand + depthwise + pointwise'''
-    def __init__(self, kernel_size, in_size, expand_size, out_size, nolinear, semodule, stride):
-        super(Block, self).__init__()
-        self.stride = stride
-        self.se = semodule
-
-        self.conv1 = nn.Conv2d(in_size, expand_size, kernel_size=1, stride=1, padding=0, bias=False)
-        self.bn1 = nn.BatchNorm2d(expand_size)
-        self.nolinear1 = nolinear
-        self.conv2 = nn.Conv2d(expand_size, expand_size, kernel_size=kernel_size, stride=stride, padding=kernel_size//2, groups=expand_size, bias=False)
-        self.bn2 = nn.BatchNorm2d(expand_size)
-        self.nolinear2 = nolinear
-        self.conv3 = nn.Conv2d(expand_size, out_size, kernel_size=1, stride=1, padding=0, bias=False)
-        self.bn3 = nn.BatchNorm2d(out_size)
-
-        self.shortcut = nn.Sequential()
-        if stride == 1 and in_size != out_size:
-            self.shortcut = nn.Sequential(
-                nn.Conv2d(in_size, out_size, kernel_size=1, stride=1, padding=0, bias=False),
-                nn.BatchNorm2d(out_size),
-            )
-
-    def forward(self, x):
-        out = self.nolinear1(self.bn1(self.conv1(x)))
-        out = self.nolinear2(self.bn2(self.conv2(out)))
-        out = self.bn3(self.conv3(out))
-        if self.se != None:
-            out = self.se(out)
-        out = out + self.shortcut(x) if self.stride==1 else out
-        return out
-
-class MobileNetV3_Small(nn.Module):
-    def __init__(self, num_classes= 30):
-        super(MobileNetV3_Small, self).__init__()
-        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=2, padding=1, bias=False)
-        self.bn1 = nn.BatchNorm2d(16)
-        self.hs1 = hswish()
-
-        self.bneck = nn.Sequential(
-            Block(3, 16, 16, 16, nn.ReLU(inplace=True), SeModule(16), 2),
-            Block(3, 16, 72, 24, nn.ReLU(inplace=True), None, 2),
-            Block(3, 24, 88, 24, nn.ReLU(inplace=True), None, 1),
-            Block(5, 24, 96, 40, hswish(), SeModule(40), 2),
-            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
-            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
-            Block(5, 40, 120, 48, hswish(), SeModule(48), 1),
-            Block(5, 48, 144, 48, hswish(), SeModule(48), 1),
-            Block(5, 48, 288, 96, hswish(), SeModule(96), 2),
-            Block(5, 96, 576, 96, hswish(), SeModule(96), 1),
-            Block(5, 96, 576, 96, hswish(), SeModule(96), 1),
-        )
-
-
-        self.conv2 = nn.Conv2d(96, 576, kernel_size=1, stride=1, padding=0, bias=False)
-        self.bn2 = nn.BatchNorm2d(576)
-        self.hs2 = hswish()
-        self.linear3 = nn.Linear(576, 1280)
-        self.bn3 = nn.BatchNorm1d(1280)
-        self.hs3 = hswish()
-        self.linear4 = nn.Linear(1280, num_classes)
-        self.init_params()
-
-    def init_params(self):
-        for m in self.modules():
-            if isinstance(m, nn.Conv2d):
-                init.kaiming_normal_(m.weight, mode='fan_out')
-                if m.bias is not None:
-                    init.constant_(m.bias, 0)
-            elif isinstance(m, nn.BatchNorm2d):
-                init.constant_(m.weight, 1)
-                init.constant_(m.bias, 0)
-            elif isinstance(m, nn.Linear):
-                init.normal_(m.weight, std=0.001)
-                if m.bias is not None:
-                    init.constant_(m.bias, 0)
-
-    def forward(self, x):
-        out = self.hs1(self.bn1(self.conv1(x)))
-        out = self.bneck(out)
-        out = self.hs2(self.bn2(self.conv2(out)))
-        out = F.avg_pool2d(out, 7)
-        out = out.view(out.size(0), -1)
-        out = self.hs3(self.bn3(self.linear3(out)))
-        out = self.linear4(out)
-        return out
-
-
-
-"""creating modelinstance"""
-model = MobileNetV3_Small(num_classes=30).to("cpu")
-model.load_state_dict( torch.load("MobileNet3_small_StateDictionary.pth"))
-
-classes = ['antelope',
- 'buffalo',
- 'chimpanzee',
- 'cow',
- 'deer',
- 'dolphin',
- 'elephant',
- 'fox',
- 'giant+panda',
- 'giraffe',
- 'gorilla',
- 'grizzly+bear',
- 'hamster',
- 'hippopotamus',
- 'horse',
- 'humpback+whale',
- 'leopard',
- 'lion',
- 'moose',
- 'otter',
- 'ox',
- 'pig',
- 'polar+bear',
