v0.38.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.
- EfficientNet-V2-s_float.dlc +2 -2
- EfficientNet-V2-s_float.onnx.zip +2 -2
- EfficientNet-V2-s_w8a16.dlc +2 -2
- README.md +26 -30
- precompiled/qualcomm-qcs6490-proxy/EfficientNet-V2-s_w8a16.bin +0 -3
- precompiled/qualcomm-qcs6490-proxy/EfficientNet-V2-s_w8a16.onnx.zip +0 -3
- precompiled/qualcomm-qcs6490-proxy/tool-versions.yaml +0 -3
- precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_float.bin +0 -3
- precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_float.onnx.zip +0 -3
- precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_w8a16.bin +0 -3
- precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_w8a16.onnx.zip +0 -3
- precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml +0 -3
- tool-versions.yaml +1 -1
EfficientNet-V2-s_float.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:552047eb13a12e3f64a942319e46d05894c5bd64ae066d89cfdae155fe412837
|
| 3 |
+
size 86056060
|
EfficientNet-V2-s_float.onnx.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:905e167ec7fcc57e6cfc4f8b03a1ead9c8fb9888f7b0e0723421b26519943d4f
|
| 3 |
+
size 79809738
|
EfficientNet-V2-s_w8a16.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32a75290a02d11358cbc5e322698e2f4241db4a1b8e666058695347987172116
|
| 3 |
+
size 28563948
|
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-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 10.
|
| 41 |
-
| EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 10.
|
| 42 |
-
| EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.
|
| 43 |
-
| EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.
|
| 44 |
-
| EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.
|
| 45 |
-
| EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.
|
| 46 |
-
| EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.
|
| 47 |
-
| EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3.
|
| 48 |
-
| EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.
|
| 49 |
-
| EfficientNet-V2-s | float | Samsung Galaxy
|
| 50 |
-
| EfficientNet-V2-s | float | Samsung Galaxy
|
| 51 |
-
| EfficientNet-V2-s | float | Samsung Galaxy
|
| 52 |
-
| EfficientNet-V2-s | float | Samsung Galaxy
|
| 53 |
-
| EfficientNet-V2-s | float | Samsung Galaxy
|
| 54 |
-
| EfficientNet-V2-s | float | Samsung Galaxy
|
| 55 |
-
| EfficientNet-V2-s | float | Snapdragon
|
| 56 |
-
| EfficientNet-V2-s | float | Snapdragon
|
| 57 |
-
| EfficientNet-V2-s |
|
| 58 |
-
| EfficientNet-V2-s |
|
| 59 |
-
| EfficientNet-V2-s |
|
| 60 |
-
| EfficientNet-V2-s | w8a16 |
|
| 61 |
-
| EfficientNet-V2-s | w8a16 |
|
| 62 |
-
| EfficientNet-V2-s | w8a16 |
|
| 63 |
-
| EfficientNet-V2-s | w8a16 |
|
| 64 |
-
| EfficientNet-V2-s | w8a16 |
|
| 65 |
-
| EfficientNet-V2-s | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 2.619 ms | 0 - 16 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 66 |
-
| EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.761 ms | 0 - 76 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 67 |
-
| EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.479 ms | 0 - 70 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 68 |
-
| EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.901 ms | 106 - 106 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 69 |
|
| 70 |
|
| 71 |
|
|
@@ -147,7 +143,7 @@ from qai_hub_models.models.efficientnet_v2_s import Model
|
|
| 147 |
torch_model = Model.from_pretrained()
|
| 148 |
|
| 149 |
# Device
|
| 150 |
-
device = hub.Device("Samsung Galaxy
|
| 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-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 10.963 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
|
| 41 |
+
| EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 10.756 ms | 0 - 35 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
|
| 42 |
+
| EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.87 ms | 0 - 90 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
|
| 43 |
+
| EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.581 ms | 1 - 46 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
|
| 44 |
+
| EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.684 ms | 0 - 375 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
|
| 45 |
+
| EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.564 ms | 1 - 11 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
|
| 46 |
+
| EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.666 ms | 0 - 107 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
|
| 47 |
+
| EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3.843 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
|
| 48 |
+
| EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.666 ms | 1 - 35 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
|
| 49 |
+
| EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.004 ms | 0 - 104 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
|
| 50 |
+
| EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.893 ms | 1 - 64 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
|
| 51 |
+
| EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.967 ms | 0 - 68 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
|
| 52 |
+
| EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.57 ms | 0 - 82 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
|
| 53 |
+
| EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.488 ms | 1 - 41 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
|
| 54 |
+
| EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.589 ms | 0 - 43 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
|
| 55 |
+
| EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.85 ms | 220 - 220 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
|
| 56 |
+
| EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.677 ms | 47 - 47 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
|
| 57 |
+
| EfficientNet-V2-s | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.301 ms | 0 - 66 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 58 |
+
| EfficientNet-V2-s | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 3.288 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 59 |
+
| EfficientNet-V2-s | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.63 ms | 0 - 17 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 60 |
+
| EfficientNet-V2-s | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.007 ms | 0 - 65 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 61 |
+
| EfficientNet-V2-s | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 9.474 ms | 0 - 125 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 62 |
+
| EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.752 ms | 0 - 79 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 63 |
+
| EfficientNet-V2-s | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.227 ms | 0 - 71 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
|
| 64 |
+
| EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.911 ms | 95 - 95 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_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-V2-s_w8a16.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1366451c3e090161c91a7dc625500aed028a024faeac28d9882aaedfcf42bb8f
|
| 3 |
-
size 32378880
|
|
|
|
|
|
|
|
|
|
|
|
precompiled/qualcomm-qcs6490-proxy/EfficientNet-V2-s_w8a16.onnx.zip
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8e22a3ac8ef5773b7c2f1518daeee0c0073c993f83c480f96cce6c8556094f35
|
| 3 |
-
size 19994003
|
|
|
|
|
|
|
|
|
|
|
|
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-V2-s_float.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:28f5fe9780bd5cbbb1f2155e58a312aded189e06bfd743d6f4d466253ab2c528
|
| 3 |
-
size 49291264
|
|
|
|
|
|
|
|
|
|
|
|
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_float.onnx.zip
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ddf405e7f38251bab6d0c9b5030c49961614bf1ff4f70f180fce4a642b44e792
|
| 3 |
-
size 41340323
|
|
|
|
|
|
|
|
|
|
|
|
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_w8a16.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ce36c5eba199699a8d8213d9fc74201460bce0de4da1c30d33caf0df210c726f
|
| 3 |
-
size 25288704
|
|
|
|
|
|
|
|
|
|
|
|
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-V2-s_w8a16.onnx.zip
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c89d1d45d9a94bd70cb8095fe87a4dccd5c9d46b70d3a62576ef75df5327f65d
|
| 3 |
-
size 20063533
|
|
|
|
|
|
|
|
|
|
|
|
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.
|
|
|
|
| 1 |
tool_versions:
|
| 2 |
qnn_dlc:
|
| 3 |
+
qairt: 2.38.0.250901140452_125126
|