在线时间:8:00-16:00
迪恩网络APP
随时随地掌握行业动态
扫描二维码
关注迪恩网络微信公众号
开源软件名称(OpenSource Name):tonylins/pytorch-mobilenet-v2开源软件地址(OpenSource Url):https://github.com/tonylins/pytorch-mobilenet-v2开源编程语言(OpenSource Language):Python 100.0%开源软件介绍(OpenSource Introduction):A PyTorch implementation of MobileNetV2This is a PyTorch implementation of MobileNetV2 architecture as described in the paper Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. [NEW] Add the code to automatically download the pre-trained weights. Training RecipeRecently I have figured out a good training setting:
You should get >72% top-1 accuracy with this training recipe! Accuracy & StatisticsHere is a comparison of statistics against the official TensorFlow implementation.
UsageTo use the pretrained model, run from MobileNetV2 import mobilenet_v2
net = mobilenet_v2(pretrained=True) Data Pre-processingI used the following code for data pre-processing on ImageNet: normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
input_size = 224
train_dataset = datasets.ImageFolder(
traindir,
transforms.Compose([
transforms.RandomResizedCrop(input_size, scale=(0.2, 1.0)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
]))
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=batch_size, shuffle=True,
num_workers=n_worker, pin_memory=True)
val_loader = torch.utils.data.DataLoader(
datasets.ImageFolder(valdir, transforms.Compose([
transforms.Resize(int(input_size/0.875)),
transforms.CenterCrop(input_size),
transforms.ToTensor(),
normalize,
])),
batch_size=batch_size, shuffle=False,
num_workers=n_worker, pin_memory=True) |
2023-10-27
2022-08-15
2022-08-17
2022-09-23
2022-08-13
请发表评论