Upload 7 files

evaluate.py

@@ -0,0 +1,13 @@
+import torch
+
+features = torch.load("features.pth")
+qf = features["qf"]
+ql = features["ql"]
+gf = features["gf"]
+gl = features["gl"]
+
+scores = qf.mm(gf.t())
+res = scores.topk(5, dim=1)[1][:, 0]
+top1correct = gl[res].eq(ql).sum().item()
+
+print("Acc top1:{:.3f}".format(top1correct / ql.size(0)))

feature_extractor.py

@@ -0,0 +1,54 @@
+import torch
+import torchvision.transforms as transforms
+import numpy as np
+import cv2
+import logging
+
+from .model import Net
+
+
+class Extractor(object):
+    def __init__(self, model_path, use_cuda=True):
+        self.net = Net(reid=True)
+        self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
+        state_dict = torch.load(model_path, map_location=torch.device(self.device))[
+            'net_dict']
+        self.net.load_state_dict(state_dict)
+        logger = logging.getLogger("root.tracker")
+        logger.info("Loading weights from {}... Done!".format(model_path))
+        self.net.to(self.device)
+        self.size = (64, 128)
+        self.norm = transforms.Compose([
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+        ])
+
+    def _preprocess(self, im_crops):
+        """
+        TODO:
+            1. to float with scale from 0 to 1
+            2. resize to (64, 128) as Market1501 dataset did
+            3. concatenate to a numpy array
+            3. to torch Tensor
+            4. normalize
+        """
+        def _resize(im, size):
+            return cv2.resize(im.astype(np.float32)/255., size)
+
+        im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(
+            0) for im in im_crops], dim=0).float()
+        return im_batch
+
+    def __call__(self, im_crops):
+        im_batch = self._preprocess(im_crops)
+        with torch.no_grad():
+            im_batch = im_batch.to(self.device)
+            features = self.net(im_batch)
+        return features.cpu().numpy()
+
+
+if __name__ == '__main__':
+    img = cv2.imread("demo.jpg")[:, :, (2, 1, 0)]
+    extr = Extractor("checkpoint/ckpt.t7")
+    feature = extr(img)
+    print(feature.shape)

model.py

@@ -0,0 +1,109 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class BasicBlock(nn.Module):
+    def __init__(self, c_in, c_out, is_downsample=False):
+        super(BasicBlock, self).__init__()
+        self.is_downsample = is_downsample
+        if is_downsample:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=2, padding=1, bias=False)
+        else:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(c_out)
+        self.relu = nn.ReLU(True)
+        self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1,
+                               padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(c_out)
+        if is_downsample:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+        elif c_in != c_out:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+            self.is_downsample = True
+
+    def forward(self, x):
+        y = self.conv1(x)
+        y = self.bn1(y)
+        y = self.relu(y)
+        y = self.conv2(y)
+        y = self.bn2(y)
+        if self.is_downsample:
+            x = self.downsample(x)
+        return F.relu(x.add(y), True)
+
+
+def make_layers(c_in, c_out, repeat_times, is_downsample=False):
+    blocks = []
+    for i in range(repeat_times):
+        if i == 0:
+            blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ]
+        else:
+            blocks += [BasicBlock(c_out, c_out), ]
+    return nn.Sequential(*blocks)
+
+
+class Net(nn.Module):
+    def __init__(self, num_classes=751, reid=False):
+        super(Net, self).__init__()
+        # 3 128 64
+        self.conv = nn.Sequential(
+            nn.Conv2d(3, 64, 3, stride=1, padding=1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True),
+            # nn.Conv2d(32,32,3,stride=1,padding=1),
+            # nn.BatchNorm2d(32),
+            # nn.ReLU(inplace=True),
+            nn.MaxPool2d(3, 2, padding=1),
+        )
+        # 32 64 32
+        self.layer1 = make_layers(64, 64, 2, False)
+        # 32 64 32
+        self.layer2 = make_layers(64, 128, 2, True)
+        # 64 32 16
+        self.layer3 = make_layers(128, 256, 2, True)
+        # 128 16 8
+        self.layer4 = make_layers(256, 512, 2, True)
+        # 256 8 4
+        self.avgpool = nn.AvgPool2d((8, 4), 1)
+        # 256 1 1
+        self.reid = reid
+        self.classifier = nn.Sequential(
+            nn.Linear(512, 256),
+            nn.BatchNorm1d(256),
+            nn.ReLU(inplace=True),
+            nn.Dropout(),
+            nn.Linear(256, num_classes),
+        )
+
+    def forward(self, x):
+        x = self.conv(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)
+        # B x 128
+        if self.reid:
+            x = x.div(x.norm(p=2, dim=1, keepdim=True))
+            return x
+        # classifier
+        x = self.classifier(x)
+        return x
+
+
+if __name__ == '__main__':
+    net = Net()
+    x = torch.randn(4, 3, 128, 64)
+    y = net(x)
+    import ipdb
+    ipdb.set_trace()

