Hugging Face's logo

qualcomm
/
EfficientNet-V2-s

Image Classification
PyTorch
TF Lite
ONNX
backbone
android
Model card Files Community
qaihm-bot commited on
Commit
96e9827
·
verified ·
1 Parent(s): 90d77c7

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +19 -18
README.md CHANGED
@@ -35,29 +35,29 @@ 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
- | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.761 ms | 0 - 222 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
39
- | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.881 ms | 0 - 171 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
40
- | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.843 ms | 0 - 190 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
41
- | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.056 ms | 0 - 30 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
42
- | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.118 ms | 1 - 29 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
43
- | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.216 ms | 0 - 39 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
44
- | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.682 ms | 0 - 32 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
45
- | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.683 ms | 1 - 31 MB | FP16 | NPU | Use Export Script |
46
- | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.028 ms | 0 - 35 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
47
- | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.768 ms | 0 - 223 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
48
- | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.754 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
49
- | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.204 ms | 0 - 38 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
50
- | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.337 ms | 1 - 34 MB | FP16 | NPU | Use Export Script |
51
- | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.032 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
52
- | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.049 ms | 48 - 48 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
53
 
54
 
55
 
56
 
57
  ## Installation
58
 
59
- This model can be installed as a Python package via pip.
60
 
 
61
  ```bash
62
  pip install qai-hub-models
63
  ```
@@ -141,7 +141,7 @@ from qai_hub_models.models.efficientnet_v2_s import Model
141
  torch_model = Model.from_pretrained()
142
 
143
  # Device
144
- device = hub.Device("Samsung Galaxy S23")
145
 
146
  # Trace model
147
  input_shape = torch_model.get_input_spec()
@@ -233,7 +233,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
233
 
234
 
235
  ## License
236
- * The license for the original implementation of EfficientNet-V2-s can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
 
237
  * 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)
238
 
239
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.77 ms | 0 - 222 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
39
+ | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.882 ms | 0 - 171 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
40
+ | EfficientNet-V2-s | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.962 ms | 0 - 189 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
41
+ | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.055 ms | 0 - 29 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
42
+ | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.104 ms | 1 - 31 MB | FP16 | NPU | [EfficientNet-V2-s.so](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.so) |
43
+ | EfficientNet-V2-s | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.186 ms | 0 - 41 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
44
+ | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.638 ms | 0 - 32 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
45
+ | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.98 ms | 1 - 30 MB | FP16 | NPU | Use Export Script |
46
+ | EfficientNet-V2-s | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.083 ms | 1 - 37 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
47
+ | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.762 ms | 0 - 223 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
48
+ | EfficientNet-V2-s | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.766 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
49
+ | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.223 ms | 0 - 39 MB | FP16 | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
50
+ | EfficientNet-V2-s | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.41 ms | 1 - 38 MB | FP16 | NPU | Use Export Script |
51
+ | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.035 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
52
+ | EfficientNet-V2-s | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.078 ms | 49 - 49 MB | FP16 | NPU | [EfficientNet-V2-s.onnx](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx) |
53
 
54
 
55
 
56
 
57
  ## Installation
58
 
 
59
 
60
+ Install the package via pip:
61
  ```bash
62
  pip install qai-hub-models
63
  ```
 
141
  torch_model = Model.from_pretrained()
142
 
143
  # Device
144
+ device = hub.Device("Samsung Galaxy S24")
145
 
146
  # Trace model
147
  input_shape = torch_model.get_input_spec()
 
233
 
234
 
235
  ## License
236
+ * The license for the original implementation of EfficientNet-V2-s can be found
237
+ [here](https://github.com/pytorch/vision/blob/main/LICENSE).
238
  * 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)
239
 
240