Add paddlespeech.cls and esc50 example.

examples/esc50/README.md

@@ -28,7 +28,7 @@ PaddleAudio提供了PANNs的CNN14、CNN10和CNN6的预训练模型，可供用
 $ CUDA_VISIBLE_DEVICES=0 ./run.sh 1
 ```
 
-`paddlespeech/cls/exps/PANNs/train.py` 脚本中可支持配置的参数：
+`paddlespeech/cls/exps/panns/train.py` 脚本中可支持配置的参数：
 
 - `device`: 指定模型预测时使用的设备。
 - `feat_backend`: 选择提取特征的后端，可选`'numpy'`或`'paddle'`，默认为`'numpy'`。
@@ -65,7 +65,7 @@ model = SoundClassifier(backbone, num_class=len(ESC50.label_list))
 $ CUDA_VISIBLE_DEVICES=0 ./run.sh 2
 ```
 
-`paddlespeech/cls/exps/PANNs/predict.py` 脚本中可支持配置的参数：
+`paddlespeech/cls/exps/panns/predict.py` 脚本中可支持配置的参数：
 
 - `device`: 指定模型预测时使用的设备。
 - `wav`: 指定预测的音频文件。
@@ -91,7 +91,7 @@ Cat: 6.579841738130199e-06
 $ CUDA_VISIBLE_DEVICES=0 ./run.sh 3
 ```
 
-`paddlespeech/cls/exps/PANNs/export_model.py` 脚本中可支持配置的参数：
+`paddlespeech/cls/exps/panns/export_model.py` 脚本中可支持配置的参数：
 - `checkpoint`: 模型参数checkpoint文件。
 - `output_dir`: 导出静态图模型和参数文件的保存目录。
 
@@ -106,16 +106,13 @@ export
 
 #### 2. 模型部署和预测
 
-`paddlespeech/cls/exps/PANNs/deploy/predict.py` 脚本使用了`paddle.inference`模块下的api，提供了python端部署的示例：
+`paddlespeech/cls/exps/panns/deploy/predict.py` 脚本使用了`paddle.inference`模块下的api，提供了python端部署的示例：
 
