first commit

vgg_baye.py

@@ -0,0 +1,95 @@
+import torch.nn as nn
+import torch.utils.model_zoo as model_zoo
+import torch
+import os
+from torch.nn import functional as F
+
+__all__ = ['vgg19']
+model_urls = {
+    'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
+}
+
+class VGG(nn.Module):
+    def __init__(self, features):
+        super(VGG, self).__init__()
+        self.features = features
+        self.reg_layer = nn.Sequential(
+            nn.Conv2d(512, 256, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(256, 128, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(128, 1, 1)
+        )
+        # left_header
+        # self.left_header = nn.Sequential(
+        #     nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
+        #     nn.MaxPool2d(kernel_size=2, stride=2),
+        #     nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
+        #     nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
+        #     nn.AvgPool2d(kernel_size=2, stride=2),
+        #     nn.Flatten(),
+        #     nn.Linear(18432, 1000),
+        #     nn.Linear(1000, 5)
+        # )
+        # # right_header
+        # self.right_header = nn.Sequential(
+        #     nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
+        #     nn.MaxPool2d(kernel_size=2, stride=2),
+        #     nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
+        #     nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
+        #     nn.AvgPool2d(kernel_size=2, stride=2),
+        #     nn.Flatten(),
+        #     nn.Linear(18432, 1000),  #512 - 32768
+        #     nn.Linear(1000, 13)
+        # )
+
+    def forward(self, x):
+        outputs = []
+        # VGG19 outputs 0
+        x = self.features(x)
+        outputs.append(x)
+        #with torch.no_grad():
+            # left_header 1 posture
+        # x_left = self.left_header(x)
+        # outputs.append(x_left)
+        # # right_header 2
+        # x_right = self.right_header(x)
+        # outputs.append(x_right)
+        # density outputs 3
+        x = F.upsample_bilinear(x, scale_factor=2)
+        x = self.reg_layer(x)
+        outputs.append(torch.abs(x))
+        return torch.abs(x)
+
+def make_layers(cfg, batch_norm=False):
+    layers = []
+    in_channels = 3
+    for v in cfg:
+        if v == 'M':
+            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
+        else:
+            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
+            if batch_norm:
+                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
+            else:
+                layers += [conv2d, nn.ReLU(inplace=True)]
+            in_channels = v
+    return nn.Sequential(*layers)
+
+cfg = {
+    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512]
+}
+
+def vgg19():
+    """VGG 19-layer model (configuration "E")
+        model pre-trained on ImageNet
+    """
+    #make_layers(cfg['E'])
+    model = VGG(make_layers(cfg['E']))
+    model.load_state_dict(model_zoo.load_url(model_urls['vgg19']), strict=False)
+    # checkpoint = torch.load('./Net_model_bird/0121-110701/115_ckpt.tar')
+    # model.load_state_dict(checkpoint['model_state_dict'])
+    # model.load_state_dict(torch.load(os.path.join('./Net_model_bird', '84_best_model.pth')))
+
+    return model
+