diff --git a/README.md b/README.md
index cc560f0ad70a6d74e6175302350f6fb349e16734..8e0e8d9ad21ac742676af1cca6a285d9572db827 100644
--- a/README.md
+++ b/README.md
@@ -13,11 +13,7 @@ The required Python modules are listed in the 'requirement.txt' file. Beware tha
The 'creation_datasets' folder can be used to create the datasets to train and test the AI
To use the AI :
-put in the input folder :
-an "audio_files" folder with the audios and a csv file containing the audios you want to test. The format of the csv is :
-audio_id
-audio1
-audio2
+put in the input folder a csv file with a column audio_id containing the list of the link to the file you want to test the model on
...
no extension on the audio_id column
diff --git a/README.txt b/README.txt
deleted file mode 100644
index 3d6133f1485b9e85e8055549a5ddb55a1068af8e..0000000000000000000000000000000000000000
--- a/README.txt
+++ /dev/null
@@ -1,30 +0,0 @@
-To use the ia :
-put in the input folder :
-an audio_files with the audios and a csv file containing the audios you want to test. The format is :
-audio_id
-audio1
-audio2
-...
-
-no extension on the audio_id column
-Note : the csv can have multiple columns, but only the audio_id is considered
-
-
-To make the training :
-download and preprocess the dataset : in Terminal, put yourself in the "birdcall-detection" folder. Then type "make prepare"
-Wait the download end. Then you can launch the training with "make train".
-If you have not enough RAM, you'd better train models one by one. To do so, write (still in the "birdcall-detection" folder) :
-python train -m 1
-python train -m 2
-python train -m 3
-python train -m 4
-
-Note : If you want to make your own dataset, in the train/data_training folder, put an audio_files folder and a csv with the adequate format :
-cnt,en,id,length
-**,class1,audio1.mp3,**
-**,class1,audio2.mp3,**
-...
-**,class2,audio4.wav,**
-...
-
-where audio.* is just the name of the corresponding audio file and *** are characters that needs to be there but are not important
diff --git a/creation_datasets/audio_files_birds_america/601776.mp3 b/creation_datasets/audio_files_birds_america/601776.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..867547a81ac66ad68c88d4d6c164e325a4475757
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/601776.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/618567.mp3 b/creation_datasets/audio_files_birds_america/618567.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..bd6924fc7d17c087d3a7813590fa7a2fa3d64149
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/618567.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/681816.mp3 b/creation_datasets/audio_files_birds_america/681816.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..851b48afacf55ce797bb60991f73554c54b67c9b
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/681816.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/681907.mp3 b/creation_datasets/audio_files_birds_america/681907.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..4d542f733d8e22ccb52b84cdd870489732360e5e
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/681907.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/690946.mp3 b/creation_datasets/audio_files_birds_america/690946.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..d45942861199e68130dc745c810dd445afa031ad
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/690946.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/705383.mp3 b/creation_datasets/audio_files_birds_america/705383.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..9688af90d897b3f523ba97bcffe559f58379a825
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/705383.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/720038.mp3 b/creation_datasets/audio_files_birds_america/720038.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..1263a1c09819bbcb5167ebe9b40074f2b3a5d67d
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/720038.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/720284.mp3 b/creation_datasets/audio_files_birds_america/720284.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..d400cc098291747faa46105b31829052177955ad
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/720284.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/723797.mp3 b/creation_datasets/audio_files_birds_america/723797.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..7e7c32e8342a0c557424e06efdbc2a32596b512b
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/723797.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/726547.mp3 b/creation_datasets/audio_files_birds_america/726547.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..e93b88c4d44f45a20822d8725f286c9e1929c751
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/726547.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/734890.mp3 b/creation_datasets/audio_files_birds_america/734890.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..67adb7ce0b89c1aeffbe30f22bb070c5c1d82c1b
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/734890.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/739245.mp3 b/creation_datasets/audio_files_birds_america/739245.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..f63c3c92438e869c8f3635e1792da136468d3288
