Hugging Face's logo

qualcomm
/
Shufflenet-v2Quantized

Image Classification
PyTorch
TF Lite
ONNX
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
202d6a9
·
verified ·
1 Parent(s): 7546985

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +48 -30
README.md CHANGED
@@ -35,32 +35,34 @@ 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
- | Shufflenet-v2Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.609 ms | 0 - 1 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
39
- | Shufflenet-v2Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.592 ms | 0 - 4 MB | INT8 | NPU | [Shufflenet-v2Quantized.so](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.so) |
40
- | Shufflenet-v2Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 13.536 ms | 0 - 12 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
41
- | Shufflenet-v2Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.433 ms | 0 - 27 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
42
- | Shufflenet-v2Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.427 ms | 0 - 14 MB | INT8 | NPU | [Shufflenet-v2Quantized.so](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.so) |
43
- | Shufflenet-v2Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 11.339 ms | 2 - 483 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
44
- | Shufflenet-v2Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.472 ms | 0 - 20 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
45
- | Shufflenet-v2Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.379 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
46
- | Shufflenet-v2Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 12.276 ms | 2 - 452 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
47
- | Shufflenet-v2Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.905 ms | 0 - 21 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
48
- | Shufflenet-v2Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.15 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
49
- | Shufflenet-v2Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 9.722 ms | 0 - 5 MB | FP32 | CPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
50
- | Shufflenet-v2Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.613 ms | 0 - 1 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
51
- | Shufflenet-v2Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.54 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
52
- | Shufflenet-v2Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.612 ms | 0 - 11 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
53
- | Shufflenet-v2Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.544 ms | 2 - 3 MB | INT8 | NPU | Use Export Script |
54
- | Shufflenet-v2Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.614 ms | 0 - 1 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
55
- | Shufflenet-v2Quantized | SA8775 (Proxy) | SA8775P Proxy | QNN | 0.541 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
56
- | Shufflenet-v2Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.612 ms | 0 - 2 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
57
- | Shufflenet-v2Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.545 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
58
- | Shufflenet-v2Quantized | SA8295P ADP | SA8295P | TFLITE | 0.964 ms | 0 - 19 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
59
- | Shufflenet-v2Quantized | SA8295P ADP | SA8295P | QNN | 0.999 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
60
- | Shufflenet-v2Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.648 ms | 0 - 29 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
61
- | Shufflenet-v2Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.636 ms | 0 - 16 MB | INT8 | NPU | Use Export Script |
62
- | Shufflenet-v2Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.673 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
63
- | Shufflenet-v2Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 15.566 ms | 10 - 10 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
 
 
64
 
65
 
66
 
@@ -125,9 +127,9 @@ Shufflenet-v2Quantized
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
  Estimated inference time (ms) : 0.6
128
- Estimated peak memory usage (MB): [0, 1]
129
- Total # Ops : 233
130
- Compute Unit(s) : NPU (233 ops)
131
  ```
132
 
133
 
@@ -146,13 +148,29 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
146
  import torch
147
 
148
  import qai_hub as hub
149
- from qai_hub_models.models.shufflenet_v2_quantized import
150
 
151
  # Load the model
 
152
 
153
  # Device
154
  device = hub.Device("Samsung Galaxy S23")
155
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
156
 
157
  ```
158
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Shufflenet-v2Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.631 ms | 0 - 8 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
39
+ | Shufflenet-v2Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.593 ms | 0 - 8 MB | INT8 | NPU | [Shufflenet-v2Quantized.so](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.so) |
40
+ | Shufflenet-v2Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 14.988 ms | 2 - 64 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
41
+ | Shufflenet-v2Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.437 ms | 0 - 14 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
42
+ | Shufflenet-v2Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.426 ms | 0 - 15 MB | INT8 | NPU | [Shufflenet-v2Quantized.so](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.so) |
43
+ | Shufflenet-v2Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 12.068 ms | 2 - 464 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
44
+ | Shufflenet-v2Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.482 ms | 0 - 11 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
45
+ | Shufflenet-v2Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.463 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
46
+ | Shufflenet-v2Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 12.977 ms | 2 - 420 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
47
+ | Shufflenet-v2Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.911 ms | 0 - 13 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
48
+ | Shufflenet-v2Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.119 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
49
+ | Shufflenet-v2Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 9.77 ms | 0 - 5 MB | FP32 | CPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
50
+ | Shufflenet-v2Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.632 ms | 0 - 8 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
51
+ | Shufflenet-v2Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.539 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
52
+ | Shufflenet-v2Quantized | SA7255P ADP | SA7255P | TFLITE | 1.605 ms | 0 - 11 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
53
+ | Shufflenet-v2Quantized | SA7255P ADP | SA7255P | QNN | 1.732 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
54
+ | Shufflenet-v2Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.628 ms | 0 - 60 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
55
+ | Shufflenet-v2Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.535 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
56
+ | Shufflenet-v2Quantized | SA8295P ADP | SA8295P | TFLITE | 0.994 ms | 0 - 10 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
57
+ | Shufflenet-v2Quantized | SA8295P ADP | SA8295P | QNN | 0.996 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
58
+ | Shufflenet-v2Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.631 ms | 0 - 8 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
59
+ | Shufflenet-v2Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.538 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
60
+ | Shufflenet-v2Quantized | SA8775P ADP | SA8775P | TFLITE | 1.037 ms | 0 - 9 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
61
+ | Shufflenet-v2Quantized | SA8775P ADP | SA8775P | QNN | 1.037 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
62
+ | Shufflenet-v2Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.672 ms | 0 - 15 MB | INT8 | NPU | [Shufflenet-v2Quantized.tflite](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.tflite) |
63
+ | Shufflenet-v2Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.637 ms | 0 - 16 MB | INT8 | NPU | Use Export Script |
64
+ | Shufflenet-v2Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.978 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
65
+ | Shufflenet-v2Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 18.268 ms | 10 - 10 MB | INT8 | NPU | [Shufflenet-v2Quantized.onnx](https://huggingface.co/qualcomm/Shufflenet-v2Quantized/blob/main/Shufflenet-v2Quantized.onnx) |
66
 
67
 
68
 
 
127
  Device : Samsung Galaxy S23 (13)
128
  Runtime : TFLITE
129
  Estimated inference time (ms) : 0.6
130
+ Estimated peak memory usage (MB): [0, 8]
131
+ Total # Ops : 220
132
+ Compute Unit(s) : NPU (220 ops)
133
  ```
134
 
135
 
 
148
  import torch
149
 
150
  import qai_hub as hub
151
+ from qai_hub_models.models.shufflenet_v2_quantized import Model
152
 
153
  # Load the model
154
+ torch_model = Model.from_pretrained()
155
 
156
  # Device
157
  device = hub.Device("Samsung Galaxy S23")
158
 
159
+ # Trace model
160
+ input_shape = torch_model.get_input_spec()
161
+ sample_inputs = torch_model.sample_inputs()
162
+
163
+ pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
164
+
165
+ # Compile model on a specific device
166
+ compile_job = hub.submit_compile_job(
167
+ model=pt_model,
168
+ device=device,
169
+ input_specs=torch_model.get_input_spec(),
170
+ )
171
+
172
+ # Get target model to run on-device
173
+ target_model = compile_job.get_target_model()
174
 
175
  ```
176