qualcomm
/

FFNet-78S-Quantized

@@ -18,7 +18,7 @@ tags:
 FFNet-78S-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-78S-Quantized found [here](https://github.com/Qualcomm-AI-research/FFNet).
 This repository provides scripts to run FFNet-78S-Quantized on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/ffnet_78s_quantized).
@@ -34,14 +34,25 @@ More details on model performance across various devices, can be found
   - Model size: 26.7 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 | 5.845 ms | 1 - 3 MB | INT8 | NPU |  [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite)
 ## Installation
@@ -97,7 +108,17 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.ffnet_78s_quantized.export
 ```
@@ -121,15 +142,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on FFNet-78S-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/ffnet_78s_quantized).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
-- The license for the original implementation of FFNet-78S-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:ai-hub-support@qti.qualcomm.com).

 FFNet-78S-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-78S-Quantized found [here]({source_repo}).
 This repository provides scripts to run FFNet-78S-Quantized on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/ffnet_78s_quantized).
   - Model size: 26.7 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-78S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 5.745 ms | 0 - 2 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 11.963 ms | 0 - 24 MB | INT8 | NPU | [FFNet-78S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.onnx) |
+| FFNet-78S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.089 ms | 1 - 86 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 8.58 ms | 5 - 151 MB | INT8 | NPU | [FFNet-78S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.onnx) |
+| FFNet-78S-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 35.597 ms | 1 - 48 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 218.427 ms | 1 - 3 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 5.683 ms | 1 - 2 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 5.752 ms | 1 - 3 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 5.787 ms | 0 - 2 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 5.717 ms | 1 - 3 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 7.035 ms | 1 - 90 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.501 ms | 1 - 38 MB | INT8 | NPU | [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) |
+| FFNet-78S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 8.055 ms | 7 - 76 MB | INT8 | NPU | [FFNet-78S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.onnx) |
+| FFNet-78S-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 12.351 ms | 22 - 22 MB | INT8 | NPU | [FFNet-78S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.onnx) |
 ## Installation
 ```bash
 python -m qai_hub_models.models.ffnet_78s_quantized.export
 ```
+```
+Profiling Results
+------------------------------------------------------------
+FFNet-78S-Quantized
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE
+Estimated inference time (ms)   : 5.7
+Estimated peak memory usage (MB): [0, 2]
+Total # Ops                     : 156
+Compute Unit(s)                 : NPU (156 ops)
+```
 Get more details on FFNet-78S-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/ffnet_78s_quantized).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
+* The license for the original implementation of FFNet-78S-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:ai-hub-support@qti.qualcomm.com).