sync ms model

README.md

@@ -9,12 +9,18 @@ tags:
 - art
 metrics:
 - accuracy
-pipeline_tag: image-classification
+pipeline_tag: audio-classification
 library_name: https://github.com/monetjoe/Piano-Classification
 ---
 
 This study, based on deep learning technology, draws inspiration from classical backbone network structures in the computer vision domain to construct an innovative 8-class piano timbre discriminator model through audio data processing. The model focuses on eight brands and types of pianos, including Kawai, Kawai Grand, YOUNG CHANG, HSINGHAI, Steinway Theatre, Steinway Grand, Pearl River, and Yamaha. By transforming audio data into Mel spectrograms and conducting supervised learning in the fine-tuning phase, the model accurately distinguishes different piano timbres and performs well in practical testing. In the training process, a large-scale annotated audio dataset is utilized, and the introduction of deep learning technology provides crucial support for improving the model's performance by progressively learning to extract key features from audio. The piano timbre discriminator model has broad potential applications in music assessment, audio engineering, and other fields, offering an advanced and reliable solution for piano timbre discrimination. This study expands new possibilities for the application of deep learning in the audio domain, providing valuable references for future research and applications in related fields.
 
+## Usage
+```python
+from modelscope import snapshot_download
+model_dir = snapshot_download('ccmusic-database/pianos')
+```
+
 ## Maintenance
 ```bash
 GIT_LFS_SKIP_SMUDGE=1 git clone git@hf.co:ccmusic-database/pianos
@@ -23,7 +29,6 @@ cd pianos
 
 ## Results
 A demo result of SqueezeNet fine-tuning:
-
 <style>
   #pianos td {
     vertical-align: middle !important;
@@ -36,15 +41,15 @@ A demo result of SqueezeNet fine-tuning:
 <table id="pianos">
     <tr>
         <th>Loss curve</th>
-        <td><img src="https://huggingface.co/ccmusic-database/pianos/resolve/main/loss.jpg"></td>
+        <td><img src="./loss.jpg"></td>
     </tr>
     <tr>
         <th>Training and validation accuracy</th>
-        <td><img src="https://huggingface.co/ccmusic-database/pianos/resolve/main/acc.jpg"></td>
+        <td><img src="./acc.jpg"></td>
     </tr>
     <tr>
         <th>Confusion matrix</th>
-        <td><img src="https://huggingface.co/ccmusic-database/pianos/resolve/main/mat.jpg"></td>
+        <td><img src="./mat.jpg"></td>
     </tr>
 </table>
 

acc.csv

@@ -1,41 +0,0 @@
-tra_acc_list,val_acc_list,lr_list
-48.13950386769805,46.7982924226254,0.001
-58.64897305948252,57.1504802561366,0.001
-63.230194718591626,62.4332977588047,0.001
-68.17151240330755,67.2358591248666,0.001
-71.53907708722326,69.05016008537886,0.001
-73.25286743131501,69.74386339381003,0.001
-78.9877300613497,77.96157950907151,0.001
-79.93464923979728,78.54855923159018,0.001
-82.78874366497733,82.07043756670224,0.001
-84.15577487329955,82.49733191035219,0.001
-85.96292344625233,84.04482390608324,0.001
-84.76260336089624,82.55069370330843,0.001
-87.34995998933049,84.95197438633937,0.001
-88.38356895172046,86.49946638207044,0.001
-88.2568684982662,85.80576307363927,0.001
-90.86423046145639,89.70117395944503,0.0001
-91.42437983462257,88.58057630736393,0.0001
-92.06455054681248,89.2742796157951,0.0001
-92.11789810616165,90.12806830309499,0.0001
-91.96452387303282,89.64781216648879,0.0001
-92.13123499599894,90.87513340448238,0.0001
-92.71138970392104,90.18143009605123,1e-05
