mobilnet v4 部署笔记

下载模型：

https://huggingface.co/timm/mobilenetv4_hybrid_medium.e500_r224_in1k/tree/main

推理代码：

milenet_v4.py

from urllib.request import urlopenimport torch
from PIL import Image
import timmimg = Image.open(urlopen('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))# model = timm.create_model('mobilenetv1_125.ra4_e3600_r224_in1k', pretrained=False)
model = timm.create_model('mobilenetv4_conv_blur_medium.e500_r224_in1k', pretrained=False)state_dict = torch.load(r"D:\360安全浏览器下载\pytorch_model.bin", map_location='cpu')  # 或 'cuda' if GPU
model.load_state_dict(state_dict)model = model.eval()# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)print(top5_probabilities)