Skip to content

Commit

Permalink
Merge pull request ARM-software#44 from ARM-software/kws_models_update
Browse files Browse the repository at this point in the history
KWS models - update
orly-arm authored Jan 5, 2022
2 parents 7d96402 + 48a22ee commit b9e26e6
Showing 38 changed files with 100 additions and 92 deletions.
13 changes: 6 additions & 7 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@

# Model Zoo
![version](https://img.shields.io/badge/version-21.08-0091BD)
> A collection of machine learning models optimized for Arm IP.
@@ -109,7 +108,7 @@
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">0.929</td>
<td align="center">0.931</td>
</tr>
<tr>
<td><a href="models/keyword_spotting/cnn_medium/tflite_int8">CNN Medium INT8 *</a></td>
@@ -119,7 +118,7 @@
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">0.913</td>
<td align="center">0.911</td>
</tr>
<tr>
<td><a href="models/keyword_spotting/cnn_small/tflite_int8">CNN Small INT8 *</a></td>
@@ -129,7 +128,7 @@
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">0.914</td>
<td align="center">0.912</td>
</tr>
<tr>
<td><a href="models/keyword_spotting/dnn_large/tflite_int8">DNN Large INT8 *</a></td>
@@ -149,7 +148,7 @@
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">0.846</td>
<td align="center">0.844</td>
</tr>
<tr>
<td><a href="models/keyword_spotting/dnn_small/tflite_int8">DNN Small INT8 *</a></td>
@@ -159,7 +158,7 @@
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">0.827</td>
<td align="center">0.825</td>
</tr>
<tr>
<td><a href="models/keyword_spotting/ds_cnn_large/tflite_clustered_fp32">DS-CNN Clustered FP32 *</a></td>
@@ -199,7 +198,7 @@
<td align="center">:heavy_check_mark: HERO</td>
<td align="center">:heavy_check_mark: </td>
<td align="center">:heavy_check_mark: </td>
<td align="center">0.934</td>
<td align="center">0.941</td>
</tr>
<tr>
<td><a href="models/keyword_spotting/ds_cnn_small/tflite_int8">DS-CNN Small INT8 *</a></td>
6 changes: 3 additions & 3 deletions models/keyword_spotting/cnn_large/tflite_int8/README.md
Original file line number Diff line number Diff line change
@@ -17,8 +17,8 @@ Code to recreate this model can be found here: https://github.com/ARM-software/M
| Network Information | Value |
|---------------------|------------------|
| Framework | TensorFlow Lite |
| SHA-1 Hash | 59e6986c3eca496fa3d54176ac66bb7dc9ff36e0 |
| Size (Bytes) | 486560 |
| SHA-1 Hash | a61ab748ae8f52f78ab568342db67a792c6ecf34 |
| Size (Bytes) | 484600 |
| Provenance | https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m |
| Paper | https://arxiv.org/abs/1711.07128 |

@@ -27,7 +27,7 @@ Dataset: Google Speech Commands Test Set

| Metric | Value |
|--------|-------|
| Accuracy | 0.929 |
| Accuracy | 0.931 |

## Performance
| Platform | Optimized |
Git LFS file not shown
7 changes: 4 additions & 3 deletions models/keyword_spotting/cnn_large/tflite_int8/definition.yaml
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.929
Accuracy: 93.09%
description: 'This is a fully quantized version (asymmetrical int8) of the CNN Large
model developed by Arm, with training checkpoints, from the Hello Edge paper. Code
to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
license:
- Apache-2.0
network:
file_size_bytes: 486560
file_size_bytes: 484600
filename: cnn_l_quantized.tflite
framework: TensorFlow Lite
hash:
algorithm: sha1
value: 59e6986c3eca496fa3d54176ac66bb7dc9ff36e0
value: a61ab748ae8f52f78ab568342db67a792c6ecf34
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: null
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 490)
Git LFS file not shown
Git LFS file not shown
6 changes: 3 additions & 3 deletions models/keyword_spotting/cnn_medium/tflite_int8/README.md
Original file line number Diff line number Diff line change
@@ -17,8 +17,8 @@ Code to recreate this model can be found here: https://github.com/ARM-software/M
| Network Information | Value |
|---------------------|------------------|
| Framework | TensorFlow Lite |
| SHA-1 Hash | 389c6c2c7d289c0018e2dabcc66271811e52874c |
| Size (Bytes) | 187840 |
| SHA-1 Hash | 6bc68074d960bbb0c695e19fd96fd7903131ef60 |
| Size (Bytes) | 186064 |
| Provenance | https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m |
| Paper | https://arxiv.org/abs/1711.07128 |

