|
import gradio as gr |
|
import torch.nn as nn |
|
import math |
|
import torch.utils.model_zoo as model_zoo |
|
import torch |
|
import torch.nn.functional as F |
|
|
|
__all__ = ['Res2Net', 'res2net50_v1b', 'res2net101_v1b'] |
|
|
|
model_urls = { |
|
'res2net50_v1b_26w_4s': 'https://shanghuagao.oss-cn-beijing.aliyuncs.com/res2net/res2net50_v1b_26w_4s-3cf99910.pth', |
|
'res2net101_v1b_26w_4s': 'https://shanghuagao.oss-cn-beijing.aliyuncs.com/res2net/res2net101_v1b_26w_4s-0812c246.pth', |
|
} |
|
|
|
|
|
class Bottle2neck(nn.Module): |
|
expansion = 4 |
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None, baseWidth=26, scale=4, stype='normal'): |
|
""" Constructor |
|
Args: |
|
inplanes: input channel dimensionality |
|
planes: output channel dimensionality |
|
stride: conv stride. Replaces pooling layer. |
|
downsample: None when stride = 1 |
|
baseWidth: basic width of conv3x3 |
|
scale: number of scale. |
|
type: 'normal': normal set. 'stage': first block of a new stage. |
|
""" |
|
super(Bottle2neck, self).__init__() |
|
|
|
width = int(math.floor(planes * (baseWidth / 64.0))) |
|
self.conv1 = nn.Conv2d(inplanes, width * scale, kernel_size=1, bias=False) |
|
self.bn1 = nn.BatchNorm2d(width * scale) |
|
|
|
if scale == 1: |
|
self.nums = 1 |
|
else: |
|
self.nums = scale - 1 |
|
if stype == 'stage': |
|
self.pool = nn.AvgPool2d(kernel_size=3, stride=stride, padding=1) |
|
convs = [] |
|
bns = [] |
|
for i in range(self.nums): |
|
convs.append(nn.Conv2d(width, width, kernel_size=3, stride=stride, padding=1, bias=False)) |
|
bns.append(nn.BatchNorm2d(width)) |
|
self.convs = nn.ModuleList(convs) |
|
self.bns = nn.ModuleList(bns) |
|
|
|
self.conv3 = nn.Conv2d(width * scale, planes * self.expansion, kernel_size=1, bias=False) |
|
self.bn3 = nn.BatchNorm2d(planes * self.expansion) |
|
|
|
self.relu = nn.ReLU(inplace=True) |
|
self.downsample = downsample |
|
self.stype = stype |
|
self.scale = scale |
|
self.width = width |
|
|
|
def forward(self, x): |
|
residual = x |
|
|
|
out = self.conv1(x) |
|
out = self.bn1(out) |
|
out = self.relu(out) |
|
|
|
spx = torch.split(out, self.width, 1) |
|
for i in range(self.nums): |
|
if i == 0 or self.stype == 'stage': |
|
sp = spx[i] |
|
else: |
|
sp = sp + spx[i] |
|
sp = self.convs[i](sp) |
|
sp = self.relu(self.bns[i](sp)) |
|
if i == 0: |
|
out = sp |
|
else: |
|
out = torch.cat((out, sp), 1) |
|
if self.scale != 1 and self.stype == 'normal': |
|
out = torch.cat((out, spx[self.nums]), 1) |
|
elif self.scale != 1 and self.stype == 'stage': |
|
out = torch.cat((out, self.pool(spx[self.nums])), 1) |
|
|
|
out = self.conv3(out) |
|
out = self.bn3(out) |
|
|
|
if self.downsample is not None: |
|
residual = self.downsample(x) |
|
|
|
out += residual |
|
out = self.relu(out) |
|
|
|
return out |
|
|
|
|
|
class Res2Net(nn.Module): |
|
|
|
def __init__(self, block, layers, baseWidth=26, scale=4, num_classes=1000): |
|
self.inplanes = 64 |
|
super(Res2Net, self).__init__() |
|
self.baseWidth = baseWidth |
|
self.scale = scale |
|
self.conv1 = nn.Sequential( |
|
nn.Conv2d(3, 32, 3, 2, 1, bias=False), |
|
nn.BatchNorm2d(32), |
|
nn.ReLU(inplace=True), |
|
nn.Conv2d(32, 32, 3, 1, 1, bias=False), |
