ResNet-18: Image Classification
ResNet-18 is one of the shallowest models in the Residual Network (ResNet) family, consisting of 18 layers. ResNet was proposed by Kaiming He and his team at Microsoft Research in 2015 to address the vanishing and exploding gradient problems in deep neural networks. ResNet-18 introduces residual connections (skip connections), which allow the input to bypass several layers, making the network easier to train and enabling greater depth. Despite its relatively low number of parameters, ResNet-18 achieves high classification accuracy and is widely used in tasks like image classification and object detection.
Source model
- Input shape: 224x224
- Number of parameters: 11.15M
- Model size: 44.58M
- Output shape: 1x1000
Source model repository: ResNet-18
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm
License
Source Model: BSD-3-CLAUSE
Deployable Model: APLUX-MODEL-FARM-LICENSE