add source single test for train

Former-commit-id: bbbc19eaa23049a6edabf93731f799f391e9623a

Picture_Train/model.py

@@ -0,0 +1,198 @@
+import torch.nn as nn
+import torch
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
+        super(BasicBlock, self).__init__()
+        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
+                               kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(out_channel)
+        self.relu = nn.ReLU()
+        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
+                               kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(out_channel)
+        self.downsample = downsample
+
+    def forward(self, x):
+        identity = x
+        if self.downsample is not None:
+            identity = self.downsample(x)
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+
+        out += identity
+        out = self.relu(out)
+
+        return out
+
+
+class Bottleneck(nn.Module):
+    """
+    注意：原论文中，在虚线残差结构的主分支上，第一个1x1卷积层的步距是2，第二个3x3卷积层步距是1。
+    但在pytorch官方实现过程中是第一个1x1卷积层的步距是1，第二个3x3卷积层步距是2，
+    这么做的好处是能够在top1上提升大概0.5%的准确率。
+    可参考Resnet v1.5 https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch
+    """
+    expansion = 4
+
+    def __init__(self, in_channel, out_channel, stride=1, downsample=None,
+                 groups=1, width_per_group=64):
+        super(Bottleneck, self).__init__()
+
+        width = int(out_channel * (width_per_group / 64.)) * groups
+
+        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width,
+                               kernel_size=1, stride=1, bias=False)  # squeeze channels
+        self.bn1 = nn.BatchNorm2d(width)
+        # -----------------------------------------
+        self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, groups=groups,
+                               kernel_size=3, stride=stride, bias=False, padding=1)
+        self.bn2 = nn.BatchNorm2d(width)
+        # -----------------------------------------
+        self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel*self.expansion,
+                               kernel_size=1, stride=1, bias=False)  # unsqueeze channels
+        self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
+        self.relu = nn.ReLU(inplace=True)
+        self.downsample = downsample
+
+    def forward(self, x):
+        identity = x
+        if self.downsample is not None:
+            identity = self.downsample(x)
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+        out = self.relu(out)
+
+        out = self.conv3(out)
+        out = self.bn3(out)
+
+        out += identity
+        out = self.relu(out)
+
+        return out
+
+
+class ResNet(nn.Module):
+
+    def __init__(self,
+                 block,
+                 blocks_num,
+                 num_classes=1000,
+                 include_top=True,
+                 groups=1,
+                 width_per_group=64):
+        super(ResNet, self).__init__()
+        self.include_top = include_top
+        self.in_channel = 64
+
+        self.groups = groups
+        self.width_per_group = width_per_group
+
+        self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
+                               padding=3, bias=False)
+        self.bn1 = nn.BatchNorm2d(self.in_channel)
+        self.relu = nn.ReLU(inplace=True)
+        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+        self.layer1 = self._make_layer(block, 64, blocks_num[0])
+        self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
+        self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
+        self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
+        if self.include_top:
+            self.avgpool = nn.AdaptiveAvgPool2d((1, 1))  # output size = (1, 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')
+
+    def _make_layer(self, block, channel, block_num, stride=1):
+        downsample = None
+        if stride != 1 or self.in_channel != channel * block.expansion:
+            downsample = nn.Sequential(
+                nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(channel * block.expansion))
+
+        layers = []
+        layers.append(block(self.in_channel,
+                            channel,
+                            downsample=downsample,
+                            stride=stride,
+                            groups=self.groups,
+                            width_per_group=self.width_per_group))
+        self.in_channel = channel * block.expansion
+
+        for _ in range(1, block_num):
+            layers.append(block(self.in_channel,
+                                channel,
+                                groups=self.groups,
+                                width_per_group=self.width_per_group))
+
+        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)
+
+        if self.include_top:
+            x = self.avgpool(x)
+            x = torch.flatten(x, 1)
+            x = self.fc(x)
+
+        return x
+
+
+def resnet34(num_classes=1000, include_top=True):
+    # https://download.pytorch.org/models/resnet34-333f7ec4.pth
+    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)
+
+
+def resnet50(num_classes=1000, include_top=True):
+    # https://download.pytorch.org/models/resnet50-19c8e357.pth
+    return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)
+
+
+def resnet101(num_classes=1000, include_top=True):
+    # https://download.pytorch.org/models/resnet101-5d3b4d8f.pth
+    return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)
+
+
+def resnext50_32x4d(num_classes=1000, include_top=True):
+    # https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth
+    groups = 32
+    width_per_group = 4
+    return ResNet(Bottleneck, [3, 4, 6, 3],
+                  num_classes=num_classes,
+                  include_top=include_top,
+                  groups=groups,
+                  width_per_group=width_per_group)
+
+
+def resnext101_32x8d(num_classes=1000, include_top=True):
+    # https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth
+    groups = 32
+    width_per_group = 8
+    return ResNet(Bottleneck, [3, 4, 23, 3],
+                  num_classes=num_classes,
+                  include_top=include_top,
+                  groups=groups,
+                  width_per_group=width_per_group)

Picture_Train/predict.py

@@ -6,7 +6,7 @@ from PIL import Image
 from torchvision import transforms
 import matplotlib.pyplot as plt
 
-from model import vgg
+from model_train import vgg
 
 # 单张图片预测程序
 def main():
@@ -18,7 +18,7 @@ def main():
          transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
 
     # load image
-    img_path = "C:/Picture_Train/test-data/pic_0032.jpg"
+    img_path = "data/val/yellow/ticket_0_3.jpg"
     assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
     img = Image.open(img_path)
     plt.imshow(img)
@@ -37,7 +37,7 @@ def main():
     # create model
     model = vgg(model_name="vgg16", num_classes=2).to(device)
     # load model weights
-    weights_path = "C:/Picture_Train/resnet34Net.pth"
+    weights_path = "resnet34-1Net.pth"
     assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
     model.load_state_dict(torch.load(weights_path, map_location=device))
 

Picture_Train/resnet34-1Net.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eded1e9cf905cceb40b6eadf6ec9979852f4ddaf2d1d470cf681f1fbf0d3a03a
+size 85279422

Picture_Train/src_predict.py

@@ -0,0 +1,40 @@
+from PIL import Image
+from torchvision import transforms
+import torch
+import os
+import json
+from model import resnet34
+
+print("init model")
+model = resnet34(num_classes=2).to("cpu")
+
+assert os.path.exists("resnet34-1Net.pth"), "file: '{}' dose not exist.".format("resnet34-1Net.pth")
+model.load_state_dict(torch.load("resnet34-1Net.pth", map_location="cpu"))
+
+print("load model done")
+
+def predictor(im_file): # 预测分类
+        image = Image.open(im_file)
+        data_transform = transforms.Compose([
+            transforms.Resize(256),
+            transforms.CenterCrop(224),
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+        ])
+        img = data_transform(image)
+        img = torch.unsqueeze(img, dim=0)
+        with open("class_indices.json", "r") as f:
+            class_indict = json.load(f)        
+
+        model.eval()
+        with torch.no_grad():
+            output = torch.squeeze(model(img)).cpu()
+            predict = torch.softmax(output, dim=0)
+            predict_cla = torch.argmax(predict).numpy()
+
+        class_a = "{}".format(class_indict[str(predict_cla)])
+        prob_a = "{:.3}".format(predict[predict_cla].numpy())
+        prob_b = float(prob_a)
+        # print('class_:',class_a)
+        # print('prob_:',prob_b)
+        return class_a, prob_b