|
nn.BatchNorm2d(32), |
|
nn.ReLU(inplace=True), |
|
nn.Conv2d(32, 64, 3, 1, 1, bias=False) |
|
) |
|
self.bn1 = nn.BatchNorm2d(64) |
|
self.relu = nn.ReLU() |
|
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) |
|
self.layer1 = self._make_layer(block, 64, layers[0]) |
|
self.layer2 = self._make_layer(block, 128, layers[1], stride=2) |
|
self.layer3 = self._make_layer(block, 256, layers[2], stride=2) |
|
self.layer4 = self._make_layer(block, 512, layers[3], stride=2) |
|
self.avgpool = nn.AdaptiveAvgPool2d(1) |
|
self.fc = nn.Linear(512 * block.expansion, num_classes) |
|
|
|
for m in self.modules(): |
|
if isinstance(m, nn.Conv2d): |
|
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') |
|
elif isinstance(m, nn.BatchNorm2d): |
|
nn.init.constant_(m.weight, 1) |
|
nn.init.constant_(m.bias, 0) |
|
|
|
def _make_layer(self, block, planes, blocks, stride=1): |
|
downsample = None |
|
if stride != 1 or self.inplanes != planes * block.expansion: |
|
downsample = nn.Sequential( |
|
nn.AvgPool2d(kernel_size=stride, stride=stride, |
|
ceil_mode=True, count_include_pad=False), |
|
nn.Conv2d(self.inplanes, planes * block.expansion, |
|
kernel_size=1, stride=1, bias=False), |
|
nn.BatchNorm2d(planes * block.expansion), |
|
) |
|
|
|
layers = [] |
|
layers.append(block(self.inplanes, planes, stride, downsample=downsample, |
|
stype='stage', baseWidth=self.baseWidth, scale=self.scale)) |
|
self.inplanes = planes * block.expansion |
|
for i in range(1, blocks): |
|
layers.append(block(self.inplanes, planes, baseWidth=self.baseWidth, scale=self.scale)) |
|
|
|
return nn.Sequential(*layers) |
|
|
|
def forward(self, x): |
|
x = self.conv1(x) |
|
x = self.bn1(x) |
|
x = self.relu(x) |
|
x = self.maxpool(x) |
|
|
|
x = self.layer1(x) |
|
x = self.layer2(x) |
|
x = self.layer3(x) |
|
x = self.layer4(x) |
|
|
|
x = self.avgpool(x) |
|
x = x.view(x.size(0), -1) |
|
x = self.fc(x) |
|
|
|
return x |
|
|
|
|
|
def res2net50_v1b(pretrained=False, **kwargs): |
|
"""Constructs a Res2Net-50_v1b model. |
|
Res2Net-50 refers to the Res2Net-50_v1b_26w_4s. |
|
Args: |
|
pretrained (bool): If True, returns a model pre-trained on ImageNet |
|
""" |
|
model = Res2Net(Bottle2neck, [3, 4, 6, 3], baseWidth=26, scale=4, **kwargs) |
|
if pretrained: |
|
model.load_state_dict(model_zoo.load_url(model_urls['res2net50_v1b_26w_4s'])) |
|
return model |
|
|
|
|
|
def res2net101_v1b(pretrained=False, **kwargs): |
|
"""Constructs a Res2Net-50_v1b_26w_4s model. |
|
Args: |
|
pretrained (bool): If True, returns a model pre-trained on ImageNet |
|
""" |
|
model = Res2Net(Bottle2neck, [3, 4, 23, 3], baseWidth=26, scale=4, **kwargs) |
|
if pretrained: |
|
model.load_state_dict(model_zoo.load_url(model_urls['res2net101_v1b_26w_4s'])) |
|
return model |
|
|
|
|
|
def res2net50_v1b_26w_4s(pretrained=False, **kwargs): |
|
"""Constructs a Res2Net-50_v1b_26w_4s model. |
|
Args: |
|
pretrained (bool): If True, returns a model pre-trained on ImageNet |
|
""" |
|
model = Res2Net(Bottle2neck, [3, 4, 6, 3], baseWidth=26, scale=4, **kwargs) |
|
if pretrained: |
|
model.load_state_dict(torch.load(pthfile, map_location='cpu')) |
|
return model |
|
|
|
|
|
