Chua, Vui Seng commited on
Commit 路
eab1115
1
Parent(s): 8b42301
Add OpenVINO IR
Browse files- .gitattributes +1 -0
- ir/bert-base-squadv1.bin +3 -0
- ir/bert-base-squadv1.mapping +0 -0
- ir/bert-base-squadv1.xml +0 -0
- ir/mo.log +30 -0
.gitattributes
CHANGED
|
@@ -27,3 +27,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
bert-base-squadv1.onnx filter=lfs diff=lfs merge=lfs -text
|
| 29 |
eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
bert-base-squadv1.onnx filter=lfs diff=lfs merge=lfs -text
|
| 29 |
eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
ir/*.bin
|
ir/bert-base-squadv1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c95bd1b5778fbc18ee6b8156721bcd8bced863ea0d1526b5a879edcc48e9f34
|
| 3 |
+
size 435577068
|
ir/bert-base-squadv1.mapping
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ir/bert-base-squadv1.xml
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ir/mo.log
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Model Optimizer arguments:
|
| 2 |
+
Common parameters:
|
| 3 |
+
- Path to the Input Model: /data1/vchua/tld-poc/repo/bert-base-squadv1/bert-base-squadv1.onnx
|
| 4 |
+
- Path for generated IR: /data1/vchua/tld-poc/repo/bert-base-squadv1/ir
|
| 5 |
+
- IR output name: bert-base-squadv1
|
| 6 |
+
- Log level: ERROR
|
| 7 |
+
- Batch: Not specified, inherited from the model
|
| 8 |
+
- Input layers: Not specified, inherited from the model
|
| 9 |
+
- Output layers: Not specified, inherited from the model
|
| 10 |
+
- Input shapes: Not specified, inherited from the model
|
| 11 |
+
- Mean values: Not specified
|
| 12 |
+
- Scale values: Not specified
|
| 13 |
+
- Scale factor: Not specified
|
| 14 |
+
- Precision of IR: FP32
|
| 15 |
+
- Enable fusing: True
|
| 16 |
+
- Enable grouped convolutions fusing: True
|
| 17 |
+
- Move mean values to preprocess section: None
|
| 18 |
+
- Reverse input channels: False
|
| 19 |
+
ONNX specific parameters:
|
| 20 |
+
- Inference Engine found in: /opt/intel/openvino/python/python3.6/openvino
|
| 21 |
+
Inference Engine version: 2021.4.2-3974-e2a469a3450-releases/2021/4
|
| 22 |
+
Model Optimizer version: 2021.4.2-3974-e2a469a3450-releases/2021/4
|
| 23 |
+
[ WARNING ] Convert data type of Parameter "input.1" to int32
|
| 24 |
+
[ WARNING ] Convert data type of Parameter "attention_mask" to int32
|
| 25 |
+
[ WARNING ] Convert data type of Parameter "input.2" to int32
|
| 26 |
+
[ SUCCESS ] Generated IR version 10 model.
|
| 27 |
+
[ SUCCESS ] XML file: /data1/vchua/tld-poc/repo/bert-base-squadv1/ir/bert-base-squadv1.xml
|
| 28 |
+
[ SUCCESS ] BIN file: /data1/vchua/tld-poc/repo/bert-base-squadv1/ir/bert-base-squadv1.bin
|
| 29 |
+
[ SUCCESS ] Total execution time: 52.58 seconds.
|
| 30 |
+
[ SUCCESS ] Memory consumed: 1388 MB.
|