Hugging Face's logo

qualcomm
/
DeepLabV3-Plus-MobileNet

Image Segmentation
PyTorch
LiteRT
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
1af0e40
·
verified ·
1 Parent(s): 9bc9886

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +31 -30
README.md CHANGED
@@ -35,39 +35,39 @@ 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-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 13.705 ms | 0 - 17 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
39
- | DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 13.878 ms | 3 - 17 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) |
40
- | DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 12.046 ms | 1 - 40 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
41
- | DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 9.541 ms | 0 - 36 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
42
- | DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 9.687 ms | 3 - 39 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) |
43
- | DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 8.624 ms | 2 - 44 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
44
- | DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 9.412 ms | 0 - 32 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
45
- | DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 7.881 ms | 3 - 37 MB | FP16 | NPU | Use Export Script |
46
- | DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 8.291 ms | 3 - 39 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
47
- | DeepLabV3-Plus-MobileNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 13.689 ms | 0 - 20 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
48
- | DeepLabV3-Plus-MobileNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 12.403 ms | 3 - 6 MB | FP16 | NPU | Use Export Script |
49
- | DeepLabV3-Plus-MobileNet | SA7255P ADP | SA7255P | TFLITE | 421.013 ms | 0 - 27 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
50
- | DeepLabV3-Plus-MobileNet | SA7255P ADP | SA7255P | QNN | 417.135 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
51
- | DeepLabV3-Plus-MobileNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 13.695 ms | 0 - 19 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
52
- | DeepLabV3-Plus-MobileNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 12.395 ms | 3 - 6 MB | FP16 | NPU | Use Export Script |
53
- | DeepLabV3-Plus-MobileNet | SA8295P ADP | SA8295P | TFLITE | 22.736 ms | 0 - 33 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
54
- | DeepLabV3-Plus-MobileNet | SA8295P ADP | SA8295P | QNN | 21.07 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
55
- | DeepLabV3-Plus-MobileNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 13.693 ms | 0 - 17 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
56
- | DeepLabV3-Plus-MobileNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 12.433 ms | 3 - 6 MB | FP16 | NPU | Use Export Script |
57
- | DeepLabV3-Plus-MobileNet | SA8775P ADP | SA8775P | TFLITE | 24.792 ms | 0 - 28 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
58
- | DeepLabV3-Plus-MobileNet | SA8775P ADP | SA8775P | QNN | 22.333 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
59
- | DeepLabV3-Plus-MobileNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 19.638 ms | 0 - 34 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
60
- | DeepLabV3-Plus-MobileNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 20.736 ms | 3 - 40 MB | FP16 | NPU | Use Export Script |
61
- | DeepLabV3-Plus-MobileNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 13.062 ms | 3 - 3 MB | FP16 | NPU | Use Export Script |
62
- | DeepLabV3-Plus-MobileNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.646 ms | 13 - 13 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
69
- This model can be installed as a Python package via pip.
70
 
 
71
  ```bash
72
  pip install qai-hub-models
73
  ```
@@ -123,8 +123,8 @@ Profiling Results
123
  DeepLabV3-Plus-MobileNet
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
- Estimated inference time (ms) : 13.7
127
- Estimated peak memory usage (MB): [0, 17]
128
  Total # Ops : 101
129
  Compute Unit(s) : NPU (101 ops)
130
  ```
@@ -151,7 +151,7 @@ from qai_hub_models.models.deeplabv3_plus_mobilenet import Model
151
  torch_model = Model.from_pretrained()
152
 
153
  # Device
154
- device = hub.Device("Samsung Galaxy S23")
155
 
156
  # Trace model
157
  input_shape = torch_model.get_input_spec()
@@ -243,7 +243,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
243
 
244
 
245
  ## License
246
- * The license for the original implementation of DeepLabV3-Plus-MobileNet can be found [here](https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/LICENSE).
 
247
  * 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)
248
 
249
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 13.603 ms | 0 - 20 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
39
+ | DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 13.853 ms | 0 - 18 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) |
40
+ | DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 12.354 ms | 1 - 40 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
41
+ | DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 9.523 ms | 0 - 36 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
42
+ | DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 9.69 ms | 3 - 36 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) |
43
+ | DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 8.267 ms | 3 - 42 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
44
+ | DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 9.424 ms | 0 - 34 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
45
+ | DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 7.884 ms | 3 - 37 MB | FP16 | NPU | Use Export Script |
46
+ | DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 8.436 ms | 3 - 43 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
47
+ | DeepLabV3-Plus-MobileNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 13.654 ms | 0 - 19 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
48
+ | DeepLabV3-Plus-MobileNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 12.323 ms | 3 - 7 MB | FP16 | NPU | Use Export Script |
49
+ | DeepLabV3-Plus-MobileNet | SA7255P ADP | SA7255P | TFLITE | 420.787 ms | 0 - 27 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
50
+ | DeepLabV3-Plus-MobileNet | SA7255P ADP | SA7255P | QNN | 417.038 ms | 3 - 12 MB | FP16 | NPU | Use Export Script |
51
+ | DeepLabV3-Plus-MobileNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 13.696 ms | 0 - 16 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
52
+ | DeepLabV3-Plus-MobileNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 12.41 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
53
+ | DeepLabV3-Plus-MobileNet | SA8295P ADP | SA8295P | TFLITE | 22.723 ms | 0 - 33 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
54
+ | DeepLabV3-Plus-MobileNet | SA8295P ADP | SA8295P | QNN | 20.984 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
55
+ | DeepLabV3-Plus-MobileNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 13.685 ms | 0 - 16 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
56
+ | DeepLabV3-Plus-MobileNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 12.369 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
57
+ | DeepLabV3-Plus-MobileNet | SA8775P ADP | SA8775P | TFLITE | 24.776 ms | 0 - 27 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
58
+ | DeepLabV3-Plus-MobileNet | SA8775P ADP | SA8775P | QNN | 22.261 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
59
+ | DeepLabV3-Plus-MobileNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 19.736 ms | 0 - 33 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
60
+ | DeepLabV3-Plus-MobileNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 20.656 ms | 3 - 38 MB | FP16 | NPU | Use Export Script |
61
+ | DeepLabV3-Plus-MobileNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 13.015 ms | 3 - 3 MB | FP16 | NPU | Use Export Script |
62
+ | DeepLabV3-Plus-MobileNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.574 ms | 12 - 12 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
63
 
64
 
65
 
66
 
67
  ## Installation
68
 
 
69
 
70
+ Install the package via pip:
71
  ```bash
72
  pip install qai-hub-models
73
  ```
 
123
  DeepLabV3-Plus-MobileNet
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
+ Estimated inference time (ms) : 13.6
127
+ Estimated peak memory usage (MB): [0, 20]
128
  Total # Ops : 101
129
  Compute Unit(s) : NPU (101 ops)
130
  ```
 
151
  torch_model = Model.from_pretrained()
152
 
153
  # Device
154
+ device = hub.Device("Samsung Galaxy S24")
155
 
156
  # Trace model
157
  input_shape = torch_model.get_input_spec()
 
243
 
244
 
245
  ## License
246
+ * The license for the original implementation of DeepLabV3-Plus-MobileNet can be found
247
+ [here](https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/LICENSE).
248
  * 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)
249
 
250