File size: 5,911 Bytes
dfef520 f3d9287 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 |
import torch
import gradio as gd
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().to("cpu")
model.load_state_dict( torch.load("MobileNet3_small_full.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 predicts(img):
model.eval()
with torch.inference_mode:
logits = model(img.unsqueez(dim=0))
preds = logits.argmax(dim=1)
return classes[preds]
"""gradio inteface"""
demo = gd.Interface(predicts ,gd.Image("Image", width=244, height=244, image_mode="RGB", ))
"""launch interface"""
if __name__ == "__main__":
demo.launch() |