Hugging Face's logo

qualcomm
/
EfficientNet-B4

Image Classification
PyTorch
LiteRT
backbone
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
19685ae
·
verified ·
1 Parent(s): 7c51a3a

v0.30.5

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

Files changed (1) hide show
  1. README.md +31 -31
README.md CHANGED
@@ -35,34 +35,34 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.221 ms | 0 - 61 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
39
- | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 11.894 ms | 1 - 10 MB | NPU | Use Export Script |
40
- | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 7.285 ms | 0 - 78 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
41
- | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 8.057 ms | 1 - 47 MB | NPU | Use Export Script |
42
- | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.329 ms | 0 - 386 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
43
- | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.16 ms | 1 - 3 MB | NPU | Use Export Script |
44
- | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.366 ms | 0 - 62 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
45
- | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 4.178 ms | 1 - 14 MB | NPU | Use Export Script |
46
- | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 3.315 ms | 0 - 385 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
47
- | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.197 ms | 0 - 25 MB | NPU | Use Export Script |
48
- | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.251 ms | 0 - 101 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
49
- | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.451 ms | 0 - 77 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
50
- | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.341 ms | 1 - 49 MB | NPU | Use Export Script |
51
- | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.416 ms | 0 - 54 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
52
- | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.936 ms | 0 - 64 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
53
- | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.171 ms | 1 - 35 MB | NPU | Use Export Script |
54
- | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.266 ms | 0 - 37 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
55
- | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.468 ms | 1 - 1 MB | NPU | Use Export Script |
56
- | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.462 ms | 45 - 45 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
57
- | EfficientNet-B4 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 6.53 ms | 0 - 10 MB | NPU | Use Export Script |
58
- | EfficientNet-B4 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 4.433 ms | 0 - 61 MB | NPU | Use Export Script |
59
- | EfficientNet-B4 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.425 ms | 0 - 3 MB | NPU | Use Export Script |
60
- | EfficientNet-B4 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 3.856 ms | 0 - 15 MB | NPU | Use Export Script |
61
- | EfficientNet-B4 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 11.665 ms | 0 - 14 MB | NPU | Use Export Script |
62
- | EfficientNet-B4 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.423 ms | 0 - 18 MB | NPU | Use Export Script |
63
- | EfficientNet-B4 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.277 ms | 0 - 66 MB | NPU | Use Export Script |
64
- | EfficientNet-B4 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.941 ms | 0 - 54 MB | NPU | Use Export Script |
65
- | EfficientNet-B4 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.762 ms | 0 - 0 MB | NPU | Use Export Script |
66
 
67
 
68
 
@@ -127,7 +127,7 @@ EfficientNet-B4
127
  Device : cs_8275 (ANDROID 14)
128
  Runtime : TFLITE
129
  Estimated inference time (ms) : 12.2
130
- Estimated peak memory usage (MB): [0, 61]
131
  Total # Ops : 482
132
  Compute Unit(s) : npu (482 ops) gpu (0 ops) cpu (0 ops)
133
  ```
@@ -216,13 +216,13 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
216
  You can also run the demo on-device.
217
 
218
  ```bash
219
- python -m qai_hub_models.models.efficientnet_b4.demo --on-device
220
  ```
221
 
222
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
223
  environment, please add the following to your cell (instead of the above).
224
  ```
225
- %run -m qai_hub_models.models.efficientnet_b4.demo -- --on-device
226
  ```
227
 
228
 
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.165 ms | 0 - 67 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
39
+ | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 11.876 ms | 1 - 10 MB | NPU | Use Export Script |
40
+ | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.908 ms | 0 - 85 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
41
+ | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 7.7 ms | 1 - 47 MB | NPU | Use Export Script |
42
+ | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.301 ms | 0 - 423 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
43
+ | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.159 ms | 1 - 2 MB | NPU | Use Export Script |
44
+ | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.352 ms | 0 - 66 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
45
+ | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 4.185 ms | 1 - 11 MB | NPU | Use Export Script |
46
+ | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 3.326 ms | 0 - 423 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
47
+ | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.191 ms | 1 - 91 MB | NPU | Use Export Script |
48
+ | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.265 ms | 0 - 103 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
49
+ | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.442 ms | 0 - 85 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
50
+ | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.362 ms | 1 - 48 MB | NPU | Use Export Script |
51
+ | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.394 ms | 0 - 53 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
52
+ | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.337 ms | 0 - 70 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
53
+ | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.18 ms | 1 - 37 MB | NPU | Use Export Script |
54
+ | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.294 ms | 0 - 39 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
55
+ | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.459 ms | 1 - 1 MB | NPU | Use Export Script |
56
+ | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.456 ms | 45 - 45 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
57
+ | EfficientNet-B4 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 16.76 ms | 0 - 10 MB | NPU | Use Export Script |
58
+ | EfficientNet-B4 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 4.181 ms | 0 - 64 MB | NPU | Use Export Script |
59
+ | EfficientNet-B4 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.412 ms | 0 - 4 MB | NPU | Use Export Script |
60
+ | EfficientNet-B4 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 3.811 ms | 0 - 10 MB | NPU | Use Export Script |
61
+ | EfficientNet-B4 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 11.757 ms | 0 - 12 MB | NPU | Use Export Script |
62
+ | EfficientNet-B4 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.437 ms | 0 - 17 MB | NPU | Use Export Script |
63
+ | EfficientNet-B4 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.275 ms | 0 - 76 MB | NPU | Use Export Script |
64
+ | EfficientNet-B4 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.603 ms | 0 - 57 MB | NPU | Use Export Script |
65
+ | EfficientNet-B4 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.776 ms | 0 - 0 MB | NPU | Use Export Script |
66
 
67
 
68
 
 
127
  Device : cs_8275 (ANDROID 14)
128
  Runtime : TFLITE
129
  Estimated inference time (ms) : 12.2
130
+ Estimated peak memory usage (MB): [0, 67]
131
  Total # Ops : 482
132
  Compute Unit(s) : npu (482 ops) gpu (0 ops) cpu (0 ops)
133
  ```
 
216
  You can also run the demo on-device.
217
 
218
  ```bash
219
+ python -m qai_hub_models.models.efficientnet_b4.demo --eval-mode on-device
220
  ```
221
 
222
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
223
  environment, please add the following to your cell (instead of the above).
224
  ```
225
+ %run -m qai_hub_models.models.efficientnet_b4.demo -- --eval-mode on-device
226
  ```
227
 
228