qualcomm
/

FFNet-40S-Quantized

@@ -18,7 +18,7 @@ tags:
 FFNet-40S-Quantized is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.
-This model is an implementation of FFNet-40S-Quantized found [here](https://github.com/Qualcomm-AI-research/FFNet).
 This repository provides scripts to run FFNet-40S-Quantized on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/ffnet_40s_quantized).
@@ -34,14 +34,25 @@ More details on model performance across various devices, can be found
   - Model size: 13.5 MB
   - Number of output classes: 19
-| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
-| ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 4.11 ms | 1 - 17 MB | INT8 | NPU |  [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite)
 ## Installation
@@ -97,7 +108,17 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.ffnet_40s_quantized.export
 ```
@@ -135,15 +156,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on FFNet-40S-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/ffnet_40s_quantized).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
-- The license for the original implementation of FFNet-40S-Quantized can be found
-  [here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
-- The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
 ## References
 * [Simple and Efficient Architectures for Semantic Segmentation](https://arxiv.org/abs/2206.08236)
 * [Source Model Implementation](https://github.com/Qualcomm-AI-research/FFNet)
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:[email protected]).

 FFNet-40S-Quantized is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.
+This model is an implementation of FFNet-40S-Quantized found [here]({source_repo}).
 This repository provides scripts to run FFNet-40S-Quantized on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/ffnet_40s_quantized).
   - Model size: 13.5 MB
   - Number of output classes: 19
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| FFNet-40S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.177 ms | 1 - 3 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 8.966 ms | 0 - 11 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
+| FFNet-40S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.927 ms | 1 - 63 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 6.409 ms | 4 - 107 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
+| FFNet-40S-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 27.414 ms | 3 - 42 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 189.84 ms | 1 - 14 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.061 ms | 1 - 2 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 4.154 ms | 1 - 8 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 4.147 ms | 1 - 3 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.123 ms | 0 - 185 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.144 ms | 0 - 67 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.516 ms | 1 - 31 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
+| FFNet-40S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 5.339 ms | 0 - 51 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
+| FFNet-40S-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.156 ms | 10 - 10 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
 ## Installation
 ```bash
 python -m qai_hub_models.models.ffnet_40s_quantized.export
 ```
+```
+Profiling Results
+------------------------------------------------------------
+FFNet-40S-Quantized
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE
+Estimated inference time (ms)   : 4.2
+Estimated peak memory usage (MB): [1, 3]
+Total # Ops                     : 99
+Compute Unit(s)                 : NPU (99 ops)
+```
 Get more details on FFNet-40S-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/ffnet_40s_quantized).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
+* The license for the original implementation of FFNet-40S-Quantized can be found [here](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE).
+* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
 ## References
 * [Simple and Efficient Architectures for Semantic Segmentation](https://arxiv.org/abs/2206.08236)
 * [Source Model Implementation](https://github.com/Qualcomm-AI-research/FFNet)
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:[email protected]).