File size: 3,877 Bytes
b53b6d3
 
4175bb8
b53b6d3
 
 
 
 
 
 
7943976
 
 
 
a12be6f
7943976
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4175bb8
 
b53b6d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7943976
 
 
b53b6d3
7943976
b53b6d3
 
7943976
b53b6d3
 
7943976
b53b6d3
7943976
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f00d4e
7943976
 
 
b53b6d3
7943976
 
 
b53b6d3
 
7943976
b53b6d3
7943976
 
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
import cv2
import numpy as np
import gradio as gr
from PIL import Image, ImageOps
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchvision import transforms
import os
import time
import io
import base64


class Net2(nn.Module):
    def __init__(self):
        super(Net2, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, 3, padding=1)
        self.bn1 = nn.BatchNorm2d(64)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.dropout1 = nn.Dropout(0.25)

        self.conv2 = nn.Conv2d(64, 64, 3, padding=1)
        self.bn2 = nn.BatchNorm2d(64)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.dropout2 = nn.Dropout(0.25)

        self.conv3 = nn.Conv2d(64, 64, 3, padding=1)
        self.bn3 = nn.BatchNorm2d(64)
        self.pool3 = nn.MaxPool2d(2, 2)
        self.dropout3 = nn.Dropout(0.25)

        self.conv4 = nn.Conv2d(64, 64, 3, padding=1)
        self.bn4 = nn.BatchNorm2d(64)
        self.pool4 = nn.MaxPool2d(2, 2)
        self.dropout4 = nn.Dropout(0.25)

        self.flatten = nn.Flatten()

        self.fc1 = nn.Linear(64 * 5 * 5, 200)
        self.fc2 = nn.Linear(200, 150)
        self.fc3 = nn.Linear(150, 2)

    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))
        x = self.pool1(x)
        x = self.dropout1(x)

        x = F.relu(self.bn2(self.conv2(x)))
        x = self.pool2(x)
        x = self.dropout2(x)

        x = F.relu(self.bn3(self.conv3(x)))
        x = self.pool3(x)
        x = self.dropout3(x)

        x = F.relu(self.bn4(self.conv4(x)))
        x = self.pool4(x)
        x = self.dropout4(x)

        x = self.flatten(x)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = F.softmax(self.fc3(x), dim=1)
        return x


model2 = None
model2_path = "model4.pth"

if os.path.exists(model2_path):
    state_dict = torch.load(model2_path, map_location=torch.device('cpu'))
    new_state_dict = {}
    for key, value in state_dict.items():
        new_key = key.replace("module.", "")
        new_state_dict[new_key] = value

    model = Net2()
    model.load_state_dict(new_state_dict)
    model.eval()

else:
    print("Model file not found at", model2_path)


def process_image(input_image):
    image = Image.open(io.BytesIO(input_image)).convert("RGB")

    start_time = time.time()
    heatmap = scanmap(np.array(image), model)
    elapsed_time = time.time() - start_time
    heatmap_img = Image.fromarray(np.uint8(plt.cm.hot(heatmap) * 255)).convert('RGB')

    heatmap_img = heatmap_img.resize(image.size)

    return image, heatmap_img, int(elapsed_time)

def scanmap(image_np, model):
    image_np = image_np.astype(np.float32) / 255.0

    window_size = (80, 80)
    stride = 10

    height, width, channels = image_np.shape

    probabilities_map = []

    for y in range(0, height - window_size[1] + 1, stride):
        row_probabilities = []
        for x in range(0, width - window_size[0] + 1, stride):
            cropped_window = image_np[y:y + window_size[1], x:x + window_size[0]]
            cropped_window_torch = transforms.ToTensor()(cropped_window).unsqueeze(0)

            with torch.no_grad():
                probabilities = model(cropped_window_torch)

            row_probabilities.append(probabilities[0, 1].item())

        probabilities_map.append(row_probabilities)

    probabilities_map = np.array(probabilities_map)
    return probabilities_map

def gradio_process_image(input_image):
    original, heatmap, elapsed_time = process_image(input_image.read())
    return original, heatmap, f"Elapsed Time (seconds): {elapsed_time}"

inputs = gr.Image(label="Upload Image")
outputs = [
    gr.Image(label="Original Image"),
    gr.Image(label="Heatmap"),
    gr.Textbox(label="Elapsed Time")
]

iface = gr.Interface(fn=gradio_process_image, inputs=inputs, outputs=outputs)
iface.launch()