DenseNet-121: Image Classification
DenseNet (Densely Connected Convolutional Networks) is a convolutional neural network architecture that introduces dense connections, where the output of each layer is directly connected to every subsequent layer. This design helps mitigate the vanishing gradient problem, promotes feature reuse, and reduces the number of parameters, thereby improving training efficiency. DenseNet is highly parameter-efficient and computationally efficient, making it suitable for tasks like image classification and object detection. It performs particularly well in scenarios with limited data. Key variants of DenseNet include DenseNet-121, DenseNet-169, and DenseNet-201.
Source model
- Input shape: 224x224
- Number of paramaters: 7.61M
- Model size: 30.81M
- Output shape: 1x1000
Source model repository: densenet
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