Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
LiteRT
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
433d25a
·
verified ·
1 Parent(s): 24419ea

v0.32.0

Browse files

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

Files changed (7) hide show
  1. .gitattributes +1 -0
  2. ConvNext-Base.onnx +2 -2
  3. ConvNext-Base_w8a16.dlc +2 -2
  4. ConvNext-Base_w8a16.onnx +2 -2
  5. DEPLOYMENT_MODEL_LICENSE.pdf +3 -0
  6. LICENSE +2 -0
  7. README.md +20 -19
.gitattributes CHANGED
@@ -37,3 +37,4 @@ ConvNext-Base.so filter=lfs diff=lfs merge=lfs -text
37
  ConvNext-Base_w8a16.so filter=lfs diff=lfs merge=lfs -text
38
  ConvNext-Base.dlc filter=lfs diff=lfs merge=lfs -text
39
  ConvNext-Base_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
 
 
37
  ConvNext-Base_w8a16.so filter=lfs diff=lfs merge=lfs -text
38
  ConvNext-Base.dlc filter=lfs diff=lfs merge=lfs -text
39
  ConvNext-Base_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
40
+ DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
ConvNext-Base.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc694f26d604a086af548f7510a57e255d5b1567a92ac9d91f924a30684c457b
3
- size 354482269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2180d814088b7b8e07b4d8acd984653a573999e7b2da8a92b0351352162fab6
3
+ size 354498474
ConvNext-Base_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86047f869b13b1400efb90d8ca2d6b02c357270d2a3904b47e0300f4cf24c16a
3
- size 93035524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ebc45fa259a0e3d2a2533d7feedbea696115243e5ef80e592902e5d19b3755
3
+ size 93035467
ConvNext-Base_w8a16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49589d49c943b3ba4a2777f4e9cc214cdb5bb472716b4253f53bffbb05096aec
3
- size 355235397
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ae19a7b9b3f7023a05a802bf23fc37379dc36c431fcf8f50d54107a4b24b18
3
+ size 355235429
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/pytorch/vision/blob/main/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
@@ -29,8 +29,9 @@ More details on model performance across various devices, can be found
29
  - **Model Stats:**
30
  - Model checkpoint: Imagenet
31
  - Input resolution: 224x224
32
- - Number of parameters: 28.6M
33
- - Model size (float): 109 MB
 
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
@@ -44,28 +45,28 @@ More details on model performance across various devices, can be found
44
  | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.128 ms | 1 - 281 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
45
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.483 ms | 0 - 34 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
46
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.283 ms | 0 - 25 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
47
- | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.519 ms | 0 - 410 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
48
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.561 ms | 0 - 295 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
49
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.003 ms | 1 - 290 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
50
- | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.52 ms | 1 - 299 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
51
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.839 ms | 0 - 282 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
52
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.395 ms | 1 - 286 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
53
- | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.998 ms | 1 - 284 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
54
  | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.87 ms | 1390 - 1390 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
55
- | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.894 ms | 176 - 176 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
56
- | ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.529 ms | 0 - 129 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
57
- | ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 9.346 ms | 0 - 144 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
58
- | ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.98 ms | 0 - 33 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
59
- | ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.243 ms | 0 - 129 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
60
- | ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 39.465 ms | 0 - 207 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
61
- | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 5.96 ms | 0 - 33 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
62
- | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 237.787 ms | 634 - 1019 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
63
- | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.133 ms | 0 - 140 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
64
- | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 200.198 ms | 684 - 1474 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
65
- | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.805 ms | 0 - 132 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
66
- | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 157.771 ms | 685 - 1376 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
67
- | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.599 ms | 512 - 512 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
68
- | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 208.749 ms | 917 - 917 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
69
 
70
 
71
 
 
29
  - **Model Stats:**
30
  - Model checkpoint: Imagenet
31
  - Input resolution: 224x224
32
+ - Number of parameters: 88.6M
33
+ - Model size (float): 338 MB
34
+ - Model size (w8a16): 88.7 MB
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
 
45
  | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.128 ms | 1 - 281 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
46
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.483 ms | 0 - 34 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
47
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.283 ms | 0 - 25 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
48
+ | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.666 ms | 0 - 399 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
49
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.561 ms | 0 - 295 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
50
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.003 ms | 1 - 290 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
51
+ | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.511 ms | 1 - 297 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
52
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.839 ms | 0 - 282 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
53
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.395 ms | 1 - 286 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
54
+ | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.359 ms | 1 - 284 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
55
  | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.87 ms | 1390 - 1390 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
56
+ | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.876 ms | 176 - 176 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
57
+ | ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.431 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
58
+ | ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 9.619 ms | 0 - 146 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
59
+ | ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.96 ms | 0 - 33 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
60
+ | ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.226 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
61
+ | ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 39.227 ms | 0 - 206 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
62
+ | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 5.951 ms | 0 - 34 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
63
+ | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 239.386 ms | 521 - 915 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
64
+ | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.158 ms | 0 - 138 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
65
+ | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 201.977 ms | 683 - 1468 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
66
+ | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.842 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
67
+ | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 157.297 ms | 687 - 1377 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
68
+ | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.626 ms | 521 - 521 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
69
+ | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 213.519 ms | 918 - 918 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
70
 
71
 
72