@@ -27,7 +27,7 @@ Dataset: Google Speech Commands Test Set

| Metric | Value |
|--------|-------|
| Accuracy | 0.913 |
| Accuracy | 0.911 |

## Performance
| Platform | Optimized |
Git LFS file not shown
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.913
Accuracy: 91.08%
description: 'This is a fully quantized version (asymmetrical int8) of the CNN Medium
model developed by Arm, with training checkpoints, from the Hello Edge paper. Code
to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
license:
- Apache-2.0
network:
file_size_bytes: 187840
file_size_bytes: 186064
filename: cnn_m_quantized.tflite
framework: TensorFlow Lite
hash:
algorithm: sha1
value: 389c6c2c7d289c0018e2dabcc66271811e52874c
value: 6bc68074d960bbb0c695e19fd96fd7903131ef60
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: null
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 490)
Git LFS file not shown
Git LFS file not shown
6 changes: 3 additions & 3 deletions models/keyword_spotting/cnn_small/tflite_int8/README.md
Original file line number Diff line number Diff line change
@@ -17,8 +17,8 @@ Code to recreate this model can be found here: https://github.com/ARM-software/M
| Network Information | Value |
|---------------------|------------------|
| Framework | TensorFlow Lite |
| SHA-1 Hash | d3c8f4b468545d7012383f2a312bef6245a3b599 |
| Size (Bytes) | 76752 |
| SHA-1 Hash | 3415f88dfb8f78fe47d282d68ccbc3ce71a7510f |
| Size (Bytes) | 75400 |
| Provenance | https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m |
| Paper | https://arxiv.org/abs/1711.07128 |

@@ -27,7 +27,7 @@ Dataset: Google Speech Commands Test Set

| Metric | Value |
|--------|-------|
| Accuracy | 0.914 |
| Accuracy | 0.912 |

## Performance
| Platform | Optimized |
Git LFS file not shown
7 changes: 4 additions & 3 deletions models/keyword_spotting/cnn_small/tflite_int8/definition.yaml
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.914
Accuracy: 91.23%
description: 'This is a fully quantized version (asymmetrical int8) of the CNN Small
model developed by Arm, with training checkpoints, from the Hello Edge paper. Code
to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
license:
- Apache-2.0
network:
file_size_bytes: 76752
file_size_bytes: 75400
filename: cnn_s_quantized.tflite
framework: TensorFlow Lite
hash:
algorithm: sha1
value: d3c8f4b468545d7012383f2a312bef6245a3b599
value: 3415f88dfb8f78fe47d282d68ccbc3ce71a7510f
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: null
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 490)
Git LFS file not shown
Git LFS file not shown
4 changes: 2 additions & 2 deletions models/keyword_spotting/dnn_large/tflite_int8/README.md
Original file line number Diff line number Diff line change
@@ -17,8 +17,8 @@ Code to recreate this model can be found here: https://github.com/ARM-software/M
| Network Information | Value |
|---------------------|------------------|
| Framework | TensorFlow Lite |
| SHA-1 Hash | 16e03dda20ae81dfba6a567e6e7563ca67596969 |
| Size (Bytes) | 502928 |
| SHA-1 Hash | 2b1ee34e4c87ba6f24092c7457593227099efaf1 |
| Size (Bytes) | 502272 |
| Provenance | https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m |
| Paper | https://arxiv.org/abs/1711.07128 |

7 changes: 4 additions & 3 deletions models/keyword_spotting/dnn_large/tflite_int8/definition.yaml
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.863
Accuracy: 86.26%
description: 'This is a fully quantized version (asymmetrical int8) of the DNN Large
model developed by Arm, with training checkpoints, from the Hello Edge paper. Code
to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
license:
- Apache-2.0
network:
file_size_bytes: 502928
file_size_bytes: 502272
filename: dnn_l_quantized.tflite
framework: TensorFlow Lite
hash:
algorithm: sha1
value: 16e03dda20ae81dfba6a567e6e7563ca67596969
value: 2b1ee34e4c87ba6f24092c7457593227099efaf1
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: null
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 250)
Git LFS file not shown
Git LFS file not shown
Git LFS file not shown
6 changes: 3 additions & 3 deletions models/keyword_spotting/dnn_medium/tflite_int8/README.md
Original file line number Diff line number Diff line change
@@ -17,8 +17,8 @@ Code to recreate this model can be found here: https://github.com/ARM-software/M
| Network Information | Value |
|---------------------|------------------|
| Framework | TensorFlow Lite |
| SHA-1 Hash | 57ad3cf78f736819b8897f5de51f7e9a4cbd5689 |
| Size (Bytes) | 204480 |
| SHA-1 Hash | 7e138f99cfc6a603a1fc735a2d9c3e28a41a6a43 |
| Size (Bytes) | 203832 |
| Provenance | https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m |
| Paper | https://arxiv.org/abs/1711.07128 |

