ResNet-50 v1.7 — ONNX
ONNX export of ResNet-50, a deep residual network for image classification trained on ImageNet. 50-layer variant with 1000-class output.
Mirrored for use with inference4j, an inference-only AI library for Java.
Original Source
- Repository: ONNX Model Zoo
- License: mit
Usage with inference4j
try (ResNet model = ResNet.fromPretrained("models/resnet50")) {
List<Classification> results = model.classify(Path.of("cat.jpg"));
results.forEach(c -> System.out.printf("%s: %.2f%%%n", c.label(), c.score() * 100));
}
Model Details
| Property | Value |
|---|---|
| Architecture | ResNet-50 (50 layers, residual connections) |
| Task | Image classification (ImageNet 1000 classes) |
| Input | [batch, 3, 224, 224] — RGB, ImageNet-normalized |
| Output | [batch, 1000] — class probabilities |
| Original framework | ONNX Model Zoo |
License
This model is licensed under the MIT License. Original model from the ONNX Model Zoo.