original_model.py

@@ -0,0 +1,111 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class BasicBlock(nn.Module):
+    def __init__(self, c_in, c_out, is_downsample=False):
+        super(BasicBlock, self).__init__()
+        self.is_downsample = is_downsample
+        if is_downsample:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=2, padding=1, bias=False)
+        else:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(c_out)
+        self.relu = nn.ReLU(True)
+        self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1,
+                               padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(c_out)
+        if is_downsample:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+        elif c_in != c_out:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+            self.is_downsample = True
+
+    def forward(self, x):
+        y = self.conv1(x)
+        y = self.bn1(y)
+        y = self.relu(y)
+        y = self.conv2(y)
+        y = self.bn2(y)
+        if self.is_downsample:
+            x = self.downsample(x)
+        return F.relu(x.add(y), True)
+
+
+def make_layers(c_in, c_out, repeat_times, is_downsample=False):
+    blocks = []
+    for i in range(repeat_times):
+        if i == 0:
+            blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ]
+        else:
+            blocks += [BasicBlock(c_out, c_out), ]
+    return nn.Sequential(*blocks)
+
+
+class Net(nn.Module):
+    def __init__(self, num_classes=625, reid=False):
+        super(Net, self).__init__()
+        # 3 128 64
+        self.conv = nn.Sequential(
+            nn.Conv2d(3, 32, 3, stride=1, padding=1),
+            nn.BatchNorm2d(32),
+            nn.ELU(inplace=True),
+            nn.Conv2d(32, 32, 3, stride=1, padding=1),
+            nn.BatchNorm2d(32),
+            nn.ELU(inplace=True),
+            nn.MaxPool2d(3, 2, padding=1),
+        )
+        # 32 64 32
+        self.layer1 = make_layers(32, 32, 2, False)
+        # 32 64 32
+        self.layer2 = make_layers(32, 64, 2, True)
+        # 64 32 16
+        self.layer3 = make_layers(64, 128, 2, True)
+        # 128 16 8
+        self.dense = nn.Sequential(
+            nn.Dropout(p=0.6),
+            nn.Linear(128*16*8, 128),
+            nn.BatchNorm1d(128),
+            nn.ELU(inplace=True)
+        )
+        # 256 1 1
+        self.reid = reid
+        self.batch_norm = nn.BatchNorm1d(128)
+        self.classifier = nn.Sequential(
+            nn.Linear(128, num_classes),
+        )
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+
+        x = x.view(x.size(0), -1)
+        if self.reid:
+            x = self.dense[0](x)
+            x = self.dense[1](x)
+            x = x.div(x.norm(p=2, dim=1, keepdim=True))
+            return x
+        x = self.dense(x)
+        # B x 128
+        # classifier
+        x = self.classifier(x)
+        return x
+
+
+if __name__ == '__main__':
+    net = Net(reid=True)
+    x = torch.randn(4, 3, 128, 64)
+    y = net(x)
+    import ipdb
+    ipdb.set_trace()

