Image Classification
PyTorch
bu_auto
android
qaihm-bot commited on
Commit
0e29ebd
·
verified ·
1 Parent(s): 3cb1514

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

Files changed (3) hide show
  1. LeViT.onnx +1 -1
  2. LeViT_w8a16.onnx +2 -2
  3. README.md +19 -19
LeViT.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:009b2b3f1732468ad0c637e241c92621c39b13c8ac5ac8cba4159c78cc6d41d7
3
  size 31632321
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e5d5cf53d475d406b48c8119c38b0ee8479532f57ffc3ae9fca96ac6b7a7aa
3
  size 31632321
LeViT_w8a16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0d937858241031ff95f3fc20698764dc0d71ce5e8a6b2051d59220b76117706
3
- size 32278091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:842e3f7af4fa6403f67b992918de6dfa9190b13dc341317f533fa0c68c0aeeec
3
+ size 32333398
README.md CHANGED
@@ -34,21 +34,21 @@ More details on model performance across various devices, can be found
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | LeViT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3.342 ms | 0 - 37 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
38
- | LeViT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.47 ms | 0 - 48 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
39
- | LeViT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.094 ms | 0 - 76 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
40
- | LeViT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.593 ms | 0 - 39 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
41
- | LeViT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.092 ms | 0 - 69 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
42
- | LeViT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1.686 ms | 0 - 50 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
43
- | LeViT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.793 ms | 0 - 48 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
44
- | LeViT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.099 ms | 0 - 49 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
45
- | LeViT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.629 ms | 0 - 42 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
46
- | LeViT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.167 ms | 1 - 43 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
47
- | LeViT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.711 ms | 16 - 16 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
48
- | LeViT | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 17.214 ms | 2 - 19 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
49
- | LeViT | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 12.995 ms | 0 - 29 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
50
- | LeViT | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 11.172 ms | 2 - 25 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
51
- | LeViT | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 15.704 ms | 8 - 8 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
52
 
53
 
54
 
@@ -112,8 +112,8 @@ Profiling Results
112
  LeViT
113
  Device : cs_8275 (ANDROID 14)
114
  Runtime : TFLITE
115
- Estimated inference time (ms) : 3.3
116
- Estimated peak memory usage (MB): [0, 37]
117
  Total # Ops : 306
118
  Compute Unit(s) : npu (306 ops) gpu (0 ops) cpu (0 ops)
119
  ```
@@ -202,13 +202,13 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
202
  You can also run the demo on-device.
203
 
204
  ```bash
205
- python -m qai_hub_models.models.levit.demo --on-device
206
  ```
207
 
208
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
209
  environment, please add the following to your cell (instead of the above).
210
  ```
211
- %run -m qai_hub_models.models.levit.demo -- --on-device
212
  ```
213
 
214
 
 
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | LeViT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 13.633 ms | 0 - 38 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
38
+ | LeViT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.336 ms | 0 - 49 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
39
+ | LeViT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.093 ms | 0 - 91 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
40
+ | LeViT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.56 ms | 0 - 42 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
41
+ | LeViT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.092 ms | 0 - 93 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
42
+ | LeViT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1.637 ms | 0 - 48 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
43
+ | LeViT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.771 ms | 0 - 56 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
44
+ | LeViT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.096 ms | 0 - 54 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
45
+ | LeViT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.761 ms | 0 - 49 MB | NPU | [LeViT.tflite](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.tflite) |
46
+ | LeViT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.0 ms | 1 - 44 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
47
+ | LeViT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.725 ms | 16 - 16 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT.onnx) |
48
+ | LeViT | w8a16 | Samsung Galaxy S23 | Snapdragon�� 8 Gen 2 Mobile | ONNX | 16.899 ms | 2 - 19 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
49
+ | LeViT | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 14.304 ms | 2 - 32 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
50
+ | LeViT | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 12.893 ms | 3 - 22 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
51
+ | LeViT | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 15.395 ms | 8 - 8 MB | NPU | [LeViT.onnx](https://huggingface.co/qualcomm/LeViT/blob/main/LeViT_w8a16.onnx) |
52
 
53
 
54
 
 
112
  LeViT
113
  Device : cs_8275 (ANDROID 14)
114
  Runtime : TFLITE
115
+ Estimated inference time (ms) : 13.6
116
+ Estimated peak memory usage (MB): [0, 38]
117
  Total # Ops : 306
118
  Compute Unit(s) : npu (306 ops) gpu (0 ops) cpu (0 ops)
119
  ```
 
202
  You can also run the demo on-device.
203
 
204
  ```bash
205
+ python -m qai_hub_models.models.levit.demo --eval-mode on-device
206
  ```
207
 
208
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
209
  environment, please add the following to your cell (instead of the above).
210
  ```
211
+ %run -m qai_hub_models.models.levit.demo -- --eval-mode on-device
212
  ```
213
 
214