ResNet-34: Image Classification
ResNet-34 is a deep convolutional neural network in the ResNet (Residual Network) family, introduced by Kaiming He and colleagues in 2015. ResNet-34 consists of 34 layers and effectively addresses the vanishing gradient problem in deep networks by introducing residual (skip) connections, making the network easier to train as depth increases. These residual connections allow input features to bypass several layers, reducing training difficulty and enhancing performance. With greater depth than ResNet-18, ResNet-34 maintains a relatively low parameter count, making it suitable for tasks balancing computational efficiency and accuracy. This model is widely used in computer vision tasks like image classification, object detection, and semantic segmentation.
Source model
- Input shape: 224x224
- Number of parameters: 20.79M
- Model size: 83.14M
- 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