onnxmodelzoo/tf_efficientnetv2_l_in21ft1k_Opset17
By onnxmodelzoo · ↓ 0 · ♥ 0 · Updated 2025-09-25
What's in this repo
This page lists the files in onnxmodelzoo/tf_efficientnetv2_l_in21ft1k_Opset17, including tf_efficientnetv2_l_in21ft1k_Opset17.onnx.
- 1 ONNX models (.onnx files)
- 4 files, including 1 .md, 1 .onnx, 1 .yaml
- Last updated 2025-09-25
ONNX files
| File | Size | Download |
|---|---|---|
| tf_efficientnetv2_l_in21ft1k_Opset17.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
language: en license: apache-2.0 model_name: tf_efficientnetv2_l_in21ft1k_Opset17.onnx tags:
- Computer_Vision
The README content appears to be empty. Let me fetch it from the HuggingFace model page.
language: en license: apache-2.0 model_name: tf_efficientnetv2_l_in21ft1k_Opset17.onnx tags:
- 计算机视觉
注意:此仓库包含 ONNX 格式的模型。
模型来源: 该模型从 timm 转换而来。
模型描述: 该模型是从 EfficientNetV2 Large 模型转换而来,在 ImageNet-21K 数据集上进行了预训练,并在 ImageNet-1K 上进行了微调。
使用方法: 您可以使用 ONNX Runtime 来加载和运行该模型。以下是一个简单的 Python 示例:
import onnxruntime as ort
import numpy as np
from PIL import Image
from timm.data import resolve_data_config
from timm.data.transforms_factory import create_transform
# 加载模型
session = ort.InferenceSession("tf_efficientnetv2_l_in21ft1k_Opset17.onnx")
# 准备输入数据
config = resolve_data_config({}, model=session)
transform = create_transform(**config)
img = Image.open("your_image.jpg").convert("RGB")
input_tensor = transform(img).unsqueeze(0).numpy()
# 运行推理
outputs = session.run(None, {"input": input_tensor})
# 获取预测结果
predicted_class = np.argmax(outputs[0])
print(f"预测类别: {predicted_class}")
相关信息:
- Opset 版本: 17
- 原始模型: tf_efficientnetv2_l_in21ft1k
Model info
Created: 2025-09-25
Updated: 2025-09-25
View on Hugging FaceFiles (4)
Related models
More from onnxmodelzoo
More models
No task type declared.