Hugging Face's logo

qualcomm
/
FFNet-40S-Quantized

Image Segmentation
PyTorch
TF Lite
ONNX
quantized
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
6659201
•
1 Parent(s): 347e12a

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +16 -16
README.md CHANGED
@@ -37,21 +37,21 @@ More details on model performance across various devices, can be found
37
 
38
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
- | FFNet-40S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.063 ms | 1 - 3 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
41
- | FFNet-40S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 8.97 ms | 0 - 11 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
42
- | FFNet-40S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.921 ms | 1 - 66 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
43
- | FFNet-40S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 6.298 ms | 7 - 111 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
44
- | FFNet-40S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.922 ms | 1 - 31 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
45
- | FFNet-40S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 6.078 ms | 6 - 57 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
46
- | FFNet-40S-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 26.214 ms | 1 - 41 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
47
- | FFNet-40S-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 190.105 ms | 1 - 4 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
48
- | FFNet-40S-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.078 ms | 1 - 3 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
49
- | FFNet-40S-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 4.094 ms | 0 - 2 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
50
- | FFNet-40S-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 4.119 ms | 1 - 8 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
51
- | FFNet-40S-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.107 ms | 1 - 23 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
52
- | FFNet-40S-Quantized | SA8295P ADP | SA8295P | TFLITE | 7.999 ms | 10 - 41 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
53
- | FFNet-40S-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.033 ms | 0 - 66 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
54
- | FFNet-40S-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.156 ms | 9 - 9 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
55
 
56
 
57
 
@@ -116,7 +116,7 @@ Profiling Results
116
  FFNet-40S-Quantized
117
  Device : Samsung Galaxy S23 (13)
118
  Runtime : TFLITE
119
- Estimated inference time (ms) : 4.1
120
  Estimated peak memory usage (MB): [1, 3]
121
  Total # Ops : 99
122
  Compute Unit(s) : NPU (99 ops)
 
37
 
38
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | FFNet-40S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.183 ms | 1 - 3 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
41
+ | FFNet-40S-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 8.994 ms | 0 - 12 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
42
+ | FFNet-40S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.919 ms | 1 - 67 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
43
+ | FFNet-40S-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 6.253 ms | 7 - 112 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
44
+ | FFNet-40S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.975 ms | 0 - 31 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
45
+ | FFNet-40S-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 6.106 ms | 7 - 58 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
46
+ | FFNet-40S-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 26.424 ms | 0 - 38 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
47
+ | FFNet-40S-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 188.962 ms | 1 - 9 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
48
+ | FFNet-40S-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.076 ms | 0 - 139 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
49
+ | FFNet-40S-Quantized | SA8255 (Proxy) | SA8255P Proxy | 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) |
50
+ | FFNet-40S-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 4.16 ms | 0 - 175 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
51
+ | FFNet-40S-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.072 ms | 1 - 3 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
52
+ | FFNet-40S-Quantized | SA8295P ADP | SA8295P | TFLITE | 8.068 ms | 1 - 32 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
53
+ | FFNet-40S-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.159 ms | 0 - 64 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite) |
54
+ | FFNet-40S-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.128 ms | 10 - 10 MB | INT8 | NPU | [FFNet-40S-Quantized.onnx](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.onnx) |
55
 
56
 
57
 
 
116
  FFNet-40S-Quantized
117
  Device : Samsung Galaxy S23 (13)
118
  Runtime : TFLITE
119
+ Estimated inference time (ms) : 4.2
120
  Estimated peak memory usage (MB): [1, 3]
121
  Total # Ops : 99
122
  Compute Unit(s) : NPU (99 ops)