 ```shell
-$ CUDA_VISIBLE_DEVICES=0 ./run.sh 3
-```
-```sh
-python paddlespeech/cls/exps/PANNs/deploy/predict.py --model_dir ./export --device gpu
+$ CUDA_VISIBLE_DEVICES=0 ./run.sh 4
 ```
 
-`paddlespeech/cls/exps/PANNs/deploy/predict.py` 脚本中可支持配置的主要参数：
+`paddlespeech/cls/exps/panns/deploy/predict.py` 脚本中可支持配置的主要参数：
 - `device`: 指定模型预测时使用的设备。
 - `model_dir`: 导出静态图模型和参数文件的保存目录。
 - `wav`: 指定预测的音频文件。

examples/esc50/cls0/local/infer.sh

 #!/bin/bash
 
-device=$1
-audio_file=$2
-ckpt_dir=$3
-feat_backend=$4
+audio_file=$1
+ckpt_dir=$2
+feat_backend=$3
 
 python3 ${BIN_DIR}/predict.py \
---device ${device} \
 --wav ${audio_file} \
 --feat_backend ${feat_backend} \
 --top_k 10 \

examples/esc50/cls0/local/static_model_infer.sh

@@ -8,4 +8,3 @@ python3 ${BIN_DIR}/deploy/predict.py \
 --device ${device} \
 --model_dir ${model_dir} \
 --wav ${audio_file} 
-

examples/esc50/cls0/local/train.sh

 #!/bin/bash
 
 ngpu=$1
-device=$2
-feat_backend=$3
+feat_backend=$2
 
 num_epochs=50
 batch_size=16
 ckpt_dir=./checkpoint
 save_freq=10
 
-if [ ${ngpu} -gt 1 ]; then
+if [ ${ngpu} -gt 0 ]; then
     python3 -m paddle.distributed.launch --gpus $CUDA_VISIBLE_DEVICES ${BIN_DIR}/train.py \
     --epochs ${num_epochs} \
     --feat_backend ${feat_backend} \
@@ -18,7 +17,6 @@ if [ ${ngpu} -gt 1 ]; then
     --save_freq ${save_freq}
 else
     python3 ${BIN_DIR}/train.py \
-    --device ${device} \
     --epochs ${num_epochs} \
     --feat_backend ${feat_backend} \
     --batch_size ${batch_size} \

examples/esc50/cls0/path.sh

@@ -9,5 +9,5 @@ export PYTHONDONTWRITEBYTECODE=1
 export PYTHONIOENCODING=UTF-8
 export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH}
 
-MODEL=PANNs
+MODEL=panns
 export BIN_DIR=${MAIN_ROOT}/paddlespeech/cls/exps/${MODEL}
\ No newline at end of file

examples/esc50/cls0/run.sh

@@ -3,35 +3,31 @@ set -e
 source path.sh
 
 ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
-if [ ${ngpu} == 0 ];then
-    device=cpu
-else
-    device=gpu
-fi
 
 stage=$1
 stop_stage=100
 feat_backend=numpy
+audio_file=~/cat.wav
+ckpt_dir=./checkpoint/epoch_50
+output_dir=./export
+infer_device=cpu
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
-    ./local/train.sh ${ngpu} ${device} ${feat_backend} || exit -1
+    ./local/train.sh ${ngpu} ${feat_backend} || exit -1
     exit 0
 fi
 
-audio_file=~/cat.wav
-ckpt_dir=./checkpoint/epoch_50
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
-    ./local/infer.sh ${device} ${audio_file} ${ckpt_dir} ${feat_backend} || exit -1
+    ./local/infer.sh ${audio_file} ${ckpt_dir} ${feat_backend} || exit -1
     exit 0
 fi
 
-output_dir=./export
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     ./local/export.sh ${ckpt_dir} ${output_dir} || exit -1
     exit 0
 fi
 
 if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
-    ./local/static_model_infer.sh ${device} ${output_dir} ${audio_file} || exit -1
+    ./local/static_model_infer.sh ${infer_device} ${output_dir} ${audio_file} || exit -1
     exit 0
 fi

paddlespeech/cls/exps/PANNs/predict.py → paddlespeech/cls/exps/panns/predict.py

@@ -26,7 +26,6 @@ from paddlespeech.cls.models import SoundClassifier
 
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
-parser.add_argument('--device', choices=['cpu', 'gpu'], default="gpu", help="Select which device to predict, defaults to gpu.")
 parser.add_argument("--wav", type=str, required=True, help="Audio file to infer.")
 parser.add_argument("--feat_backend", type=str, choices=['numpy', 'paddle'], default='numpy', help="Choose backend to extract features from audio files.")
 parser.add_argument("--top_k", type=int, default=1, help="Show top k predicted results")
@@ -51,7 +50,6 @@ def extract_features(file: str, feat_backend: str='numpy',
 
 
 if __name__ == '__main__':
-    paddle.set_device(args.device)
 
     model = SoundClassifier(
         backbone=cnn14(pretrained=False, extract_embedding=True),

paddlespeech/cls/exps/PANNs/train.py → paddlespeech/cls/exps/panns/train.py

@@ -25,7 +25,6 @@ from paddlespeech.cls.models import SoundClassifier
 
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
-parser.add_argument('--device', choices=['cpu', 'gpu'], default="gpu", help="Select which device to train model, defaults to gpu.")
 parser.add_argument("--epochs", type=int, default=50, help="Number of epoches for fine-tuning.")
 parser.add_argument("--feat_backend", type=str, choices=['numpy', 'paddle'], default='numpy', help="Choose backend to extract features from audio files.")
 parser.add_argument("--learning_rate", type=float, default=5e-5, help="Learning rate used to train with warmup.")
@@ -38,7 +37,6 @@ args = parser.parse_args()
 # yapf: enable
 
 if __name__ == "__main__":
-    paddle.set_device(args.device)
     nranks = paddle.distributed.get_world_size()
     if paddle.distributed.get_world_size() > 1:
         paddle.distributed.init_parallel_env()

paddlespeech/cls/models/__init__.py

@@ -11,4 +11,4 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from .PANNs import *
+from .panns import *