SimpleNet

import torch
model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_5m_m1", pretrained=True)
# or any of these variants
# model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_5m_m2", pretrained=True)
# model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_9m_m1", pretrained=True)
# model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_9m_m2", pretrained=True)
# model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_small_m1_05", pretrained=True)
# model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_small_m2_05", pretrained=True)
# model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_small_m1_075", pretrained=True)
# model = torch.hub.load("coderx7/simplenet_pytorch:v1.0.0", "simplenetv1_small_m2_075", pretrained=True)
model.eval()

所有预训练模型都要求输入图像以相同的方式进行归一化,即形状为 (3 x H x W) 的 3 通道 RGB 图像的小批量,其中 HW 预计至少为 224。图像必须加载到 [0, 1] 范围内,然后使用 mean = [0.485, 0.456, 0.406]std = [0.229, 0.224, 0.225] 进行归一化。

这是一个示例执行。

# 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

SimpleNet 模型在“让我们保持简单,使用简单的架构超越更深更复杂的架构”中被提出。
这里我们有 8 个版本的 SimpleNet 模型,分别包含 1.5M、3.2M、5.7M 和 9.5M 参数。
详细的模型架构可以在表 1 和表 2 中找到。
它们在使用预训练模型在 ImageNet 数据集上的 1-crop 误差列在下方。

m2 变体

模型结构Top-1 误差Top-5 误差
simplenetv1_small_m2_0538.3316.512
simplenetv1_small_m2_07531.49411.85
simplenetv1_5m_m227.979.676
simplenetv1_9m_m225.778.252

m1 变体

模型结构Top-1 误差Top-5 误差
simplenetv1_small_m1_0538.87817.012
simplenetv1_small_m1_07532.21612.282
simplenetv1_5m_m128.45210.06
simplenetv1_9m_m126.2088.514

参考文献

让我们保持简单,使用简单的架构超越更深、更复杂的架构

模型类型: 可脚本化 | 视觉
提交者: Seyyed Hossein Hasanpour