Hugging Face's logo

qualcomm
/
DeepLabV3-ResNet50

Image Segmentation
PyTorch
TF Lite
android
Model card Files Community
qaihm-bot commited on
Commit
3a81e83
•
1 Parent(s): d94c40c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -35,15 +35,15 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | DeepLabV3-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 289.611 ms | 0 - 142 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
39
- | DeepLabV3-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 212.267 ms | 0 - 27 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
40
- | DeepLabV3-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 181.009 ms | 20 - 35 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
41
- | DeepLabV3-ResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 290.755 ms | 0 - 233 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
42
- | DeepLabV3-ResNet50 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 291.302 ms | 0 - 103 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
43
- | DeepLabV3-ResNet50 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 289.644 ms | 2 - 144 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
44
- | DeepLabV3-ResNet50 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 290.194 ms | 0 - 141 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
45
- | DeepLabV3-ResNet50 | SA8295P ADP | SA8295P | TFLITE | 280.662 ms | 21 - 42 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
46
- | DeepLabV3-ResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 529.955 ms | 0 - 30 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
47
 
48
 
49
 
@@ -105,12 +105,12 @@ python -m qai_hub_models.models.deeplabv3_resnet50.export
105
  Profiling Results
106
  ------------------------------------------------------------
107
  DeepLabV3-ResNet50
108
- Device : Samsung Galaxy S23 (13)
109
- Runtime : TFLITE
110
- Estimated inference time (ms) : 289.6
111
- Estimated peak memory usage (MB): [0, 142]
112
- Total # Ops : 95
113
- Compute Unit(s) : GPU (95 ops)
114
  ```
115
 
116
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | DeepLabV3-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 294.937 ms | 0 - 338 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
39
+ | DeepLabV3-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 206.139 ms | 21 - 47 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
40
+ | DeepLabV3-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 222.046 ms | 22 - 42 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
41
+ | DeepLabV3-ResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 292.298 ms | 0 - 268 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
42
+ | DeepLabV3-ResNet50 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 296.485 ms | 2 - 134 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
43
+ | DeepLabV3-ResNet50 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 292.364 ms | 0 - 128 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
44
+ | DeepLabV3-ResNet50 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 295.452 ms | 0 - 164 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
45
+ | DeepLabV3-ResNet50 | SA8295P ADP | SA8295P | TFLITE | 279.707 ms | 6 - 26 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
46
+ | DeepLabV3-ResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 467.317 ms | 23 - 51 MB | FP16 | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
47
 
48
 
49
 
 
105
  Profiling Results
106
  ------------------------------------------------------------
107
  DeepLabV3-ResNet50
108
+ Device : Samsung Galaxy S23 (13)
109
+ Runtime : TFLITE
110
+ Estimated inference time (ms) : 294.9
111
+ Estimated peak memory usage (MB): [0, 338]
112
+ Total # Ops : 100
113
+ Compute Unit(s) : GPU (98 ops) CPU (2 ops)
114
  ```
115
 
116