test.py

@@ -0,0 +1,80 @@
+import torch
+import torch.backends.cudnn as cudnn
+import torchvision
+
+import argparse
+import os
+
+from model import Net
+
+parser = argparse.ArgumentParser(description="Train on market1501")
+parser.add_argument("--data-dir", default='data', type=str)
+parser.add_argument("--no-cuda", action="store_true")
+parser.add_argument("--gpu-id", default=0, type=int)
+args = parser.parse_args()
+
+# device
+device = "cuda:{}".format(
+    args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
+if torch.cuda.is_available() and not args.no_cuda:
+    cudnn.benchmark = True
+
+# data loader
+root = args.data_dir
+query_dir = os.path.join(root, "query")
+gallery_dir = os.path.join(root, "gallery")
+transform = torchvision.transforms.Compose([
+    torchvision.transforms.Resize((128, 64)),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize(
+        [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+queryloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(query_dir, transform=transform),
+    batch_size=64, shuffle=False
+)
+galleryloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(gallery_dir, transform=transform),
+    batch_size=64, shuffle=False
+)
+
+# net definition
+net = Net(reid=True)
+assert os.path.isfile(
+    "./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
+print('Loading from checkpoint/ckpt.t7')
+checkpoint = torch.load("./checkpoint/ckpt.t7")
+net_dict = checkpoint['net_dict']
+net.load_state_dict(net_dict, strict=False)
+net.eval()
+net.to(device)
+
+# compute features
+query_features = torch.tensor([]).float()
+query_labels = torch.tensor([]).long()
+gallery_features = torch.tensor([]).float()
+gallery_labels = torch.tensor([]).long()
+
+with torch.no_grad():
+    for idx, (inputs, labels) in enumerate(queryloader):
+        inputs = inputs.to(device)
+        features = net(inputs).cpu()
+        query_features = torch.cat((query_features, features), dim=0)
+        query_labels = torch.cat((query_labels, labels))
+
+    for idx, (inputs, labels) in enumerate(galleryloader):
+        inputs = inputs.to(device)
+        features = net(inputs).cpu()
+        gallery_features = torch.cat((gallery_features, features), dim=0)
+        gallery_labels = torch.cat((gallery_labels, labels))
+
+gallery_labels -= 2
+
+# save features
+features = {
+    "qf": query_features,
+    "ql": query_labels,
+    "gf": gallery_features,
+    "gl": gallery_labels
+}
+torch.save(features, "features.pth")

