ResNet-50: Image Classification
ResNet-50 is a deep convolutional neural network model initially proposed by Microsoft Research to address the degradation problem in training deep networks. It uses "residual learning" by introducing skip connections or "shortcut connections" to avoid vanishing gradient issues, allowing for a significant increase in network depth. ResNet-50 consists of 50 layers, including multiple residual blocks, each containing several convolutional layers. Due to its efficiency and accuracy, ResNet-50 is widely used in image classification, object detection, and other computer vision tasks.
Source model
- Input shape: 224x224
- Number of parameters: 24.37M
- Model size: 97.4MB
- Output shape: 1x1000
Source model repository: resnet
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