File size: 6,512 Bytes
be3b791
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13685f2
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
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
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
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', 'giantpanda', 'giraffe', 'gorilla', 'grizzlybear',
    'hamster', 'hippopotamus', 'horse', 'humpbackwhale', 'leopard', 'lion',
    'moose', 'otter', 'ox', 'pig', 'polarbear', '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!")
    gr.Markdown("Detectable Classes: antelope, buffalo, chimpanzee, cow, deer, dolphin, elephant, fox, giantpanda, giraffe, gorilla, grizzlybear, hamster, hippopotamus, horse, humpbackwhale, leopard, lion, moose, otter, ox, pig, polarbear, rabbit, rhinoceros, seal, sheep, squirrel, tiger, zebra")
    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)