@@ -27,7 +27,7 @@ Dataset: Google Speech Commands Test Set

| Metric | Value |
|--------|-------|
| Accuracy | 0.846 |
| Accuracy | 0.844 |

## Performance
| Platform | Optimized |
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.846
Accuracy: 84.44%
description: 'This is a fully quantized version (asymmetrical int8) of the DNN Medium
model developed by Arm, with training checkpoints, from the Hello Edge paper. Code
to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
license:
- Apache-2.0
network:
file_size_bytes: 204480
file_size_bytes: 203832
filename: dnn_m_quantized.tflite
framework: TensorFlow Lite
hash:
algorithm: sha1
value: 57ad3cf78f736819b8897f5de51f7e9a4cbd5689
value: 7e138f99cfc6a603a1fc735a2d9c3e28a41a6a43
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: null
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 250)
Git LFS file not shown
Git LFS file not shown
Git LFS file not shown
6 changes: 3 additions & 3 deletions models/keyword_spotting/dnn_small/tflite_int8/README.md
Original file line number Diff line number Diff line change
@@ -17,8 +17,8 @@ Code to recreate this model can be found here: https://github.com/ARM-software/M
| Network Information | Value |
|---------------------|------------------|
| Framework | TensorFlow Lite |
| SHA-1 Hash | 5b00a7eb54eb2650c50026ddef2b3134a71ab6cf |
| Size (Bytes) | 84192 |
| SHA-1 Hash | 4b92e09fb43b2f042ce2811b91c7c67bf7186b6b |
| Size (Bytes) | 83544 |
| Provenance | https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m |
| Paper | https://arxiv.org/abs/1711.07128 |

@@ -27,7 +27,7 @@ Dataset: Google Speech Commands Test Set

| Metric | Value |
|--------|-------|
| Accuracy | 0.827 |
| Accuracy | 0.825 |

## Performance
| Platform | Optimized |
7 changes: 4 additions & 3 deletions models/keyword_spotting/dnn_small/tflite_int8/definition.yaml
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.827
Accuracy: 82.45%
description: 'This is a fully quantized version (asymmetrical int8) of the DNN Small
model developed by Arm, with training checkpoints, from the Hello Edge paper. Code
to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
license:
- Apache-2.0
network:
file_size_bytes: 84192
file_size_bytes: 83544
filename: dnn_s_quantized.tflite
framework: TensorFlow Lite
hash:
algorithm: sha1
value: 5b00a7eb54eb2650c50026ddef2b3134a71ab6cf
value: 4b92e09fb43b2f042ce2811b91c7c67bf7186b6b
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: null
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 250)
Git LFS file not shown
Git LFS file not shown
Git LFS file not shown
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.946
Accuracy: 94.58%
description: 'This is a fully quantized version (asymmetrical int8) of the DS-CNN
Large model developed by Arm, with training checkpoints, from the Hello Edge paper.
Code to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
@@ -14,6 +14,7 @@ network:
algorithm: sha1
value: 504f8e7bfa5c0f15c5475e5d08637b3b8aad0972
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: hero#CORTEX-M
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 490)
6 changes: 3 additions & 3 deletions models/keyword_spotting/ds_cnn_medium/tflite_int8/README.md
Original file line number Diff line number Diff line change
@@ -17,8 +17,8 @@ Code to recreate this model can be found here: https://github.com/ARM-software/M
| Network Information | Value |
|---------------------|------------------|
| Framework | TensorFlow Lite |
| SHA-1 Hash | c6923b02806224775b58ab9bc11e03e021ff407e |
| Size (Bytes) | 200928 |
| SHA-1 Hash | 740d32adde16948b2ab45e1e8c856de2925a05eb |
| Size (Bytes) | 186288 |
| Provenance | https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m |
| Paper | https://arxiv.org/abs/1711.07128 |

@@ -27,7 +27,7 @@ Dataset: Google Speech Commands Test Set

| Metric | Value |
|--------|-------|
| Accuracy | 0.934 |
| Accuracy | 0.941 |

## Performance
| Platform | Optimized |
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.934
Accuracy: 94.13%
description: 'This is a fully quantized version (asymmetrical int8) of the DS-CNN
Medium model developed by Arm, with training checkpoints, from the Hello Edge paper.
Code to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
license:
- Apache-2.0
network:
file_size_bytes: 200928
file_size_bytes: 186288
filename: ds_cnn_m_quantized.tflite
framework: TensorFlow Lite
hash:
algorithm: sha1
value: c6923b02806224775b58ab9bc11e03e021ff407e
value: 740d32adde16948b2ab45e1e8c856de2925a05eb
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: hero#CORTEX-M
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 490)
Git LFS file not shown
Git LFS file not shown
Git LFS file not shown
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
benchmark:
Google Speech Commands test set:
Accuracy: 0.935
Accuracy: 93.56%
description: 'This is a fully quantized version (asymmetrical int8) of the DS-CNN
Small model developed by Arm, with training checkpoints, from the Hello Edge paper.
Code to recreate this model can be found here: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m'
@@ -14,6 +14,7 @@ network:
algorithm: sha1
value: cf24429e86a9647b1632c382894bc68d26d34039
provenance: https://github.com/ARM-software/ML-examples/tree/master/tflu-kws-cortex-m
quality_level: hero#CORTEX-M
network_parameters:
input_nodes:
- description: The input is a processed MFCCs of shape (1, 490)

0 comments on commit b9e26e6

Please sign in to comment.