Hugging Face's logo

qualcomm
/
Mask2Former

Image Segmentation
PyTorch
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
3063816
·
verified ·
1 Parent(s): 0a8ef9b

v0.31.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.31.0 for changelog.

Files changed (3) hide show
  1. Mask2Former.onnx +0 -3
  2. Mask2Former.tflite +0 -3
  3. README.md +24 -23
Mask2Former.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:086495902ef46f0c480b178e07059f482d2ae86e80f591db6b6c44674369ca4c
3
- size 210437039
 
 
 
 
Mask2Former.tflite DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbef5537b4d16dcbcffa1d737881870238cf95cb0c3b9141ff64781cbc20e283
3
- size 222266592
 
 
 
 
README.md CHANGED
@@ -35,22 +35,23 @@ 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
- | Mask2Former | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 1890.028 ms | 164 - 178 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
39
- | Mask2Former | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1867.002 ms | 164 - 196 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
40
- | Mask2Former | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1347.193 ms | 163 - 190 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
41
- | Mask2Former | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1590.836 ms | 164 - 179 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
42
- | Mask2Former | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 1890.028 ms | 164 - 178 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
43
- | Mask2Former | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1394.976 ms | 137 - 168 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
44
- | Mask2Former | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1322.242 ms | 164 - 187 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
45
- | Mask2Former | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1424.374 ms | 163 - 168 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
46
- | Mask2Former | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1590.836 ms | 164 - 179 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
47
- | Mask2Former | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1346.481 ms | 164 - 168 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
48
- | Mask2Former | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 918.571 ms | 119 - 139 MB | CPU | [Mask2Former.onnx](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.onnx) |
49
- | Mask2Former | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1238.585 ms | 163 - 192 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
50
- | Mask2Former | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 679.982 ms | 216 - 244 MB | CPU | [Mask2Former.onnx](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.onnx) |
51
- | Mask2Former | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 974.151 ms | 163 - 183 MB | CPU | [Mask2Former.tflite](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.tflite) |
52
- | Mask2Former | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 587.886 ms | 178 - 195 MB | CPU | [Mask2Former.onnx](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.onnx) |
53
- | Mask2Former | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 444.851 ms | 268 - 268 MB | CPU | [Mask2Former.onnx](https://huggingface.co/qualcomm/Mask2Former/blob/main/Mask2Former.onnx) |
 
54
 
55
 
56
 
@@ -113,11 +114,11 @@ Profiling Results
113
  ------------------------------------------------------------
114
  Mask2Former
115
  Device : cs_8275 (ANDROID 14)
116
- Runtime : TFLITE
117
- Estimated inference time (ms) : 1890.0
118
- Estimated peak memory usage (MB): [164, 178]
119
- Total # Ops : 3213
120
- Compute Unit(s) : npu (0 ops) gpu (0 ops) cpu (3213 ops)
121
  ```
122
 
123
 
@@ -204,13 +205,13 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
204
  You can also run the demo on-device.
205
 
206
  ```bash
207
- python -m qai_hub_models.models.mask2former.demo --on-device
208
  ```
209
 
210
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
211
  environment, please add the following to your cell (instead of the above).
212
  ```
213
- %run -m qai_hub_models.models.mask2former.demo -- --on-device
214
  ```
215
 
216
 
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Mask2Former | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 378.098 ms | 2 - 11 MB | NPU | Use Export Script |
39
+ | Mask2Former | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 352.222 ms | 2 - 18 MB | NPU | Use Export Script |
40
+ | Mask2Former | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 217.892 ms | 2 - 4 MB | NPU | Use Export Script |
41
+ | Mask2Former | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 224.361 ms | 2 - 12 MB | NPU | Use Export Script |
42
+ | Mask2Former | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 378.098 ms | 2 - 11 MB | NPU | Use Export Script |
43
+ | Mask2Former | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 217.919 ms | 2 - 4 MB | NPU | Use Export Script |
44
+ | Mask2Former | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 288.399 ms | 2 - 17 MB | NPU | Use Export Script |
45
+ | Mask2Former | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 217.23 ms | 2 - 4 MB | NPU | Use Export Script |
46
+ | Mask2Former | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 224.361 ms | 2 - 12 MB | NPU | Use Export Script |
47
+ | Mask2Former | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 217.14 ms | 2 - 5 MB | NPU | Use Export Script |
48
+ | Mask2Former | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 218.642 ms | 0 - 115 MB | NPU | Use Export Script |
49
+ | Mask2Former | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 140.424 ms | 2 - 22 MB | NPU | Use Export Script |
50
+ | Mask2Former | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 140.725 ms | 9 - 29 MB | NPU | Use Export Script |
51
+ | Mask2Former | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 125.966 ms | 2 - 16 MB | NPU | Use Export Script |
52
+ | Mask2Former | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 106.794 ms | 7 - 21 MB | NPU | Use Export Script |
53
+ | Mask2Former | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 224.698 ms | 2 - 2 MB | NPU | Use Export Script |
54
+ | Mask2Former | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 224.493 ms | 108 - 108 MB | NPU | Use Export Script |
55
 
56
 
57
 
 
114
  ------------------------------------------------------------
115
  Mask2Former
116
  Device : cs_8275 (ANDROID 14)
117
+ Runtime : QNN_CONTEXT_BINARY
118
+ Estimated inference time (ms) : 378.1
119
+ Estimated peak memory usage (MB): [2, 11]
120
+ Total # Ops : 1954
121
+ Compute Unit(s) : npu (1954 ops) gpu (0 ops) cpu (0 ops)
122
  ```
123
 
124
 
 
205
  You can also run the demo on-device.
206
 
207
  ```bash
208
+ python -m qai_hub_models.models.mask2former.demo --eval-mode on-device
209
  ```
210
 
211
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
212
  environment, please add the following to your cell (instead of the above).
213
  ```
214
+ %run -m qai_hub_models.models.mask2former.demo -- --eval-mode on-device
215
  ```
216
 
217