qaihm-bot commited on
Commit
a9a687f
·
verified ·
1 Parent(s): d39ce1a

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

FastSam-S_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4d9adcd77029f344c6f87a1637a19d3e9b2d56fecadbab891a6af53223eec09
3
- size 47469460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17aadba2bf68763a28ae6764ba88b8f79895d36d01196a6395ed9d580140903
3
+ size 47486756
FastSam-S_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9702d2e2a20ca825d6d22d0c83f7c4b10d369bc5475af1d189001d8f82e680aa
3
- size 39845766
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa192b5a2cf42d70774fc52262f6850a5ad0565efb62ca6f3c76cff57588510f
3
+ size 39846861
FastSam-S_float.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c41438aefb63ed6bfb8e9fa5d7ebf1dfccd0761493e218015c109588a0fb70e
3
- size 47282796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5f404d40a0be98aae9be2140e64a9d7e91d750e7bbcb598b8f0890b4f5bd4b
3
+ size 47288960
README.md CHANGED
@@ -36,36 +36,33 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | FastSam-S | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 38.561 ms | 4 - 51 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
40
- | FastSam-S | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 37.961 ms | 0 - 70 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
41
- | FastSam-S | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.397 ms | 4 - 63 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
42
- | FastSam-S | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 15.787 ms | 4 - 45 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
43
- | FastSam-S | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 6.973 ms | 4 - 28 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
44
- | FastSam-S | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 6.982 ms | 5 - 22 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
45
- | FastSam-S | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.496 ms | 0 - 81 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
46
- | FastSam-S | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.089 ms | 4 - 52 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
47
- | FastSam-S | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 10.784 ms | 2 - 82 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
48
- | FastSam-S | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 38.561 ms | 4 - 51 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
49
- | FastSam-S | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 37.961 ms | 0 - 70 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
50
- | FastSam-S | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 7.251 ms | 4 - 30 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
51
- | FastSam-S | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.992 ms | 5 - 24 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
52
- | FastSam-S | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 14.685 ms | 4 - 53 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
53
- | FastSam-S | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 13.564 ms | 0 - 43 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
54
- | FastSam-S | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 7.269 ms | 4 - 29 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
55
- | FastSam-S | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 7.004 ms | 5 - 26 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
56
- | FastSam-S | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 11.089 ms | 4 - 52 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
57
- | FastSam-S | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 10.784 ms | 2 - 82 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
58
- | FastSam-S | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.265 ms | 4 - 30 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
59
- | FastSam-S | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 7.107 ms | 5 - 21 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
60
- | FastSam-S | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 8.438 ms | 0 - 83 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
61
- | FastSam-S | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.426 ms | 3 - 66 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
62
- | FastSam-S | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.27 ms | 5 - 100 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
63
- | FastSam-S | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.105 ms | 15 - 93 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
64
- | FastSam-S | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.88 ms | 4 - 56 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
65
- | FastSam-S | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.888 ms | 5 - 81 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
66
- | FastSam-S | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.543 ms | 16 - 89 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
67
- | FastSam-S | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 7.587 ms | 5 - 5 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
68
- | FastSam-S | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.68 ms | 20 - 20 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
69
 
70
 
71
 
@@ -147,7 +144,7 @@ from qai_hub_models.models.fastsam_s import Model
147
  torch_model = Model.from_pretrained()
148
 
149
  # Device
150
- device = hub.Device("Samsung Galaxy S24")
151
 
152
  # Trace model
153
  input_shape = torch_model.get_input_spec()
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | FastSam-S | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 38.431 ms | 4 - 82 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
40
+ | FastSam-S | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 37.78 ms | 1 - 112 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
41
+ | FastSam-S | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 12.765 ms | 4 - 64 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
42
+ | FastSam-S | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 16.067 ms | 4 - 43 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
43
+ | FastSam-S | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.178 ms | 4 - 45 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
44
+ | FastSam-S | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 6.907 ms | 5 - 41 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
45
+ | FastSam-S | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.527 ms | 0 - 106 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
46
+ | FastSam-S | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.013 ms | 4 - 82 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
47
+ | FastSam-S | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 10.871 ms | 1 - 119 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
48
+ | FastSam-S | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 38.431 ms | 4 - 82 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
49
+ | FastSam-S | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 37.78 ms | 1 - 112 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
50
+ | FastSam-S | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 7.16 ms | 4 - 41 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
51
+ | FastSam-S | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.92 ms | 5 - 20 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
52
+ | FastSam-S | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 14.352 ms | 4 - 54 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
53
+ | FastSam-S | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 12.87 ms | 4 - 42 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
54
+ | FastSam-S | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 7.144 ms | 4 - 43 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
55
+ | FastSam-S | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 6.957 ms | 5 - 33 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
56
+ | FastSam-S | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 11.013 ms | 4 - 82 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
57
+ | FastSam-S | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 10.871 ms | 1 - 119 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
58
+ | FastSam-S | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.397 ms | 3 - 97 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
59
+ | FastSam-S | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.2 ms | 5 - 175 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
60
+ | FastSam-S | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.164 ms | 14 - 150 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
61
+ | FastSam-S | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 4.042 ms | 3 - 89 MB | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) |
62
+ | FastSam-S | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 3.966 ms | 5 - 112 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
63
+ | FastSam-S | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.887 ms | 9 - 127 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
64
+ | FastSam-S | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 7.61 ms | 44 - 44 MB | NPU | [FastSam-S.dlc](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.dlc) |
65
+ | FastSam-S | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.83 ms | 20 - 20 MB | NPU | [FastSam-S.onnx.zip](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.onnx.zip) |
 
 
 
66
 
67
 
68
 
 
144
  torch_model = Model.from_pretrained()
145
 
146
  # Device
147
+ device = hub.Device("Samsung Galaxy S25")
148
 
149
  # Trace model
150
  input_shape = torch_model.get_input_spec()
precompiled/qualcomm-snapdragon-x-elite/FastSam-S_float.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d57e0195a1fef721258aaf73c68ff44fd6b3dad0becf16bdc0739d0f1f00a3a2
3
- size 25096192
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/FastSam-S_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c209711074c1de8d78aad6b30b01c24d6437022cea571046430b8718d4788a9a
3
- size 22354421
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- precompiled_qnn_onnx:
3
- qairt: 2.36.4.250725200057_123280
 
 
 
 
tool-versions.yaml CHANGED
@@ -1,4 +1,4 @@
1
  tool_versions:
2
  onnx:
3
- qairt: 2.36.4.250725200057_123280
4
  onnx_runtime: 1.22.2
 
1
  tool_versions:
2
  onnx:
3
+ qairt: 2.37.1.250807093845_124904
4
  onnx_runtime: 1.22.2