Skip to content

Latest commit

 

History

History
95 lines (80 loc) · 3.51 KB

pytorch_vision_shufflenet_v2.md

File metadata and controls

95 lines (80 loc) · 3.51 KB
Raw
layout background-class body-class title summary category image author tags github-link github-id featured_image_1 featured_image_2 accelerator order demo-model-link
hub_detail
hub-background
hub
ShuffleNet v2
An efficient ConvNet optimized for speed and memory, pre-trained on Imagenet
researchers
shufflenet_v2_1.png
Pytorch Team
vision
scriptable
pytorch/vision
shufflenet_v2_1.png
shufflenet_v2_2.png
cuda-optional
10
 
import torch
model = torch.hub.load('pytorch/vision:v0.10.0', 'shufflenet_v2_x1_0', pretrained=True)
model.eval()

All pre-trained models expect input images normalized in the same way, i.e. mini-batches of 3-channel RGB images of shape (3 x H x W), where H and W are expected to be at least 224. The images have to be loaded in to a range of [0, 1] and then normalized using mean = [0.485, 0.456, 0.406] and std = [0.229, 0.224, 0.225].

Here's a sample execution.

# 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())

Model Description

Previously, neural network architecture design was mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characteristics. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state of-the-art in terms of speed and accuracy tradeoff.

Model structure Top-1 error Top-5 error
shufflenet_v2 30.64 11.68

References