Hugging Face's logo

qualcomm
/
RTMDet

Object Detection
PyTorch
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
00d3d20
·
verified ·
1 Parent(s): 4b51505

v0.32.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

Files changed (4) hide show
  1. .gitattributes +1 -0
  2. DEPLOYMENT_MODEL_LICENSE.pdf +3 -0
  3. LICENSE +2 -0
  4. README.md +5 -5
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
DEPLOYMENT_MODEL_LICENSE.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
+ size 109629
LICENSE ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ The license of the original trained model can be found at https://github.com/open-mmlab/mmdetection/blob/3.x/LICENSE.
2
+ The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
README.md CHANGED
@@ -28,7 +28,7 @@ This model is an implementation of RTMDet found [here](https://github.com/open-m
28
  - Model checkpoint: RTMDet Medium
29
  - Input resolution: 640x640
30
  - Number of parameters: 27.5M
31
- - Model size: 105 MB
32
 
33
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
34
  |---|---|---|---|---|---|---|---|---|
@@ -42,12 +42,12 @@ This model is an implementation of RTMDet found [here](https://github.com/open-m
42
  | RTMDet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 16.216 ms | 0 - 13 MB | NPU | -- |
43
  | RTMDet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 23.681 ms | 0 - 63 MB | NPU | -- |
44
  | RTMDet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 16.224 ms | 0 - 14 MB | NPU | -- |
45
- | RTMDet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 15.336 ms | 2 - 160 MB | NPU | -- |
46
  | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 12.277 ms | 0 - 102 MB | NPU | -- |
47
- | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 12.3 ms | 4 - 53 MB | NPU | -- |
48
  | RTMDet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 11.391 ms | 0 - 69 MB | NPU | -- |
49
- | RTMDet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 9.423 ms | 5 - 44 MB | NPU | -- |
50
- | RTMDet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 16.768 ms | 48 - 48 MB | NPU | -- |
51
 
52
 
53
 
 
28
  - Model checkpoint: RTMDet Medium
29
  - Input resolution: 640x640
30
  - Number of parameters: 27.5M
31
+ - Model size (float): 105 MB
32
 
33
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
34
  |---|---|---|---|---|---|---|---|---|
 
42
  | RTMDet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 16.216 ms | 0 - 13 MB | NPU | -- |
43
  | RTMDet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 23.681 ms | 0 - 63 MB | NPU | -- |
44
  | RTMDet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 16.224 ms | 0 - 14 MB | NPU | -- |
45
+ | RTMDet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 14.484 ms | 1 - 141 MB | NPU | -- |
46
  | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 12.277 ms | 0 - 102 MB | NPU | -- |
47
+ | RTMDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 11.001 ms | 4 - 50 MB | NPU | -- |
48
  | RTMDet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 11.391 ms | 0 - 69 MB | NPU | -- |
49
+ | RTMDet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 10.193 ms | 7 - 47 MB | NPU | -- |
50
+ | RTMDet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 15.801 ms | 51 - 51 MB | NPU | -- |
51
 
52
 
53