-92.47132568684982,90.71504802561367,1e-05
-92.69805281408375,90.82177161152615,1e-05
-92.68471592424646,90.92849519743864,1e-05
-92.16457722059216,91.03521878335113,1e-05
-92.39797279274472,91.46211312700106,1e-05
-92.53134169111763,90.18143009605123,1e-05
-92.61803147506001,90.07470651013874,1e-05
-92.61136303014138,90.18143009605123,1e-05
-92.47132568684982,90.0213447171825,1e-05
-92.79141104294479,89.70117395944503,1e-05
-92.73806348359562,90.18143009605123,1.0000000000000002e-06
-92.50466791144305,90.2881536819637,1.0000000000000002e-06
-92.61803147506001,90.92849519743864,1.0000000000000002e-06
-92.44465190717524,90.92849519743864,1.0000000000000002e-06
-92.65804214457188,90.66168623265742,1.0000000000000002e-06
-92.4979994665244,90.44823906083245,1.0000000000000002e-06
-92.60469458522273,90.34151547491996,1.0000000000000002e-07
-92.81808482261937,90.98185699039489,1.0000000000000002e-07

mat.csv

@@ -1,8 +0,0 @@
-3.946666666666666379e-02,5.333333333333333589e-04,3.200000000000000153e-03,0.000000000000000000e+00,1.600000000000000077e-03,0.000000000000000000e+00,0.000000000000000000e+00,1.066666666666666718e-03
-0.000000000000000000e+00,1.946666666666666545e-01,5.333333333333333589e-04,2.666666666666666578e-03,5.333333333333333155e-03,0.000000000000000000e+00,3.200000000000000153e-03,2.666666666666666578e-03
-3.733333333333333295e-03,2.133333333333333436e-03,2.048000000000000098e-01,3.733333333333333295e-03,5.333333333333333589e-04,0.000000000000000000e+00,5.333333333333333589e-04,2.133333333333333436e-03
-1.600000000000000077e-03,2.133333333333333436e-03,3.200000000000000153e-03,9.493333333333332791e-02,1.066666666666666718e-03,0.000000000000000000e+00,6.933333333333333015e-03,2.133333333333333436e-03
-1.600000000000000077e-03,2.666666666666666578e-03,0.000000000000000000e+00,5.333333333333333589e-04,7.040000000000000424e-02,1.066666666666666718e-03,2.666666666666666578e-03,2.666666666666666578e-03
-0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,5.333333333333333589e-04,0.000000000000000000e+00,7.946666666666667156e-02,0.000000000000000000e+00,0.000000000000000000e+00
-0.000000000000000000e+00,1.066666666666666718e-03,1.066666666666666718e-03,4.266666666666666871e-03,1.066666666666666718e-03,0.000000000000000000e+00,1.157333333333333270e-01,5.333333333333333155e-03
-1.066666666666666718e-03,1.600000000000000077e-03,5.333333333333333589e-04,1.600000000000000077e-03,1.600000000000000077e-03,0.000000000000000000e+00,9.066666666666667318e-03,1.098666666666666680e-01

result.log

@@ -1,21 +0,0 @@
-              precision    recall  f1-score   support
-
-  PearlRiver      0.831     0.860     0.846        86
-  YoungChang      0.951     0.931     0.941       392
-  Steinway-T      0.960     0.941     0.950       408
-    Hsinghai      0.877     0.848     0.862       210
-       Kawai      0.863     0.863     0.863       153
-    Steinway      0.987     0.993     0.990       150
-     Kawai-G      0.838     0.900     0.868       241
-      Yamaha      0.873     0.877     0.875       235
-
-    accuracy                          0.909      1875
-   macro avg      0.897     0.902     0.899      1875
-weighted avg      0.910     0.909     0.910      1875
-
-Backbone     : squeezenet1_1
-Start time   : 2024-01-08 21:56:02
-Finish time  : 2024-01-08 23:20:54
-Time cost    : 5092s
-Full finetune: True
-Focal loss   : True

save.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c909b4adf93fc850ac5284e62ea23c64a4fa558ac4242e88b70cfae2be166163
-size 3319671