Hugging Face's logo

qualcomm
/
RTMDet

Object Detection
PyTorch
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
bc7d069
·
verified ·
1 Parent(s): a573899

v0.38.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Files changed (1) hide show
  1. README.md +16 -18
README.md CHANGED
@@ -36,23 +36,21 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | RTMDet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 85.371 ms | 0 - 66 MB | NPU | -- |
40
- | RTMDet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 32.048 ms | 0 - 115 MB | NPU | -- |
41
- | RTMDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 16.164 ms | 0 - 13 MB | NPU | -- |
42
- | RTMDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 14.591 ms | 0 - 62 MB | NPU | -- |
43
- | RTMDet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 23.717 ms | 0 - 66 MB | NPU | -- |
44
- | RTMDet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 85.371 ms | 0 - 66 MB | NPU | -- |
45
- | RTMDet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 16.164 ms | 0 - 12 MB | NPU | -- |
46
- | RTMDet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 34.815 ms | 0 - 75 MB | NPU | -- |
47
- | RTMDet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 16.185 ms | 0 - 14 MB | NPU | -- |
48
- | RTMDet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 23.717 ms | 0 - 66 MB | NPU | -- |
49
- | RTMDet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 15.883 ms | 0 - 17 MB | NPU | -- |
50
- | RTMDet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 14.666 ms | 0 - 62 MB | NPU | -- |
51
- | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 12.319 ms | 0 - 106 MB | NPU | -- |
52
- | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 11.083 ms | 4 - 46 MB | NPU | -- |
53
- | RTMDet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 11.317 ms | 0 - 70 MB | NPU | -- |
54
- | RTMDet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 10.326 ms | 0 - 37 MB | NPU | -- |
55
- | RTMDet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.965 ms | 51 - 51 MB | NPU | -- |
56
 
57
 
58
 
@@ -134,7 +132,7 @@ from qai_hub_models.models.rtmdet import Model
134
  torch_model = Model.from_pretrained()
135
 
136
  # Device
137
- device = hub.Device("Samsung Galaxy S24")
138
 
139
  # Trace model
140
  input_shape = torch_model.get_input_spec()
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | RTMDet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 85.357 ms | 0 - 67 MB | NPU | -- |
40
+ | RTMDet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 32.319 ms | 0 - 113 MB | NPU | -- |
41
+ | RTMDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 16.852 ms | 0 - 17 MB | NPU | -- |
42
+ | RTMDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 14.271 ms | 0 - 122 MB | NPU | -- |
43
+ | RTMDet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 23.861 ms | 0 - 67 MB | NPU | -- |
44
+ | RTMDet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 85.357 ms | 0 - 67 MB | NPU | -- |
45
+ | RTMDet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 16.361 ms | 0 - 17 MB | NPU | -- |
46
+ | RTMDet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 34.89 ms | 0 - 75 MB | NPU | -- |
47
+ | RTMDet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 16.064 ms | 0 - 15 MB | NPU | -- |
48
+ | RTMDet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 23.861 ms | 0 - 67 MB | NPU | -- |
49
+ | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 12.191 ms | 0 - 109 MB | NPU | -- |
50
+ | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.621 ms | 5 - 52 MB | NPU | -- |
51
+ | RTMDet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 9.366 ms | 0 - 70 MB | NPU | -- |
52
+ | RTMDet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 8.372 ms | 2 - 43 MB | NPU | -- |
53
+ | RTMDet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.48 ms | 51 - 51 MB | NPU | -- |
 
 
54
 
55
 
56
 
 
132
  torch_model = Model.from_pretrained()
133
 
134
  # Device
135
+ device = hub.Device("Samsung Galaxy S25")
136
 
137
  # Trace model
138
  input_shape = torch_model.get_input_spec()