v0.44.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.44.0 for changelog.
- BEVDet_float.onnx.zip +2 -2
- BEVDet_float.tflite +2 -2
- BEVDet_w8a16_mixed_fp16.onnx.zip +2 -2
- DEPLOYMENT_MODEL_LICENSE.pdf +0 -3
- LICENSE +1 -2
- README.md +24 -23
BEVDet_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 sha256:6fc12dc9108fc5c8b16ce48b5444f3f12eee8415c46171ea1efcedafd58f4801
|
| 3 |
+
size 165998526
|
BEVDet_float.tflite
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 sha256:304ca8d81c632c43c8ebcfcbdab8d615c5c034582047dad893664850b15f0e2c
|
| 3 |
+
size 196507236
|
BEVDet_w8a16_mixed_fp16.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 sha256:5b2a586fe2357a63d7f797273f9710b0033417b491993b8927dea55873d2e494
|
| 3 |
+
size 80581105
|
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
|
|
|
|
|
|
|
|
|
|
|
|
LICENSE
CHANGED
|
@@ -1,2 +1 @@
|
|
| 1 |
-
The license of the original trained model can be found at https://github.com/HuangJunJie2017/BEVDet/blob/dev3.0/LICENSE.
|
| 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 https://github.com/HuangJunJie2017/BEVDet/blob/dev3.0/LICENSE https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf.
|
|
|
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
library_name: pytorch
|
| 3 |
license: other
|
| 4 |
tags:
|
|
|
|
| 5 |
- android
|
| 6 |
pipeline_tag: other
|
| 7 |
|
|
@@ -35,27 +36,28 @@ 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 |
-
| BEVDet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE |
|
| 39 |
-
| BEVDet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE |
|
| 40 |
-
| BEVDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE |
|
| 41 |
-
| BEVDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX |
|
| 42 |
-
| BEVDet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE |
|
| 43 |
-
| BEVDet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE |
|
| 44 |
-
| BEVDet | float |
|
| 45 |
-
| BEVDet | float |
|
| 46 |
-
| BEVDet | float |
|
| 47 |
-
| BEVDet | float |
|
| 48 |
-
| BEVDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile |
|
| 49 |
-
| BEVDet | float | Samsung Galaxy
|
| 50 |
-
| BEVDet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile |
|
| 51 |
-
| BEVDet | float |
|
| 52 |
-
| BEVDet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile |
|
| 53 |
-
| BEVDet | float | Snapdragon
|
| 54 |
-
| BEVDet |
|
| 55 |
-
| BEVDet | w8a16_mixed_fp16 |
|
| 56 |
-
| BEVDet | w8a16_mixed_fp16 | Samsung Galaxy
|
| 57 |
-
| BEVDet | w8a16_mixed_fp16 |
|
| 58 |
-
| BEVDet | w8a16_mixed_fp16 | Snapdragon
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
|
|
@@ -232,8 +234,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
| 232 |
|
| 233 |
## License
|
| 234 |
* The license for the original implementation of BEVDet can be found
|
| 235 |
-
[here](https://github.com/HuangJunJie2017/BEVDet/blob/dev3.0/LICENSE).
|
| 236 |
-
* 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)
|
| 237 |
|
| 238 |
|
| 239 |
|
|
|
|
| 2 |
library_name: pytorch
|
| 3 |
license: other
|
| 4 |
tags:
|
| 5 |
+
- bu_auto
|
| 6 |
- android
|
| 7 |
pipeline_tag: other
|
| 8 |
|
|
|
|
| 36 |
|
| 37 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 38 |
|---|---|---|---|---|---|---|---|---|
|
| 39 |
+
| BEVDet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3054.307 ms | 129 - 140 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 40 |
+
| BEVDet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 2586.577 ms | 128 - 157 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 41 |
+
| BEVDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2305.945 ms | 127 - 130 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 42 |
+
| BEVDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2637.508 ms | 290 - 293 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
|
| 43 |
+
| BEVDet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2510.003 ms | 129 - 140 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 44 |
+
| BEVDet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3054.307 ms | 129 - 140 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 45 |
+
| BEVDet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 2077.211 ms | 128 - 135 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 46 |
+
| BEVDet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2016.564 ms | 128 - 143 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 47 |
+
| BEVDet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 2173.285 ms | 126 - 130 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 48 |
+
| BEVDet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2510.003 ms | 129 - 140 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 49 |
+
| BEVDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1616.313 ms | 123 - 146 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 50 |
+
| BEVDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2030.173 ms | 298 - 318 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
|
| 51 |
+
| BEVDet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1339.121 ms | 97 - 114 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 52 |
+
| BEVDet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1514.717 ms | 259 - 270 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
|
| 53 |
+
| BEVDet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1032.083 ms | 108 - 120 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
|
| 54 |
+
| BEVDet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1442.572 ms | 284 - 295 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
|
| 55 |
+
| BEVDet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 692.919 ms | 598 - 598 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
|
| 56 |
+
| BEVDet | w8a16_mixed_fp16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2538.096 ms | 317 - 338 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
|
| 57 |
+
| BEVDet | w8a16_mixed_fp16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2117.963 ms | 311 - 337 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
|
| 58 |
+
| BEVDet | w8a16_mixed_fp16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1666.704 ms | 319 - 337 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
|
| 59 |
+
| BEVDet | w8a16_mixed_fp16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1854.312 ms | 315 - 328 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
|
| 60 |
+
| BEVDet | w8a16_mixed_fp16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 864.519 ms | 1099 - 1099 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
|
| 61 |
|
| 62 |
|
| 63 |
|
|
|
|
| 234 |
|
| 235 |
## License
|
| 236 |
* The license for the original implementation of BEVDet can be found
|
| 237 |
+
[here](https://github.com/HuangJunJie2017/BEVDet/blob/dev3.0/LICENSE https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf).
|
|
|
|
| 238 |
|
| 239 |
|
| 240 |
|