Hugging Face's logo

qualcomm
/
DDRNet23-Slim

Image Segmentation
PyTorch
LiteRT
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
30779ac
·
verified ·
1 Parent(s): 067dba8

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +29 -28
README.md CHANGED
@@ -37,39 +37,39 @@ 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
- | DDRNet23-Slim | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 5.128 ms | 1 - 22 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
41
- | DDRNet23-Slim | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.092 ms | 9 - 22 MB | FP16 | NPU | [DDRNet23-Slim.so](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.so) |
42
- | DDRNet23-Slim | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 7.602 ms | 11 - 53 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
43
- | DDRNet23-Slim | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.527 ms | 0 - 35 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
44
- | DDRNet23-Slim | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.529 ms | 0 - 34 MB | FP16 | NPU | [DDRNet23-Slim.so](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.so) |
45
- | DDRNet23-Slim | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 5.199 ms | 11 - 57 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
46
- | DDRNet23-Slim | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.45 ms | 0 - 33 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
47
- | DDRNet23-Slim | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.738 ms | 9 - 41 MB | FP16 | NPU | Use Export Script |
48
- | DDRNet23-Slim | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 5.13 ms | 9 - 45 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
49
- | DDRNet23-Slim | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 5.161 ms | 1 - 20 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
50
- | DDRNet23-Slim | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.593 ms | 9 - 13 MB | FP16 | NPU | Use Export Script |
51
- | DDRNet23-Slim | SA7255P ADP | SA7255P | TFLITE | 180.379 ms | 1 - 27 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
52
- | DDRNet23-Slim | SA7255P ADP | SA7255P | QNN | 179.765 ms | 5 - 14 MB | FP16 | NPU | Use Export Script |
53
- | DDRNet23-Slim | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 5.126 ms | 1 - 20 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
54
- | DDRNet23-Slim | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.651 ms | 9 - 12 MB | FP16 | NPU | Use Export Script |
55
- | DDRNet23-Slim | SA8295P ADP | SA8295P | TFLITE | 8.902 ms | 1 - 29 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
56
- | DDRNet23-Slim | SA8295P ADP | SA8295P | QNN | 8.961 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
57
- | DDRNet23-Slim | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 5.083 ms | 1 - 16 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
58
- | DDRNet23-Slim | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.686 ms | 9 - 12 MB | FP16 | NPU | Use Export Script |
59
- | DDRNet23-Slim | SA8775P ADP | SA8775P | TFLITE | 10.144 ms | 1 - 27 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
60
- | DDRNet23-Slim | SA8775P ADP | SA8775P | QNN | 9.462 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
61
- | DDRNet23-Slim | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 7.51 ms | 1 - 28 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
62
- | DDRNet23-Slim | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.65 ms | 9 - 38 MB | FP16 | NPU | Use Export Script |
63
- | DDRNet23-Slim | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.962 ms | 9 - 9 MB | FP16 | NPU | Use Export Script |
64
- | DDRNet23-Slim | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.405 ms | 9 - 9 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
65
 
66
 
67
 
68
 
69
  ## Installation
70
 
71
- This model can be installed as a Python package via pip.
72
 
 
73
  ```bash
74
  pip install qai-hub-models
75
  ```
@@ -153,7 +153,7 @@ from qai_hub_models.models.ddrnet23_slim import Model
153
  torch_model = Model.from_pretrained()
154
 
155
  # Device
156
- device = hub.Device("Samsung Galaxy S23")
157
 
158
  # Trace model
159
  input_shape = torch_model.get_input_spec()
@@ -245,7 +245,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
245
 
246
 
247
  ## License
248
- * The license for the original implementation of DDRNet23-Slim can be found [here](https://github.com/chenjun2hao/DDRNet.pytorch/blob/main/LICENSE).
 
249
  * 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)
250
 
251
 
 
37
 
38
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | DDRNet23-Slim | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 5.079 ms | 1 - 22 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
41
+ | DDRNet23-Slim | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.105 ms | 9 - 28 MB | FP16 | NPU | [DDRNet23-Slim.so](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.so) |
42
+ | DDRNet23-Slim | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 7.409 ms | 11 - 54 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
43
+ | DDRNet23-Slim | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.51 ms | 0 - 34 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
44
+ | DDRNet23-Slim | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.515 ms | 9 - 43 MB | FP16 | NPU | [DDRNet23-Slim.so](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.so) |
45
+ | DDRNet23-Slim | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 5.164 ms | 11 - 51 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
46
+ | DDRNet23-Slim | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.532 ms | 0 - 33 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
47
+ | DDRNet23-Slim | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.574 ms | 9 - 41 MB | FP16 | NPU | Use Export Script |
48
+ | DDRNet23-Slim | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.243 ms | 3 - 41 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
49
+ | DDRNet23-Slim | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 5.103 ms | 1 - 16 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
50
+ | DDRNet23-Slim | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.552 ms | 9 - 12 MB | FP16 | NPU | Use Export Script |
51
+ | DDRNet23-Slim | SA7255P ADP | SA7255P | TFLITE | 180.228 ms | 1 - 28 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
52
+ | DDRNet23-Slim | SA7255P ADP | SA7255P | QNN | 179.797 ms | 4 - 14 MB | FP16 | NPU | Use Export Script |
53
+ | DDRNet23-Slim | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 5.198 ms | 1 - 20 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
54
+ | DDRNet23-Slim | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.632 ms | 9 - 12 MB | FP16 | NPU | Use Export Script |
55
+ | DDRNet23-Slim | SA8295P ADP | SA8295P | TFLITE | 8.886 ms | 1 - 29 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
56
+ | DDRNet23-Slim | SA8295P ADP | SA8295P | QNN | 8.571 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
57
+ | DDRNet23-Slim | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 5.124 ms | 1 - 16 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
58
+ | DDRNet23-Slim | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.665 ms | 9 - 12 MB | FP16 | NPU | Use Export Script |
59
+ | DDRNet23-Slim | SA8775P ADP | SA8775P | TFLITE | 10.036 ms | 1 - 27 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
60
+ | DDRNet23-Slim | SA8775P ADP | SA8775P | QNN | 9.504 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
61
+ | DDRNet23-Slim | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 7.533 ms | 1 - 33 MB | FP16 | NPU | [DDRNet23-Slim.tflite](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.tflite) |
62
+ | DDRNet23-Slim | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.591 ms | 8 - 35 MB | FP16 | NPU | Use Export Script |
63
+ | DDRNet23-Slim | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.918 ms | 9 - 9 MB | FP16 | NPU | Use Export Script |
64
+ | DDRNet23-Slim | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.409 ms | 9 - 9 MB | FP16 | NPU | [DDRNet23-Slim.onnx](https://huggingface.co/qualcomm/DDRNet23-Slim/blob/main/DDRNet23-Slim.onnx) |
65
 
66
 
67
 
68
 
69
  ## Installation
70
 
 
71
 
72
+ Install the package via pip:
73
  ```bash
74
  pip install qai-hub-models
75
  ```
 
153
  torch_model = Model.from_pretrained()
154
 
155
  # Device
156
+ device = hub.Device("Samsung Galaxy S24")
157
 
158
  # Trace model
159
  input_shape = torch_model.get_input_spec()
 
245
 
246
 
247
  ## License
248
+ * The license for the original implementation of DDRNet23-Slim can be found
249
+ [here](https://github.com/chenjun2hao/DDRNet.pytorch/blob/main/LICENSE).
250
  * 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)
251
 
252