Skip to content

Recover mobilenetv2-7 and mobilenetv2-10 #563

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jcwchen merged 3 commits into from
Oct 13, 2022
Merged

Recover mobilenetv2-7 and mobilenetv2-10 #563

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
21f4566
Recover mobilenetv2-7 and mobilenetv2-10
jcwchen Oct 13, 2022
48e3dca
update -7.tar.gz
jcwchen Oct 13, 2022
6a09a96
fix broken test directory
jcwchen Oct 13, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
86 changes: 64 additions & 22 deletions ONNX_HUB_MANIFEST.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3218,6 +3218,61 @@
"model_with_data_bytes": 26751
}
},
{
"model": "MobileNet v2-1.0",
"model_path": "vision/classification/mobilenet/model/mobilenetv2-10.onnx",
"onnx_version": "1.5.0",
"opset_version": 10,
"metadata": {
"model_sha": "0e7c0aa4bc74650386fa1d2c84705753de7c2bdb21909ada5c59154bb429e092",
"model_bytes": 13963115,
"tags": [
"vision",
"classification",
"mobilenet"
],
"io_ports": {
"inputs": [
{
"name": "input",
"shape": [
"batch_size",
3,
224,
224
],
"type": "tensor(float)"
}
],
"outputs": [
{
"name": "output",
"shape": [
"batch_size",
1000
],
"type": "tensor(float)"
}
]
},
"extra_ports": {
"features": [
{
"name": "464",
"shape": [
0,
1280,
1,
1
]
}
]
},
"model_with_data_path": "vision/classification/mobilenet/model/mobilenetv2-10.tar.gz",
"model_with_data_sha": "3e4e9e2de0241cc829917e9c0233229974f5d35d3cfd012a263ca36c98f36ac3",
"model_with_data_bytes": 13504391
}
},
{
"model": "MobileNet v2-1.0-int8",
"model_path": "vision/classification/mobilenet/model/mobilenetv2-12-int8.onnx",
Expand Down Expand Up @@ -3345,13 +3400,13 @@
}
},
{
"model": "MobileNet v2-1.0",
"model": "MobileNet v2-7",
"model_path": "vision/classification/mobilenet/model/mobilenetv2-7.onnx",
"onnx_version": "1.2.1",
"opset_version": 7,
"metadata": {
"model_sha": "0e7c0aa4bc74650386fa1d2c84705753de7c2bdb21909ada5c59154bb429e092",
"model_bytes": 13963115,
"model_sha": "c1c513582d56afceff8516c73804e484c81c6a830712ab6d682253f4a3cd042f",
"model_bytes": 14246826,
"tags": [
"vision",
"classification",
Expand All @@ -3360,9 +3415,9 @@
"io_ports": {
"inputs": [
{
"name": "input",
"name": "data",
"shape": [
"batch_size",
1,
3,
224,
224
Expand All @@ -3372,31 +3427,18 @@
],
"outputs": [
{
"name": "output",
"name": "mobilenetv20_output_flatten0_reshape0",
"shape": [
"batch_size",
1,
1000
],
"type": "tensor(float)"
}
]
},
"extra_ports": {
"features": [
{
"name": "464",
"shape": [
0,
1280,
1,
1
]
}
]
},
"model_with_data_path": "vision/classification/mobilenet/model/mobilenetv2-7.tar.gz",
"model_with_data_sha": "3e4e9e2de0241cc829917e9c0233229974f5d35d3cfd012a263ca36c98f36ac3",
"model_with_data_bytes": 13504391
"model_with_data_sha": "b463ad62dae99f13afd88549ca7d43e9bda6876614f3592ebb41177e1db0fcc5",
"model_with_data_bytes": 13682646
}
},
{
Expand Down
7 changes: 4 additions & 3 deletions vision/classification/mobilenet/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,10 @@ The below model is using multiplier value as 1.0.

|Model |Download |Download (with sample test data)| ONNX version |Opset version|Top-1 accuracy (%)|Top-5 accuracy (%)|
|-------------|:--------------|:--------------|:--------------|:--------------|:--------------|:--------------|
|MobileNet v2-1.0| [13.6 MB](model/mobilenetv2-7.onnx) | [14.1 MB](model/mobilenetv2-7.tar.gz) | 1.2.1 | 7| 70.94 | 89.99 |
|MobileNet v2-1.0-fp32| [13.3 MB](model/mobilenetv2-12.onnx) | [12.9 MB](model/mobilenetv2-12.tar.gz) | 1.9.0 | 12| 69.48 | 89.26 |
|MobileNet v2-1.0-int8| [3.5 MB](model/mobilenetv2-12-int8.onnx) | [3.7 MB](model/mobilenetv2-12-int8.tar.gz) | 1.9.0 | 12| 68.30 | 88.44 |
|MobileNet v2-7| [13.5 MB](model/mobilenetv2-7.onnx) | [14.0 MB](model/mobilenetv2-7.tar.gz) | 1.2.1 | 7 | 70.94 | 89.99 |
|MobileNet v2-1.0| [13.3 MB](model/mobilenetv2-10.onnx) | [12.8 MB](model/mobilenetv2-10.tar.gz) | 1.5.0 | 10 | 70.94 | 89.99 |
|MobileNet v2-1.0-fp32| [13.3 MB](model/mobilenetv2-12.onnx) | [12.9 MB](model/mobilenetv2-12.tar.gz) | 1.9.0 | 12| 69.48 | 89.26 |
|MobileNet v2-1.0-int8| [3.5 MB](model/mobilenetv2-12-int8.onnx) | [3.7 MB](model/mobilenetv2-12-int8.tar.gz) | 1.9.0 | 12| 68.30 | 88.44 |
|MobileNet v2-1.0-qdq| [3.4 MB](model/mobilenetv2-12-qdq.onnx) | [3.3 MB](model/mobilenetv2-12-qdq.tar.gz) |1.10.0| 12 |67.40 | |
> Compared with the fp32 MobileNet v2-1.0, int8 MobileNet v2-1.0's Top-1 accuracy decline ratio is 1.70%, Top-5 accuracy decline ratio is 0.92% and performance improvement is 1.05x.
>
Expand Down
3 changes: 3 additions & 0 deletions vision/classification/mobilenet/model/mobilenetv2-10.onnx
View file
Open in desktop
Git LFS file not shown
3 changes: 3 additions & 0 deletions vision/classification/mobilenet/model/mobilenetv2-10.tar.gz
View file
Open in desktop
Git LFS file not shown
4 changes: 2 additions & 2 deletions vision/classification/mobilenet/model/mobilenetv2-7.onnx
View file
Open in desktop
Git LFS file not shown
4 changes: 2 additions & 2 deletions vision/classification/mobilenet/model/mobilenetv2-7.tar.gz
View file
Open in desktop
Git LFS file not shown