Hugging Face's logo

qualcomm
/
Inception-v3

Image Classification
PyTorch
LiteRT
backbone
android
Model card Files
xet
Community
bhushans commited on
Commit
65c7a58
·
verified ·
1 Parent(s): fb26358

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +42 -25
README.md CHANGED
@@ -35,29 +35,30 @@ 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
- | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.33 ms | 0 - 2 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
39
- | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.411 ms | 0 - 141 MB | FP16 | NPU | [Inception-v3.so](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.so) |
40
- | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.761 ms | 0 - 50 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
41
- | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.999 ms | 0 - 58 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
42
- | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.049 ms | 0 - 18 MB | FP16 | NPU | [Inception-v3.so](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.so) |
43
- | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.289 ms | 0 - 57 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
44
- | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.949 ms | 0 - 22 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
45
- | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.049 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
46
- | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.268 ms | 0 - 24 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
47
- | Inception-v3 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.328 ms | 0 - 2 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
48
- | Inception-v3 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.451 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
49
- | Inception-v3 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.332 ms | 0 - 2 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
50
- | Inception-v3 | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.457 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
51
- | Inception-v3 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 1.329 ms | 0 - 2 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
52
- | Inception-v3 | SA8775 (Proxy) | SA8775P Proxy | QNN | 1.465 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
53
- | Inception-v3 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.332 ms | 0 - 2 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
54
- | Inception-v3 | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.463 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
55
- | Inception-v3 | SA8295P ADP | SA8295P | TFLITE | 2.552 ms | 0 - 22 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
56
- | Inception-v3 | SA8295P ADP | SA8295P | QNN | 2.755 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
57
- | Inception-v3 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.103 ms | 0 - 56 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
58
- | Inception-v3 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.183 ms | 0 - 19 MB | FP16 | NPU | Use Export Script |
59
- | Inception-v3 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.501 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
60
- | Inception-v3 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.659 ms | 48 - 48 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
 
61
 
62
 
63
 
@@ -122,7 +123,7 @@ Inception-v3
122
  Device : Samsung Galaxy S23 (13)
123
  Runtime : TFLITE
124
  Estimated inference time (ms) : 1.3
125
- Estimated peak memory usage (MB): [0, 2]
126
  Total # Ops : 129
127
  Compute Unit(s) : NPU (129 ops)
128
  ```
@@ -143,13 +144,29 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
143
  import torch
144
 
145
  import qai_hub as hub
146
- from qai_hub_models.models.inception_v3 import
147
 
148
  # Load the model
 
149
 
150
  # Device
151
  device = hub.Device("Samsung Galaxy S23")
152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
153
 
154
  ```
155
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.329 ms | 0 - 191 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
39
+ | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.407 ms | 0 - 141 MB | FP16 | NPU | [Inception-v3.so](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.so) |
40
+ | Inception-v3 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.745 ms | 0 - 563 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
41
+ | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.993 ms | 0 - 19 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
42
+ | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.052 ms | 0 - 19 MB | FP16 | NPU | [Inception-v3.so](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.so) |
43
+ | Inception-v3 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.283 ms | 0 - 57 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
44
+ | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.845 ms | 0 - 16 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
45
+ | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.003 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
46
+ | Inception-v3 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.261 ms | 0 - 25 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
47
+ | Inception-v3 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.329 ms | 0 - 191 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
48
+ | Inception-v3 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.45 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
49
+ | Inception-v3 | SA7255P ADP | SA7255P | TFLITE | 58.004 ms | 0 - 14 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
50
+ | Inception-v3 | SA7255P ADP | SA7255P | QNN | 58.269 ms | 1 - 6 MB | FP16 | NPU | Use Export Script |
51
+ | Inception-v3 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.334 ms | 0 - 191 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
52
+ | Inception-v3 | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.458 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
53
+ | Inception-v3 | SA8295P ADP | SA8295P | TFLITE | 2.558 ms | 0 - 14 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
54
+ | Inception-v3 | SA8295P ADP | SA8295P | QNN | 2.842 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
55
+ | Inception-v3 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.335 ms | 0 - 191 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
56
+ | Inception-v3 | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.471 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
57
+ | Inception-v3 | SA8775P ADP | SA8775P | QNN | 2.864 ms | 1 - 6 MB | FP16 | NPU | Use Export Script |
58
+ | Inception-v3 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.155 ms | 0 - 22 MB | FP16 | NPU | [Inception-v3.tflite](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.tflite) |
59
+ | Inception-v3 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.189 ms | 1 - 17 MB | FP16 | NPU | Use Export Script |
60
+ | Inception-v3 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.487 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
61
+ | Inception-v3 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.656 ms | 49 - 49 MB | FP16 | NPU | [Inception-v3.onnx](https://huggingface.co/qualcomm/Inception-v3/blob/main/Inception-v3.onnx) |
62
 
63
 
64
 
 
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
  Estimated inference time (ms) : 1.3
126
+ Estimated peak memory usage (MB): [0, 191]
127
  Total # Ops : 129
128
  Compute Unit(s) : NPU (129 ops)
129
  ```
 
144
  import torch
145
 
146
  import qai_hub as hub
147
+ from qai_hub_models.models.inception_v3 import Model
148
 
149
  # Load the model
150
+ torch_model = Model.from_pretrained()
151
 
152
  # Device
153
  device = hub.Device("Samsung Galaxy S23")
154
 
155
+ # Trace model
156
+ input_shape = torch_model.get_input_spec()
157
+ sample_inputs = torch_model.sample_inputs()
158
+
159
+ pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
160
+
161
+ # Compile model on a specific device
162
+ compile_job = hub.submit_compile_job(
163
+ model=pt_model,
164
+ device=device,
165
+ input_specs=torch_model.get_input_spec(),
166
+ )
167
+
168
+ # Get target model to run on-device
169
+ target_model = compile_job.get_target_model()
170
 
171
  ```
172