ResNeSt

import torch
# get list of models
torch.hub.list('zhanghang1989/ResNeSt', force_reload=True)
# load pretrained models, using ResNeSt-50 as an example
model = torch.hub.load('zhanghang1989/ResNeSt', 'resnest50', pretrained=True)
model.eval()
所有預訓練模型都要求輸入影像以相同的方式進行歸一化,即由形狀為 (3 x H x W) 的 3 通道 RGB 影像組成的小批次資料,其中 H 和 W 預計至少為 224。影像必須載入到 [0, 1] 範圍內,然後使用 mean = [0.485, 0.456, 0.406] 和 std = [0.229, 0.224, 0.225] 進行歸一化。
這是一個示例執行。
# Download an example image from the pytorch website
import urllib
url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
try: urllib.URLopener().retrieve(url, filename)
except: urllib.request.urlretrieve(url, filename)
# sample execution (requires torchvision)
from PIL import Image
from torchvision import transforms
input_image = Image.open(filename)
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
# move the input and model to GPU for speed if available
if torch.cuda.is_available():
input_batch = input_batch.to('cuda')
model.to('cuda')
with torch.no_grad():
output = model(input_batch)
# Tensor of shape 1000, with confidence scores over ImageNet's 1000 classes
print(output[0])
# The output has unnormalized scores. To get probabilities, you can run a softmax on it.
probabilities = torch.nn.functional.softmax(output[0], dim=0)
print(probabilities)
# Download ImageNet labels
!wget https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt
# Read the categories
with open("imagenet_classes.txt", "r") as f:
categories = [s.strip() for s in f.readlines()]
# Show top categories per image
top5_prob, top5_catid = torch.topk(probabilities, 5)
for i in range(top5_prob.size(0)):
print(categories[top5_catid[i]], top5_prob[i].item())
模型描述
ResNeSt 模型來源於 ResNeSt: 分裂注意力網路 論文。
儘管影像分類模型在最近持續取得進展,但大多數下游應用(如目標檢測和語義分割)仍採用 ResNet 變體作為骨幹網路,因為它們結構簡單且模組化。我們提出了一種簡單而模組化的分裂注意力(Split-Attention)塊,它實現了跨特徵圖組的注意力。透過像 ResNet 風格一樣堆疊這些分裂注意力塊,我們獲得了一種新的 ResNet 變體,我們稱之為 ResNeSt。我們的網路保留了 ResNet 的整體結構,以便直接用於下游任務,而不會引入額外的計算成本。ResNeSt 模型在相似模型複雜度的網路中表現出色,並且也有助於包括目標檢測、例項分割和語義分割在內的下游任務。
| 裁剪尺寸 | PyTorch | |
|---|---|---|
| ResNeSt-50 | 224 | 81.03 |
| ResNeSt-101 | 256 | 82.83 |
| ResNeSt-200 | 320 | 83.84 |
| ResNeSt-269 | 416 | 84.54 |
參考文獻