File	Description	Quantization
`densenet201_fp32.tflite`	Floating-point LiteRT/TFLite model.	Floating-point weights and activations.
`densenet201_dynamic_wi8_afp32.tflite`	Dynamic weight-quantized LiteRT/TFLite model.	INT8 weights with floating-point activations.
`densenet201_int8_channelwise.tflite`	Static INT8 LiteRT/TFLite model.	INT8 weights and INT8 activations, with channelwise weight quantization.

Quantization Schema

densenet201_int8_channelwise.tflite was quantized with AI Edge Quantizer's static W8A8 recipe (STATIC_WI8_AI8).

The schema is:

Tensor group	Quantization
Weights	INT8, symmetric, channelwise quantization.
Activations	INT8, asymmetric, tensorwise quantization.
Model input	INT8, tensorwise quantized NCHW image tensor with shape `[1, 3, 224, 224]`.
Model output	INT8, tensorwise quantized logits tensor with shape `[1, 1000]`.

Calibration used real ImageNet validation images with the TIMM preprocessing flow for densenet201.tv_in1k. The resolved TIMM preprocessing config was

{"crop_mode": "center", "crop_pct": 0.875, "input_size": [3, 224, 224], "interpolation": "bicubic", "mean": [0.485, 0.456, 0.406], "std": [0.229, 0.224, 0.225]}

. When using APIs that expose raw tensor buffers, prepare the input and output using the quantization parameters stored in the model.

Runtime Compatibility

These artifacts are intended for LiteRT CPU and GPU execution.

The static INT8 channelwise artifact also AOT-compiled successfully through the LiteRT Qualcomm compiler plugin for SM8750, with the compiled model fully selected into Qualcomm NPU dispatch.

Enablement for other NPU backends is still under validation.

Intended Uses & Limitations

The model files were converted from pretrained weights from TIMM. The models may have their own licenses or terms and conditions derived from TIMM and the dataset used for training. It is your responsibility to determine whether you have permission to use the models for your use case.

Model Details

Model Type: Image classification / feature backbone
Model Stats:
- Params (M): 20.0
- GMACs: 4.3
- Activations (M): 7.9
- Image size: 224 x 224
Papers:
- Densely Connected Convolutional Networks: https://arxiv.org/abs/1608.06993
Dataset: ImageNet-1k
Original: https://github.com/pytorch/vision

Citation

bibtex

@inproceedings{huang2017densely,
  title={Densely Connected Convolutional Networks},
  author={Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q },
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2017}
}

litert-community/densenet201.tv_in1k

Densenet201

Model Description

Available Model Files

Quantization Schema

Runtime Compatibility

Intended Uses & Limitations

Model Details

Citation

litert-community/
densenet201.tv_in1k