Hugging Face's logo

qualcomm
/
DeepLabV3-ResNet50

Image Segmentation
PyTorch
LiteRT
android
Model card Files Community
qaihm-bot commited on
Commit
9080abd
·
verified ·
1 Parent(s): aa7c317

v0.30.2

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.30.2 for changelog.

Files changed (2) hide show
  1. DeepLabV3-ResNet50.so +0 -3
  2. README.md +14 -14
DeepLabV3-ResNet50.so DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:87b9214b80c944a6cd281c09ac310a0565fd6c1658103de124d1f5c341d33730
3
- size 159083080
 
 
 
 
README.md CHANGED
@@ -35,18 +35,18 @@ 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
- | DeepLabV3-ResNet50 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 1567.599 ms | 21 - 41 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
39
- | DeepLabV3-ResNet50 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 453.237 ms | 23 - 53 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
40
- | DeepLabV3-ResNet50 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 317.153 ms | 0 - 199 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
41
- | DeepLabV3-ResNet50 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 593.132 ms | 23 - 39 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
42
- | DeepLabV3-ResNet50 | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 1567.599 ms | 21 - 41 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
43
- | DeepLabV3-ResNet50 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 292.309 ms | 0 - 167 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
44
- | DeepLabV3-ResNet50 | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 266.633 ms | 22 - 43 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
45
- | DeepLabV3-ResNet50 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 293.043 ms | 0 - 205 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
46
- | DeepLabV3-ResNet50 | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 593.132 ms | 23 - 39 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
47
- | DeepLabV3-ResNet50 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 592.51 ms | 2 - 189 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
48
- | DeepLabV3-ResNet50 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 214.819 ms | 22 - 52 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
49
- | DeepLabV3-ResNet50 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 222.349 ms | 21 - 40 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
50
 
51
 
52
 
@@ -110,8 +110,8 @@ Profiling Results
110
  DeepLabV3-ResNet50
111
  Device : cs_8275 (ANDROID 14)
112
  Runtime : TFLITE
113
- Estimated inference time (ms) : 1567.6
114
- Estimated peak memory usage (MB): [21, 41]
115
  Total # Ops : 100
116
  Compute Unit(s) : npu (0 ops) gpu (98 ops) cpu (2 ops)
117
  ```
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | DeepLabV3-ResNet50 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 1185.986 ms | 6 - 23 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
39
+ | DeepLabV3-ResNet50 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 786.162 ms | 21 - 51 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
40
+ | DeepLabV3-ResNet50 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 304.269 ms | 3 - 201 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
41
+ | DeepLabV3-ResNet50 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 718.986 ms | 23 - 39 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
42
+ | DeepLabV3-ResNet50 | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 1185.986 ms | 6 - 23 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
43
+ | DeepLabV3-ResNet50 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 293.789 ms | 0 - 210 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
44
+ | DeepLabV3-ResNet50 | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 266.482 ms | 23 - 44 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
45
+ | DeepLabV3-ResNet50 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 292.485 ms | 2 - 190 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
46
+ | DeepLabV3-ResNet50 | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 718.986 ms | 23 - 39 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
47
+ | DeepLabV3-ResNet50 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 294.648 ms | 2 - 210 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
48
+ | DeepLabV3-ResNet50 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 264.494 ms | 21 - 49 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
49
+ | DeepLabV3-ResNet50 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 187.222 ms | 23 - 44 MB | GPU | [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) |
50
 
51
 
52
 
 
110
  DeepLabV3-ResNet50
111
  Device : cs_8275 (ANDROID 14)
112
  Runtime : TFLITE
113
+ Estimated inference time (ms) : 1186.0
114
+ Estimated peak memory usage (MB): [6, 23]
115
  Total # Ops : 100
116
  Compute Unit(s) : npu (0 ops) gpu (98 ops) cpu (2 ops)
117
  ```