def res2net101_v1b_26w_4s(pretrained=False, **kwargs): |
|
"""Constructs a Res2Net-50_v1b_26w_4s model. |
|
Args: |
|
pretrained (bool): If True, returns a model pre-trained on ImageNet |
|
""" |
|
model = Res2Net(Bottle2neck, [3, 4, 23, 3], baseWidth=26, scale=4, **kwargs) |
|
if pretrained: |
|
model.load_state_dict(model_zoo.load_url(model_urls['res2net101_v1b_26w_4s'])) |
|
return model |
|
|
|
|
|
def res2net152_v1b_26w_4s(pretrained=False, **kwargs): |
|
"""Constructs a Res2Net-50_v1b_26w_4s model. |
|
Args: |
|
pretrained (bool): If True, returns a model pre-trained on ImageNet |
|
""" |
|
model = Res2Net(Bottle2neck, [3, 8, 36, 3], baseWidth=26, scale=4, **kwargs) |
|
if pretrained: |
|
model.load_state_dict(model_zoo.load_url(model_urls['res2net152_v1b_26w_4s'])) |
|
return model |
|
|
|
|
|
class mutil_model(nn.Module): |
|
|
|
def __init__(self, category_num=10): |
|
super(mutil_model, self).__init__() |
|
self.model1 = res2net50_v1b_26w_4s(pretrained=False) |
|
self.model1.fc = nn.Sequential( |
|
nn.Linear(in_features=2048, out_features=category_num, bias=True), |
|
) |
|
self.model2 = torch.load('./enet_b2_8' + '.pt', map_location=torch.device('cpu')) |
|
self.model2.classifier = nn.Sequential( |
|
nn.Linear(in_features=1408, out_features=category_num, bias=True), |
|
) |
|
self.fc = nn.Linear(in_features=category_num * 2, out_features=category_num, bias=True) |
|
|
|
def forward(self, x): |
|
x1 = self.model1(x) |
|
x2 = self.model2(x) |
|
x = torch.cat((x1, x2), 1) |
|
x = self.fc(x) |
|
return x |
|
|
|
|
|
pth_path = './res2net_pretrain_model_999.pt' |
|
category_num = 9 |
|
|
|
|
|
|
|
device = "cpu" |
|
|
|
|
|
|
|
model = res2net50_v1b_26w_4s(pretrained=False) |
|
|
|
num_ftrs = model.fc.in_features |
|
model.fc = nn.Sequential( |
|
nn.Linear(in_features=2048, out_features=1000, bias=True), |
|
nn.Dropout(0.5), |
|
nn.Linear(1000, out_features=category_num) |
|
) |
|
model.fc = nn.Sequential( |
|
nn.Linear(in_features=2048, out_features=category_num, bias=True), |
|
) |
|
|
|
model = model.to(device) |
|
model.device = device |
|
model.load_state_dict(torch.load(pth_path,torch.device('cpu'))) |
|
model.eval() |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
labels = ['中国风', '古典', '电子', '摇滚', '乡村', '说唱', '民谣', '动漫', '现代'] |
|
|
|
import requests |
|
import torch |
|
|
|
import gradio as gr |
|
import torchvision.transforms as transforms |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
print(len(labels)) |
|
|
|
|
|
def classify_image(inp): |
|
|
|
|
|
transform_test = transforms.Compose([ |
|
|
|
transforms.Resize((256, 256)), |
|
transforms.ToTensor(), |
|
transforms.Normalize((0.485, 0.456, 0.406), |
|
(0.229, 0.224, 0.225)), |
|
]) |
|
inp = transform_test(inp) |
|
print(inp) |
|
with torch.no_grad(): |
|
prediction = model(torch.unsqueeze(inp, 0)).flatten() |
|
print(prediction) |
|
prediction = torch.nn.Softmax(dim=0)(prediction) |
|
print(prediction) |
|
return {labels[i]: float(prediction[i].item()) for i in range(len(labels))} |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gr.Interface( |
|
classify_image, |
|
|
|
gr.inputs.Image(type='pil'), |
|
outputs='label' |
|
|
|
|
|
|
|
).launch(share=True) |
|
|