- 'rabbit',
- 'rhinoceros',
- 'seal',
- 'sheep',
- 'squirrel',
- 'tiger',
- 'zebra']
-
-
-
-def predict(img):
-    # Add preprocessing and fix inference mode
-    model.eval()
-    
-    # Convert Gradio input to tensor
-    preprocess = transforms.Compose([
-        transforms.Resize(256),
-        transforms.CenterCrop(224),
-        transforms.ToTensor(),
-        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-    ])
-    
-    img_tensor = preprocess(img).unsqueeze(0)  
-
-    with torch.inference_mode():  
-        logits = model(img_tensor)
-        preds = logits.argmax(dim=1)
-    return classes[preds.item()]
-
-
-
-"""gradio interface"""
-"""demo = gr.Interface(
-    fn=predict,
-    inputs=gr.Image(type="pil", width=244, height=244),  
-    outputs="label", 
-    title="Animal Classifier",
-    description="Classify 30 animal categories: antelope, buffalo, chimpanzee, cow, deer, dolphin, elephant, fox, giant+panda, giraffe, gorilla, grizzly+bear, hamster, hippopotamus, horse, humpback+whale, leopard, lion, moose, otter, ox, pig, polar+bear, rabbit, rhinoceros, seal, sheep, squirrel, tiger, zebra"
-)
-"""
-
-with gr.Blocks() as demo:
-    gr.Markdown("## Animal Classifier")
-    gr.Markdown("Classify 30 animal categories: antelope, buffalo, chimpanzee, cow, deer, dolphin, elephant, fox, giant+panda, giraffe, gorilla, grizzly+bear, hamster, hippopotamus, horse, humpback+whale, leopard, lion, moose, otter, ox, pig, polar+bear, rabbit, rhinoceros, seal, sheep, squirrel, tiger, zebra")
-    with gr.Row():
-        upload = gr.File(
-            file_count="multiple",
-            file_types=["image"],
-            label="Upload Images"
-        )
-        submit = gr.Button("Classify")
-    
-    with gr.Row():
-        gallery = gr.Gallery(label="Uploaded Images")
-        predictions = gr.Textbox(label="Predictions", interactive=False)
-    
-    submit.click(
-        fn=lambda files: (
-            [f.name for f in files],
-            ", ".join([predict([file]) for file in files])
-        ),
-        inputs=upload,
-        outputs=[gallery, predictions]
-    )
-
-"""launch interface"""
-if __name__ == "__main__":
-    demo.launch()
+import torch
+import gradio as gr
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.nn import init
+import torchvision.transforms as transforms
+from PIL import Image
+
+# MobileNetV3 Model Definition (keep this exactly as in your original code)
+class hswish(nn.Module):
+    def forward(self, x):
+        return x * F.relu6(x + 3) / 6
+
+class hsigmoid(nn.Module):
+    def forward(self, x):
+        return F.relu6(x + 3) / 6
+
+class SeModule(nn.Module):
+    def __init__(self, in_size, reduction=4):
+        super().__init__()
+        self.se = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1),
+            nn.Conv2d(in_size, in_size//reduction, 1, bias=False),
+            nn.BatchNorm2d(in_size//reduction),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(in_size//reduction, in_size, 1, bias=False),
+            nn.BatchNorm2d(in_size),
+            hsigmoid()
+        )
+
+    def forward(self, x):
+        return x * self.se(x)
+
+class Block(nn.Module):
+    def __init__(self, kernel_size, in_size, expand_size, out_size, nolinear, semodule, stride):
+        super().__init__()
+        self.stride = stride
+        self.se = semodule
+        self.conv1 = nn.Conv2d(in_size, expand_size, 1, 1, 0, bias=False)
+        self.bn1 = nn.BatchNorm2d(expand_size)
+        self.nolinear1 = nolinear
+        self.conv2 = nn.Conv2d(expand_size, expand_size, kernel_size, stride, kernel_size//2, groups=expand_size, bias=False)
+        self.bn2 = nn.BatchNorm2d(expand_size)
+        self.nolinear2 = nolinear
+        self.conv3 = nn.Conv2d(expand_size, out_size, 1, 1, 0, bias=False)
+        self.bn3 = nn.BatchNorm2d(out_size)
+        self.shortcut = nn.Sequential()
+        if stride == 1 and in_size != out_size:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(in_size, out_size, 1, 1, 0, bias=False),
+                nn.BatchNorm2d(out_size),
+            )
+
+    def forward(self, x):
+        out = self.nolinear1(self.bn1(self.conv1(x)))
+        out = self.nolinear2(self.bn2(self.conv2(out)))
