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

Link to TFHub model pages, where there are more model information and image models many with metadata.

Browse Source 
PiperOrigin-RevId: 300286091
Change-Id: Ifaedf6f023ea850f56756db87910eeeccfc79810
This commit is contained in:
A. Unique TensorFlower 2020-03-11 03:07:26 -07:00 committed by TensorFlower Gardener
parent 8a6710a496
commit 59d97e3414
1 changed files with 23 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
tensorflow/lite/g3doc/guide/hosted_models.md
View File

@ -3,7 +3,9 @@
The following is an incomplete list of pre-trained models optimized to work with
TensorFlow Lite.
To get started choosing a model, visit <a href="../models">Models</a>.
To get started choosing a model, visit <a href="../models">Models</a> page with
end-to-end examples, or pick a [TensorFlow Lite model from TensorFlow Hub]
(https://tfhub.dev/s?deployment-format=lite).
Note: The best model for a given application depends on your requirements. For
example, some applications might benefit from higher accuracy, while others
@ -22,6 +24,9 @@ classification models offer the smallest model size and fastest performance, at
the expense of accuracy. The performance values are measured on Pixel 3 on
Android 10.
You can find many [quantized models](https://tfhub.dev/s?deployment-format=lite&module-type=image-classification&q=quantized)
from TensorFlow Hub and get more model information there.
Model name | Paper and model | Model size | Top-1 accuracy | Top-5 accuracy | CPU, 4 threads | NNAPI
--------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | ---------: | -------------: | -------------: | -------------: | ----:
Mobilenet_V1_0.25_128_quant | [paper](https://arxiv.org/pdf/1712.05877.pdf), [tflite&pb](https://storage.googleapis.com/download.tensorflow.org/models/mobilenet_v1_2018_08_02/mobilenet_v1_0.25_128_quant.tgz) | 0.5 Mb | 39.5% | 64.4% | 0.8 ms | 2 ms
@ -60,6 +65,9 @@ performance. <a href="../performance/gpu">GPU acceleration</a> requires the use
of floating point models. The performance values are measured on Pixel 3 on
Android 10.
You can find many [image classification models](https://tfhub.dev/s?deployment-format=lite&module-type=image-classification)
from TensorFlow Hub and get more model information there.
Model name | Paper and model | Model size | Top-1 accuracy | Top-5 accuracy | CPU, 4 threads | GPU | NNAPI
--------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | ---------: | -------------: | -------------: | -------------: | -----: | ----:
DenseNet | [paper](https://arxiv.org/abs/1608.06993), [tflite&pb](https://storage.googleapis.com/download.tensorflow.org/models/tflite/model_zoo/upload_20180427/densenet_2018_04_27.tgz) | 43.6 Mb | 64.2% | 85.6% | 195 ms | 60 ms | 1656 ms
@ -94,6 +102,9 @@ The following image classification models were created using
<a href="https://cloud.google.com/automl/">Cloud AutoML</a>. The performance
values are measured on Pixel 3 on Android 10.
You can find these models in [TensorFlow Hub](https://tfhub.dev/s?deployment-format=lite&q=MnasNet)
and get more model information there.
Model Name | Paper and model | Model size | Top-1 accuracy | Top-5 accuracy | CPU, 4 threads | GPU | NNAPI
---------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------: | ---------: | -------------: | -------------: | -------------: | ------: | ----:
MnasNet_0.50_224 | [paper](https://arxiv.org/abs/1807.11626), [tflite&pb](https://storage.cloud.google.com/download.tensorflow.org/models/tflite/mnasnet_0.5_224_09_07_2018.tgz) | 8.5 Mb | 68.03% | 87.79% | 9.5 ms | 5.9 ms | 16.6 ms
@ -114,44 +125,37 @@ Accuracy numbers were computed using the
For more information about object detection, see
<a href="../models/object_detection/overview.md">Object detection</a>.
The object detection model we currently host is
**coco_ssd_mobilenet_v1_1.0_quant_2018_06_29**.
<a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/tflite/coco_ssd_mobilenet_v1_1.0_quant_2018_06_29.zip">Download
model and labels</a>
Please find [object detection models](https://tfhub.dev/s?deployment-format=lite&module-type=image-object-detection)
from TensorFlow Hub.
## Pose estimation
For more information about pose estimation, see
<a href="../models/pose_estimation/overview.md">Pose estimation</a>.
The pose estimation model we currently host is
**multi_person_mobilenet_v1_075_float**.
<a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/tflite/gpu/multi_person_mobilenet_v1_075_float.tflite">Download
model</a>
Please find [pose estimation models](https://tfhub.dev/s?deployment-format=lite&module-type=image-pose-detection)
from TensorFlow Hub.
## Image segmentation
For more information about image segmentation, see
<a href="../models/segmentation/overview.md">Segmentation</a>.
The image segmentation model we currently host is **deeplabv3_257_mv_gpu**.
<a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/tflite/gpu/deeplabv3_257_mv_gpu.tflite">Download
model</a>
Please find [image segmentation models](https://tfhub.dev/s?deployment-format=lite&module-type=image-segmentation)
from TensorFlow Hub.
## Question and Answer
For more information about text classification with Mobile BERT, see
<a href="../models/bert_qa/overview.md">Question And Answer</a>.
Please find [Mobile BERT model](https://tfhub.dev/tensorflow/mobilebert/1) from
TensorFlow Hub.
## Smart reply
For more information about smart reply, see
<a href="../models/smart_reply/overview.md">Smart reply</a>.
The smart reply model we currently host is **smartreply_1.0_2017_11_01**.
<a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/smartreply_1.0_2017_11_01.zip">Download
model</a>
Please find [Smart Reply model](https://tfhub.dev/tensorflow/smartreply/1) from
TensorFlow Hub.