You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: README.md
+4-4
Original file line number
Diff line number
Diff line change
@@ -17,7 +17,7 @@ This repository contains the source code of **OpenVINO™ integration with Tenso
17
17
18
18
- Ubuntu 18.04, 20.04
19
19
- Python 3.6, 3.7, or 3.8
20
-
- TensorFlow v2.4.1
20
+
- TensorFlow v2.5.0
21
21
22
22
Check our [Interactive Installation Table](https://openvinotoolkit.github.io/openvino_tensorflow/) for a menu of installation options. The table will help you configure the installation process.
23
23
@@ -30,7 +30,7 @@ This **OpenVINO™ integration with TensorFlow** package comes with pre-built li
30
30
31
31
32
32
pip3 install -U pip==21.0.1
33
-
pip3 install -U tensorflow==2.4.1
33
+
pip3 install -U tensorflow==2.5.0
34
34
pip3 install openvino-tensorflow
35
35
36
36
@@ -49,10 +49,10 @@ To see if **OpenVINO™ integration with TensorFlow** is properly installed, run
49
49
50
50
This should produce an output like:
51
51
52
-
TensorFlow version: 2.4.1
52
+
TensorFlow version: 2.5.0
53
53
OpenVINO integration with TensorFlow version: b'0.5.0'
54
54
OpenVINO version used for this build: b'2021.3'
55
-
TensorFlow version used for this build: v2.4.1
55
+
TensorFlow version used for this build: v2.5.0
56
56
CXX11_ABI flag used for this build: 0
57
57
OpenVINO integration with TensorFlow built with Grappler: False
Copy file name to clipboardexpand all lines: docs/ARCHITECTURE.md
+2
Original file line number
Diff line number
Diff line change
@@ -36,3 +36,5 @@ Backend manager creates a backend for the execution of the CNNNetwork. We implem
36
36
Basic backend is used for Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs and Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs). The backend creates an inference request and runs inference on a given input data.
37
37
38
38
VAD-M backend is used for Intel® Vision Accelerator Design with 8 Intel<sup>®</sup> Movidius™ MyriadX VPUs (referred as VAD-M or HDDL). We support batched inference execution in the VAD-M backend. When the user provides a batched input, multiple inference requests are created and inference is run in parallel on all the available VPUs in the VAD-M.
39
+
40
+
Backend Manager supports Dynamic Fallback which means if the execution of the corresponding CNNNetwork fails in OpenVINO runtime, the execution fallbacks to stock TensorFlow runtime.
3. Download & install Intel® Distribution of OpenVINO™ Toolkit 2021.3 release along with its dependencies from ([https://software.intel.com/en-us/openvino-toolkit/download](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit/download.html)).
54
54
@@ -142,10 +142,10 @@ Verify that `openvino-tensorflow` is installed correctly:
142
142
143
143
This should produce an output like:
144
144
145
-
TensorFlow version: 2.4.1
145
+
TensorFlow version: 2.5.0
146
146
OpenVINO integration with TensorFlow version: b'0.5.0'
147
147
OpenVINO version used for this build: b'2021.3'
148
-
TensorFlow version used for this build: v2.4.1
148
+
TensorFlow version used for this build: v2.5.0
149
149
CXX11_ABI flag used for this build: 1
150
150
OpenVINO integration with TensorFlow built with Grappler: False
151
151
@@ -181,9 +181,9 @@ TensorFlow can be built from source using `build_tf.py`. The build artifacts can
0 commit comments