Hugging Face's logo

qualcomm
/
DLA-102-X

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
576b960
·
verified ·
1 Parent(s): 750ea13

v0.44.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.44.0 for changelog.

Files changed (6) hide show
  1. DEPLOYMENT_MODEL_LICENSE.pdf +0 -3
  2. DLA-102-X_float.dlc +1 -1
  3. DLA-102-X_float.onnx.zip +2 -2
  4. DLA-102-X_float.tflite +2 -2
  5. LICENSE +0 -1
  6. README.md +21 -21
DEPLOYMENT_MODEL_LICENSE.pdf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
- size 109629
 
 
 
 
DLA-102-X_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fe7fc75a510961acbf7743bb0364cf9b622b2f7c8612e5b5caefa439b7e4ab9
3
  size 105356884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7420873dcc5d212adad1a1e3914bae3cd4b8a8361f2491590576b0d3d4d9f3
3
  size 105356884
DLA-102-X_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd8978cc7fbe36ffdd49269e1ceb26d81aca1478be06f2ac8c0b05f034b199f4
3
- size 98614711
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d02ca8af9d1c246f8e27e0a1c1e0197fecb419621142430dac87fdd3198a59e
3
+ size 98614731
DLA-102-X_float.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2517ec10879608ff951794d7c33d1ff47e681c243c5b7942d9fe61ff7672e56
3
- size 105106268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575833fa9ed0ee78b18290727992425848075cd4bd477b7378e22b7ffd368c58
3
+ size 105106288
LICENSE CHANGED
@@ -1,2 +1 @@
1
  The license of the original trained model can be found at hhttps://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/bsd-3-clause.md.
2
- The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
 
1
  The license of the original trained model can be found at hhttps://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/bsd-3-clause.md.
 
README.md CHANGED
@@ -3,6 +3,7 @@ library_name: pytorch
3
  license: other
4
  tags:
5
  - backbone
 
6
  - android
7
  pipeline_tag: image-classification
8
 
@@ -36,26 +37,26 @@ 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
- | DLA-102-X | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.682 ms | 0 - 102 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
40
- | DLA-102-X | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.409 ms | 1 - 50 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
41
- | DLA-102-X | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 3.78 ms | 0 - 98 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
42
- | DLA-102-X | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.325 ms | 1 - 48 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
43
- | DLA-102-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.802 ms | 0 - 17 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
44
- | DLA-102-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.778 ms | 0 - 19 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
45
- | DLA-102-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.89 ms | 0 - 135 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
46
- | DLA-102-X | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.492 ms | 0 - 102 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
47
- | DLA-102-X | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 18.82 ms | 1 - 50 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
48
- | DLA-102-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.032 ms | 0 - 111 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
49
- | DLA-102-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.961 ms | 1 - 58 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
50
- | DLA-102-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.02 ms | 0 - 59 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
51
- | DLA-102-X | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.666 ms | 0 - 106 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
52
- | DLA-102-X | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.61 ms | 0 - 56 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
53
- | DLA-102-X | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.717 ms | 0 - 52 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
54
- | DLA-102-X | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1.381 ms | 0 - 102 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
55
- | DLA-102-X | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.225 ms | 0 - 58 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
56
- | DLA-102-X | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.395 ms | 0 - 55 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
57
- | DLA-102-X | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.073 ms | 154 - 154 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
58
- | DLA-102-X | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.895 ms | 54 - 54 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
59
 
60
 
61
 
@@ -218,7 +219,6 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
218
  ## License
219
  * The license for the original implementation of DLA-102-X can be found
220
  [here](hhttps://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/bsd-3-clause.md).
221
- * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
222
 
223
 
224
 
 
3
  license: other
4
  tags:
5
  - backbone
6
+ - bu_auto
7
  - android
8
  pipeline_tag: image-classification
9
 
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | DLA-102-X | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.436 ms | 0 - 232 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
41
+ | DLA-102-X | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.421 ms | 1 - 181 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
42
+ | DLA-102-X | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.4 ms | 0 - 260 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
43
+ | DLA-102-X | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.422 ms | 1 - 210 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
44
+ | DLA-102-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.755 ms | 0 - 3 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
45
+ | DLA-102-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.824 ms | 1 - 3 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
46
+ | DLA-102-X | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.862 ms | 0 - 58 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
47
+ | DLA-102-X | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.428 ms | 0 - 231 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
48
+ | DLA-102-X | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.37 ms | 0 - 180 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
49
+ | DLA-102-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.965 ms | 0 - 284 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
50
+ | DLA-102-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.976 ms | 1 - 230 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
51
+ | DLA-102-X | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.016 ms | 0 - 206 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
52
+ | DLA-102-X | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.592 ms | 0 - 231 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
53
+ | DLA-102-X | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.618 ms | 0 - 180 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
54
+ | DLA-102-X | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.717 ms | 0 - 157 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
55
+ | DLA-102-X | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1.209 ms | 0 - 231 MB | NPU | [DLA-102-X.tflite](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.tflite) |
56
+ | DLA-102-X | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.231 ms | 1 - 187 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
57
+ | DLA-102-X | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.395 ms | 0 - 159 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
58
+ | DLA-102-X | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.085 ms | 1 - 1 MB | NPU | [DLA-102-X.dlc](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.dlc) |
59
+ | DLA-102-X | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.911 ms | 54 - 54 MB | NPU | [DLA-102-X.onnx.zip](https://huggingface.co/qualcomm/DLA-102-X/blob/main/DLA-102-X.onnx.zip) |
60
 
61
 
62
 
 
219
  ## License
220
  * The license for the original implementation of DLA-102-X can be found
221
  [here](hhttps://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/bsd-3-clause.md).
 
222
 
223
 
224