+        out = self.bn3(self.conv3(out))
+        if self.se: out = self.se(out)
+        return out + self.shortcut(x) if self.stride==1 else out
+
+class MobileNetV3_Small(nn.Module):
+    def __init__(self, num_classes=30):
+        super().__init__()
+        self.conv1 = nn.Conv2d(3, 16, 3, 2, 1, bias=False)
+        self.bn1 = nn.BatchNorm2d(16)
+        self.hs1 = hswish()
+        self.bneck = nn.Sequential(
+            Block(3, 16, 16, 16, nn.ReLU(), SeModule(16), 2),
+            Block(3, 16, 72, 24, nn.ReLU(), None, 2),
+            Block(3, 24, 88, 24, nn.ReLU(), None, 1),
+            Block(5, 24, 96, 40, hswish(), SeModule(40), 2),
+            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
+            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
+            Block(5, 40, 120, 48, hswish(), SeModule(48), 1),
+            Block(5, 48, 144, 48, hswish(), SeModule(48), 1),
+            Block(5, 48, 288, 96, hswish(), SeModule(96), 2),
+            Block(5, 96, 576, 96, hswish(), SeModule(96), 1),
+            Block(5, 96, 576, 96, hswish(), SeModule(96), 1),
+        )
+        self.conv2 = nn.Conv2d(96, 576, 1, 1, 0, bias=False)
+        self.bn2 = nn.BatchNorm2d(576)
+        self.hs2 = hswish()
+        self.linear3 = nn.Linear(576, 1280)
+        self.bn3 = nn.BatchNorm1d(1280)
+        self.hs3 = hswish()
+        self.linear4 = nn.Linear(1280, num_classes)
+        
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                init.kaiming_normal_(m.weight, mode='fan_out')
+                if m.bias is not None: init.constant_(m.bias, 0)
+            elif isinstance(m, nn.BatchNorm2d):
+                init.constant_(m.weight, 1)
+                init.constant_(m.bias, 0)
+            elif isinstance(m, nn.Linear):
+                init.normal_(m.weight, std=0.001)
+                if m.bias is not None: init.constant_(m.bias, 0)
+
+    def forward(self, x):
+        x = self.hs1(self.bn1(self.conv1(x)))
+        x = self.bneck(x)
+        x = self.hs2(self.bn2(self.conv2(x)))
+        x = F.avg_pool2d(x, x.size()[2:])
+        x = x.view(x.size(0), -1)
+        x = self.hs3(self.bn3(self.linear3(x)))
+        return self.linear4(x)
+
+# Initialize Model
+model = MobileNetV3_Small().cpu()
+model.load_state_dict(torch.load("MobileNet3_small_StateDictionary.pth", map_location='cpu'))
+model.eval()
+
+# Class Labels
+classes = [
+    'antelope', 'buffalo', 'chimpanzee', 'cow', 'deer', 'dolphin',
+    'elephant', 'fox', 'giant+panda', 'giraffe', 'gorilla', 'grizzly+bear',
+    'hamster', 'hippopotamus', 'horse', 'humpback+whale', 'leopard', 'lion',
+    'moose', 'otter', 'ox', 'pig', 'polar+bear', 'rabbit', 'rhinoceros',
+    'seal', 'sheep', 'squirrel', 'tiger', 'zebra'
+]
+
+# Preprocessing
+preprocess = transforms.Compose([
+    transforms.Resize(256),
+    transforms.CenterCrop(224),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+])
+
+def predict(images):
+    """Process multiple images and return predictions"""
+    predictions = []
+    
+    # Batch processing
+    batch = torch.stack([preprocess(Image.open(img).convert('RGB')) for img in images])
+    
+    with torch.inference_mode():
+        outputs = model(batch)
+        _, preds = torch.max(outputs, 1)
+    
+    return ", ".join([classes[p] for p in preds.cpu().numpy()])
+
+# Gradio Interface
+with gr.Blocks(title="Animal Classifier") as demo:
+    gr.Markdown("# 🐾 Animal Classifier")
+    gr.Markdown("Upload multiple animal images to get predictions!")
+    
+    with gr.Row():
+        inputs = gr.File(
+            file_count="multiple",
+            file_types=["image"],
+            label="Upload Animal Images"
+        )
+        submit = gr.Button("Classify 🚀", variant="primary")
+    
+    with gr.Row():
+        gallery = gr.Gallery(label="Upload Preview", columns=4)
+        outputs = gr.Textbox(label="Predictions", lines=5)
+    
+    submit.click(
+        fn=lambda files: (
+            [f.name for f in files],  # Update gallery
+            predict([f.name for f in files])  # Get predictions
+        ),
+        inputs=inputs,
+        outputs=[gallery, outputs]
+    )
+
+if __name__ == "__main__":
+    demo.launch(show_error=True)