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
6879435
·
verified ·
1 Parent(s): 99ccc89

v0.38.0

Browse files

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

Files changed (13) hide show
  1. EfficientNet-B4_float.dlc +2 -2
  2. EfficientNet-B4_float.onnx.zip +2 -2
  3. EfficientNet-B4_w8a16.dlc +2 -2
  4. README.md +26 -30
  5. precompiled/qualcomm-qcs6490-proxy/EfficientNet-B4_w8a16.bin +0 -3
  6. precompiled/qualcomm-qcs6490-proxy/EfficientNet-B4_w8a16.onnx.zip +0 -3
  7. precompiled/qualcomm-qcs6490-proxy/tool-versions.yaml +0 -3
  8. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_float.bin +0 -3
  9. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_float.onnx.zip +0 -3
  10. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_w8a16.bin +0 -3
  11. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_w8a16.onnx.zip +0 -3
  12. precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml +0 -3
  13. tool-versions.yaml +1 -1
EfficientNet-B4_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bf2031117f0a204b006f622fab936fd7ad65d256e9a6685224839235c98e982
3
- size 77622036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0997f1d4873395eda2cdf5518eb5207c6ac67d3870347eef5060993da9fce91
3
+ size 77622124
EfficientNet-B4_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4067bbe58482138ce55e619f297728450ae91ed7162f9aae84474817f370084
3
- size 72008560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0feb34adcb8e8f1410e29fac0d192da9baa4c0284bfe4e8cd034d69f945de7
3
+ size 72008668
EfficientNet-B4_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:877e6a36ff14495e3ada6e120f36be92016c98f94143bedbc99cde344f7ebff2
3
- size 25226828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18eb6d2425367ee764d60f32f04d2724fd05ccbe9083936d6302660ff3ab7cad
3
+ size 25226852
README.md CHANGED
@@ -37,35 +37,31 @@ More details on model performance across various devices, can be found
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
- | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.191 ms | 0 - 67 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
41
- | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 11.848 ms | 1 - 36 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
42
- | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.982 ms | 0 - 90 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
43
- | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.703 ms | 0 - 48 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
44
- | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.329 ms | 0 - 425 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
45
- | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.175 ms | 1 - 17 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
46
- | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 3.151 ms | 0 - 111 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
47
- | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.38 ms | 0 - 67 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
48
- | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.16 ms | 0 - 34 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
49
- | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 3.314 ms | 0 - 415 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
50
- | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.17 ms | 0 - 40 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
51
- | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.196 ms | 0 - 108 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
52
- | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.429 ms | 0 - 86 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
53
- | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.338 ms | 1 - 50 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
54
- | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.394 ms | 0 - 47 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
55
- | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.287 ms | 0 - 71 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
56
- | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.163 ms | 1 - 41 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
57
- | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.276 ms | 1 - 38 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
58
- | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.461 ms | 261 - 261 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
59
- | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.228 ms | 46 - 46 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
60
- | EfficientNet-B4 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.474 ms | 0 - 57 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
61
- | EfficientNet-B4 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.201 ms | 0 - 70 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
62
- | EfficientNet-B4 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.372 ms | 0 - 23 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
63
- | EfficientNet-B4 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.8 ms | 0 - 57 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
64
- | EfficientNet-B4 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 12.863 ms | 0 - 104 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
65
- | EfficientNet-B4 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.415 ms | 0 - 17 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
66
- | EfficientNet-B4 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.269 ms | 0 - 82 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
67
- | EfficientNet-B4 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.594 ms | 0 - 62 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
68
- | EfficientNet-B4 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.741 ms | 105 - 105 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
69
 
70
 
71
 
@@ -147,7 +143,7 @@ from qai_hub_models.models.efficientnet_b4 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()
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.199 ms | 0 - 67 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
41
+ | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 11.778 ms | 1 - 36 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
42
+ | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.873 ms | 0 - 89 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
43
+ | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.679 ms | 1 - 49 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
44
+ | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.306 ms | 0 - 424 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
45
+ | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.152 ms | 0 - 21 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
46
+ | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 3.203 ms | 0 - 108 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
47
+ | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.338 ms | 0 - 67 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
48
+ | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.155 ms | 1 - 36 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
49
+ | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.424 ms | 0 - 83 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_DLC | 2.322 ms | 1 - 52 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
51
+ | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.363 ms | 0 - 50 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
52
+ | EfficientNet-B4 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.946 ms | 0 - 72 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
53
+ | EfficientNet-B4 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.822 ms | 1 - 42 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
54
+ | EfficientNet-B4 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.926 ms | 0 - 40 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
55
+ | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.433 ms | 268 - 268 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
56
+ | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.254 ms | 46 - 46 MB | NPU | [EfficientNet-B4.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx.zip) |
57
+ | EfficientNet-B4 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.533 ms | 0 - 61 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
58
+ | EfficientNet-B4 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.081 ms | 0 - 77 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
59
+ | EfficientNet-B4 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.452 ms | 0 - 16 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
60
+ | EfficientNet-B4 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.844 ms | 0 - 61 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
61
+ | EfficientNet-B4 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 12.933 ms | 0 - 104 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
62
+ | EfficientNet-B4 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.282 ms | 0 - 80 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
63
+ | EfficientNet-B4 | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.601 ms | 0 - 64 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
64
+ | EfficientNet-B4 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.811 ms | 105 - 105 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
 
 
 
 
65
 
66
 
67
 
 
143
  torch_model = Model.from_pretrained()
144
 
145
  # Device
146
+ device = hub.Device("Samsung Galaxy S25")
147
 
148
  # Trace model
149
  input_shape = torch_model.get_input_spec()
precompiled/qualcomm-qcs6490-proxy/EfficientNet-B4_w8a16.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e9f554e1d8c87b397b4324aceeabdd6b6f493ecf20f0060a798b77a35880ef9
3
- size 37965824
 
 
 
 
precompiled/qualcomm-qcs6490-proxy/EfficientNet-B4_w8a16.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ab1a82bf3075f701f5c3a118f0d8478f9f318283737dfcd7cd783f9e454fc7b
3
- size 18727541
 
 
 
 
precompiled/qualcomm-qcs6490-proxy/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- precompiled_qnn_onnx:
3
- qairt: 2.36.4.250725200057_123280
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_float.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:449d1e8eb59efa2299414ec495c808ae3b1b58ad494211086dc294b9006c76bd
3
- size 47423488
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9848ad54443f221c60d06a1ea4218ee3346334dcb800c9bd90c99266d38a5a7b
3
- size 37588241
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_w8a16.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6831b457662508e2f88f6ec95871683b2311ea885af8c28261d6927ba74d7b2c
3
- size 24797184
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_w8a16.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b8717501a2a3281fcb0323ad7f466a4be373e49260ad1406bea6b6175d61413
3
- size 18576531
 
 
 
 
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
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_dlc:
3
- qairt: 2.37.0.250724175447_124859
 
1
  tool_versions:
2
  qnn_dlc:
3
+ qairt: 2.38.0.250901140452_125126