train.py

@@ -0,0 +1,206 @@
+import argparse
+import os
+import time
+
+import numpy as np
+import matplotlib.pyplot as plt
+import torch
+import torch.backends.cudnn as cudnn
+import torchvision
+
+from model import Net
+
+parser = argparse.ArgumentParser(description="Train on market1501")
+parser.add_argument("--data-dir", default='data', type=str)
+parser.add_argument("--no-cuda", action="store_true")
+parser.add_argument("--gpu-id", default=0, type=int)
+parser.add_argument("--lr", default=0.1, type=float)
+parser.add_argument("--interval", '-i', default=20, type=int)
+parser.add_argument('--resume', '-r', action='store_true')
+args = parser.parse_args()
+
+# device
+device = "cuda:{}".format(
+    args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
+if torch.cuda.is_available() and not args.no_cuda:
+    cudnn.benchmark = True
+
+# data loading
+root = args.data_dir
+train_dir = os.path.join(root, "train")
+test_dir = os.path.join(root, "test")
+transform_train = torchvision.transforms.Compose([
+    torchvision.transforms.RandomCrop((128, 64), padding=4),
+    torchvision.transforms.RandomHorizontalFlip(),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize(
+        [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+transform_test = torchvision.transforms.Compose([
+    torchvision.transforms.Resize((128, 64)),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize(
+        [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+trainloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(train_dir, transform=transform_train),
+    batch_size=64, shuffle=True
+)
+testloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(test_dir, transform=transform_test),
+    batch_size=64, shuffle=True
+)
+num_classes = max(len(trainloader.dataset.classes),
+                  len(testloader.dataset.classes))
+
+# net definition
+start_epoch = 0
+net = Net(num_classes=num_classes)
+if args.resume:
+    assert os.path.isfile(
+        "./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
+    print('Loading from checkpoint/ckpt.t7')
+    checkpoint = torch.load("./checkpoint/ckpt.t7")
+    # import ipdb; ipdb.set_trace()
+    net_dict = checkpoint['net_dict']
+    net.load_state_dict(net_dict)
+    best_acc = checkpoint['acc']
+    start_epoch = checkpoint['epoch']
+net.to(device)
+
+# loss and optimizer
+criterion = torch.nn.CrossEntropyLoss()
+optimizer = torch.optim.SGD(
+    net.parameters(), args.lr, momentum=0.9, weight_decay=5e-4)
+best_acc = 0.
+
+# train function for each epoch
+
+
+def train(epoch):
+    print("\nEpoch : %d" % (epoch+1))
+    net.train()
+    training_loss = 0.
+    train_loss = 0.
+    correct = 0
+    total = 0
+    interval = args.interval
+    start = time.time()
+    for idx, (inputs, labels) in enumerate(trainloader):
+        # forward
+        inputs, labels = inputs.to(device), labels.to(device)
+        outputs = net(inputs)
+        loss = criterion(outputs, labels)
+
+        # backward
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        # accumurating
+        training_loss += loss.item()
+        train_loss += loss.item()
+        correct += outputs.max(dim=1)[1].eq(labels).sum().item()
+        total += labels.size(0)
+
+        # print
+        if (idx+1) % interval == 0:
+            end = time.time()
+            print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
+                100.*(idx+1)/len(trainloader), end-start, training_loss /
+                interval, correct, total, 100.*correct/total
+            ))
+            training_loss = 0.
+            start = time.time()
+
+    return train_loss/len(trainloader), 1. - correct/total
+
+
+def test(epoch):
+    global best_acc
+    net.eval()
+    test_loss = 0.
+    correct = 0
+    total = 0
+    start = time.time()
+    with torch.no_grad():
+        for idx, (inputs, labels) in enumerate(testloader):
+            inputs, labels = inputs.to(device), labels.to(device)
+            outputs = net(inputs)
+            loss = criterion(outputs, labels)
+
+            test_loss += loss.item()
+            correct += outputs.max(dim=1)[1].eq(labels).sum().item()
+            total += labels.size(0)
+
+        print("Testing ...")
+        end = time.time()
+        print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
+            100.*(idx+1)/len(testloader), end-start, test_loss /
+            len(testloader), correct, total, 100.*correct/total
+        ))
+
+    # saving checkpoint
+    acc = 100.*correct/total
+    if acc > best_acc:
+        best_acc = acc
+        print("Saving parameters to checkpoint/ckpt.t7")
+        checkpoint = {
+            'net_dict': net.state_dict(),
+            'acc': acc,
+            'epoch': epoch,
+        }
+        if not os.path.isdir('checkpoint'):
+            os.mkdir('checkpoint')
+        torch.save(checkpoint, './checkpoint/ckpt.t7')
+
+    return test_loss/len(testloader), 1. - correct/total
+
+
+# plot figure
+x_epoch = []
+record = {'train_loss': [], 'train_err': [], 'test_loss': [], 'test_err': []}
+fig = plt.figure()
+ax0 = fig.add_subplot(121, title="loss")
+ax1 = fig.add_subplot(122, title="top1err")
+
+
+def draw_curve(epoch, train_loss, train_err, test_loss, test_err):
+    global record
+    record['train_loss'].append(train_loss)
+    record['train_err'].append(train_err)
+    record['test_loss'].append(test_loss)
+    record['test_err'].append(test_err)
+
+    x_epoch.append(epoch)
+    ax0.plot(x_epoch, record['train_loss'], 'bo-', label='train')
+    ax0.plot(x_epoch, record['test_loss'], 'ro-', label='val')
+    ax1.plot(x_epoch, record['train_err'], 'bo-', label='train')
+    ax1.plot(x_epoch, record['test_err'], 'ro-', label='val')
+    if epoch == 0:
+        ax0.legend()
+        ax1.legend()
+    fig.savefig("train.jpg")
+
+# lr decay
+
+
+def lr_decay():
+    global optimizer
+    for params in optimizer.param_groups:
+        params['lr'] *= 0.1
+        lr = params['lr']
+        print("Learning rate adjusted to {}".format(lr))
+
+
+def main():
+    for epoch in range(start_epoch, start_epoch+40):
+        train_loss, train_err = train(epoch)
+        test_loss, test_err = test(epoch)
+        draw_curve(epoch, train_loss, train_err, test_loss, test_err)
+        if (epoch+1) % 20 == 0:
+            lr_decay()
+
+
+if __name__ == '__main__':
+    main()