Commit
•
bd13a8f
1
Parent(s):
fff851d
update int8 onnx model and readme
Browse filesSigned-off-by: dujun <jun.du@intel.com>
- README.md +2 -2
- model.onnx +2 -2
README.md
CHANGED
|
@@ -53,8 +53,8 @@ The calibration dataloader is the eval dataloader. The default calibration sampl
|
|
| 53 |
|
| 54 |
| |INT8|FP32|
|
| 55 |
|---|:---:|:---:|
|
| 56 |
-
| **Accuracy (eval-f1)** |0.
|
| 57 |
-
| **Model size (MB)** |
|
| 58 |
|
| 59 |
|
| 60 |
#### Load ONNX model:
|
| 53 |
|
| 54 |
| |INT8|FP32|
|
| 55 |
|---|:---:|:---:|
|
| 56 |
+
| **Accuracy (eval-f1)** |0.8633|0.8687|
|
| 57 |
+
| **Model size (MB)** |154|254|
|
| 58 |
|
| 59 |
|
| 60 |
#### Load ONNX model:
|
model.onnx
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 sha256:9b91f6c76da5d2323d88a345c53bd4d4dd9f0daec4143e277c744be96488226b
|
| 3 |
+
size 161187871
|