experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update performance numbers for MobileNetV1/MobileNetV2/Inception

Browse Source 
These models have seen a ~20-30% latency improvement over the past
several months. Update the documented numbers accordingly.

PiperOrigin-RevId: 236904410
This commit is contained in:
Jared Duke 2019-03-05 12:59:34 -08:00 committed by TensorFlower Gardener
parent 776b5aa32a
commit 07714683be
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tensorflow/lite/g3doc/performance/model_optimization.md
View File

@ -65,11 +65,11 @@ Pixel 2 devices using a single big core. As the toolkit improves, so will t
<th> Size (Original) (MB)</th>
<th> Size (Optimized) (MB)</th>
</tr> <tr><td>Mobilenet-v1-1-224</td><td>0.709</td><td>0.657</td><td>0.70</td>
<td>180</td><td>145</td><td>80.2</td><td>16.9</td><td>4.3</td></tr>
<td>124</td><td>112</td><td>64</td><td>16.9</td><td>4.3</td></tr>
<tr><td>Mobilenet-v2-1-224</td><td>0.719</td><td>0.637</td><td>0.709</td>
<td>117</td><td>121</td><td>80.3</td><td>14</td><td>3.6</td></tr>
<td>89</td><td>98</td><td>54</td><td>14</td><td>3.6</td></tr>
<tr><td>Inception_v3</td><td>0.78</td><td>0.772</td><td>0.775</td>
<td>1585</td><td>1187</td><td>637</td><td>95.7</td><td>23.9</td></tr>
<td>1130</td><td>845</td><td>543</td><td>95.7</td><td>23.9</td></tr>
<tr><td>Resnet_v2_101</td><td>0.770</td><td>0.768</td><td>N/A</td>
<td>3973</td><td>2868</td><td>N/A</td><td>178.3</td><td>44.9</td></tr>
</table>