Hugging Face's logo

qualcomm
/
DETR-ResNet50-DC5

Object Detection
PyTorch
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
b55bf4e
·
verified ·
1 Parent(s): 58b7ad4

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: apache-2.0
4
  tags:
5
  - android
6
  pipeline_tag: object-detection
@@ -25,32 +25,32 @@ More details on model performance across various devices, can be found
25
 
26
  ### Model Details
27
 
28
- - **Model Type:** Object detection
29
  - **Model Stats:**
30
  - Model checkpoint: ResNet50-DC5
31
  - Input resolution: 480x480
32
  - Number of parameters: 42.2M
33
  - Model size: 159 MB
34
 
35
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | DETR-ResNet50-DC5 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 50.847 ms | 5 - 33 MB | FP16 | NPU | [DETR-ResNet50-DC5.so](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.so) |
38
- | DETR-ResNet50-DC5 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 59.187 ms | 1 - 252 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
39
- | DETR-ResNet50-DC5 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 38.627 ms | 5 - 135 MB | FP16 | NPU | [DETR-ResNet50-DC5.so](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.so) |
40
- | DETR-ResNet50-DC5 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 43.477 ms | 5 - 185 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
41
- | DETR-ResNet50-DC5 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 30.104 ms | 5 - 137 MB | FP16 | NPU | Use Export Script |
42
- | DETR-ResNet50-DC5 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 36.906 ms | 5 - 154 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
43
- | DETR-ResNet50-DC5 | SA7255P ADP | SA7255P | QNN | 1002.622 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
44
- | DETR-ResNet50-DC5 | SA8255 (Proxy) | SA8255P Proxy | QNN | 47.159 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
45
- | DETR-ResNet50-DC5 | SA8295P ADP | SA8295P | QNN | 62.399 ms | 1 - 19 MB | FP16 | NPU | Use Export Script |
46
- | DETR-ResNet50-DC5 | SA8650 (Proxy) | SA8650P Proxy | QNN | 46.978 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
47
- | DETR-ResNet50-DC5 | SA8775P ADP | SA8775P | QNN | 70.138 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
48
- | DETR-ResNet50-DC5 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 1002.622 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
49
- | DETR-ResNet50-DC5 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 46.225 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
50
- | DETR-ResNet50-DC5 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 70.138 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
51
- | DETR-ResNet50-DC5 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 61.004 ms | 5 - 116 MB | FP16 | NPU | Use Export Script |
52
- | DETR-ResNet50-DC5 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 46.521 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
53
- | DETR-ResNet50-DC5 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 61.192 ms | 80 - 80 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
54
 
55
 
56
 
@@ -112,12 +112,12 @@ python -m qai_hub_models.models.detr_resnet50_dc5.export
112
  Profiling Results
113
  ------------------------------------------------------------
114
  DETR-ResNet50-DC5
115
- Device : Samsung Galaxy S23 (13)
116
- Runtime : QNN
117
- Estimated inference time (ms) : 50.8
118
- Estimated peak memory usage (MB): [5, 33]
119
- Total # Ops : 827
120
- Compute Unit(s) : NPU (827 ops)
121
  ```
122
 
123
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - android
6
  pipeline_tag: object-detection
 
25
 
26
  ### Model Details
27
 
28
+ - **Model Type:** Model_use_case.object_detection
29
  - **Model Stats:**
30
  - Model checkpoint: ResNet50-DC5
31
  - Input resolution: 480x480
32
  - Number of parameters: 42.2M
33
  - Model size: 159 MB
34
 
35
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | DETR-ResNet50-DC5 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 176.745 ms | 5 - 14 MB | NPU | Use Export Script |
38
+ | DETR-ResNet50-DC5 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 79.67 ms | 5 - 134 MB | NPU | Use Export Script |
39
+ | DETR-ResNet50-DC5 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 51.087 ms | 5 - 7 MB | NPU | Use Export Script |
40
+ | DETR-ResNet50-DC5 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 64.52 ms | 2 - 12 MB | NPU | Use Export Script |
41
+ | DETR-ResNet50-DC5 | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 176.745 ms | 5 - 14 MB | NPU | Use Export Script |
42
+ | DETR-ResNet50-DC5 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 50.773 ms | 6 - 8 MB | NPU | Use Export Script |
43
+ | DETR-ResNet50-DC5 | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 70.119 ms | 0 - 18 MB | NPU | Use Export Script |
44
+ | DETR-ResNet50-DC5 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 50.666 ms | 5 - 7 MB | NPU | Use Export Script |
45
+ | DETR-ResNet50-DC5 | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 64.52 ms | 2 - 12 MB | NPU | Use Export Script |
46
+ | DETR-ResNet50-DC5 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 51.627 ms | 5 - 62 MB | NPU | Use Export Script |
47
+ | DETR-ResNet50-DC5 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 58.366 ms | 1 - 252 MB | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
48
+ | DETR-ResNet50-DC5 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 37.915 ms | 5 - 157 MB | NPU | Use Export Script |
49
+ | DETR-ResNet50-DC5 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 44.392 ms | 5 - 188 MB | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
50
+ | DETR-ResNet50-DC5 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 33.366 ms | 5 - 147 MB | NPU | Use Export Script |
51
+ | DETR-ResNet50-DC5 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 37.926 ms | 5 - 152 MB | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
52
+ | DETR-ResNet50-DC5 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 51.019 ms | 5 - 5 MB | NPU | Use Export Script |
53
+ | DETR-ResNet50-DC5 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 61.861 ms | 80 - 80 MB | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
54
 
55
 
56
 
 
112
  Profiling Results
113
  ------------------------------------------------------------
114
  DETR-ResNet50-DC5
115
+ Device : cs_8275 (ANDROID 14)
116
+ Runtime : QNN
117
+ Estimated inference time (ms) : 176.7
118
+ Estimated peak memory usage (MB): [5, 14]
119
+ Total # Ops : 829
120
+ Compute Unit(s) : npu (829 ops) gpu (0 ops) cpu (0 ops)
121
  ```
122
 
123