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/739245.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/753154.mp3 b/creation_datasets/audio_files_birds_america/753154.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..e148c0abb16b68981df5ba47bcfc311b5d301ad7
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/753154.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/756861.mp3 b/creation_datasets/audio_files_birds_america/756861.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..ed8c4168c0c808f323e838d3ccd899d2efc2f10d
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/756861.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/756999.mp3 b/creation_datasets/audio_files_birds_america/756999.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..d9892f40d6945e130cac5a197137a08ace1b8c4e
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/756999.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/762166.wav b/creation_datasets/audio_files_birds_america/762166.wav
new file mode 100644
index 0000000000000000000000000000000000000000..680b8ac00a53d7d6d16df0012b2276e2900562d0
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/762166.wav differ
diff --git a/creation_datasets/audio_files_birds_america/762167.wav b/creation_datasets/audio_files_birds_america/762167.wav
new file mode 100644
index 0000000000000000000000000000000000000000..3f7ea385b3fb8315ffe4f09db7062ff1157765ae
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/762167.wav differ
diff --git a/creation_datasets/audio_files_birds_america/772374.mp3 b/creation_datasets/audio_files_birds_america/772374.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..c404b9452eafb97083715130d8b6cf2d12947d00
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/772374.mp3 differ
diff --git a/creation_datasets/audio_files_birds_america/779660.wav b/creation_datasets/audio_files_birds_america/779660.wav
new file mode 100644
index 0000000000000000000000000000000000000000..1cdbd06bafae285eb34a865658ca42b61389cc10
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/779660.wav differ
diff --git a/creation_datasets/audio_files_birds_america/779663.wav b/creation_datasets/audio_files_birds_america/779663.wav
new file mode 100644
index 0000000000000000000000000000000000000000..311ccd346ad93a918ace831a0949835693130299
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/779663.wav differ
diff --git a/creation_datasets/audio_files_birds_america/780537.wav b/creation_datasets/audio_files_birds_america/780537.wav
new file mode 100644
index 0000000000000000000000000000000000000000..1b42b7c8b563400eb5864cc65b99d03c1bf9c686
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/780537.wav differ
diff --git a/creation_datasets/audio_files_birds_america/792018.wav b/creation_datasets/audio_files_birds_america/792018.wav
new file mode 100644
index 0000000000000000000000000000000000000000..cfab2da7122f180e77549d0dcb0f0ee0fdbff416
Binary files /dev/null and b/creation_datasets/audio_files_birds_america/792018.wav differ
diff --git a/detection.py b/detection.py
index a38cd649cfc5e4a90d6639b6827f58710b4e0afb..befb4b41d7994ec45444e5944b972a8c24ec4c7c 100644
--- a/detection.py
+++ b/detection.py
@@ -109,14 +109,13 @@ def prediction_for_clip(test_df: pd.DataFrame,
def prediction(test_df: pd.DataFrame,
- test_audio: Path,
models):
""""given the pass of a folder containing audios and a csv corresponding, it returns a prediction for each audio which need a postprocess"""
unique_audio_id = test_df.audio_id.unique()
warnings.filterwarnings("ignore")
prediction_dfs = []
for audio_id in unique_audio_id:
- clip_path = test_audio + audio_id
+ clip_path = audio_id
test_df_for_audio_id = test_df.query(
f"audio_id == '{audio_id}'").reset_index(drop=True)
with timer(f"Prediction & load on {audio_id}"):
@@ -168,12 +167,11 @@ if __name__ == '__main__':
'weights_trained/'+model+'.pth'))
models[model].to(device)
- test = pd.read_csv("input/test.csv")
- test_audio = "input/audio_files/"
+ test = pd.read_csv("input/test.csv",encoding="utf-8")
test["audio_id"] = test["audio_id"].map(str)
prediction_df = prediction(
- test_df=test, test_audio=test_audio, models=models)
+ test_df=test, models=models)
post_processed = prediction_df
if not prediction_df.empty:
diff --git a/input/audio_files/.placeholder b/input/audio_files/.placeholder
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/requirement.txt b/requirement.txt
index 31022b72b3a9693f064d56be71084bae7532d800..a76c96cf71f94f1cb619ff8ee7356f00abd22ace 100644
--- a/requirement.txt
+++ b/requirement.txt
@@ -1,5 +1,4 @@
-anaconda-client==1.11.1
-anaconda-project==0.11.1
+anaconda-client==1.1.1
appdirs==1.4.4
astroid==2.15.3
asttokens==2.2.1
@@ -18,15 +17,12 @@ cffi==1.15.1
chardet==4.0.0
charset-normalizer==2.0.4
click==8.0.4
-clyent==1.2.2
+clyent==1.2.1
colorama==0.4.6
comm==0.1.3
-conda-content-trust==0.1.3
+conda-content-trust==0.1.2
conda-pack==0.6.0
-conda-package-handling==2.0.2
conda_package_streaming==0.7.0
-conda-repo-cli==1.0.41
-conda-verify==3.4.2
contourpy==1.0.7
cryptography==39.0.1
cycler==0.11.0
@@ -64,7 +60,6 @@ MarkupSafe==2.1.1
matplotlib==3.7.1
matplotlib-inline==0.1.6
mccabe==0.7.0
-menuinst==1.4.19
mkl-fft==1.3.1
mkl-random==1.2.2
mkl-service==2.4.0
@@ -92,7 +87,7 @@ pooch==1.6.0
prompt-toolkit==3.0.38
psutil==5.9.0
pure-eval==0.2.2
-pycosat==0.6.4
+pycosat==0.6.3
pycparser==2.21
Pygments==2.14.0
PyJWT==2.4.0
@@ -112,9 +107,7 @@ pyzmq==25.0.2
QtPy==2.2.0
requests==2.28.1
resampy==0.4.2
-ruamel.yaml==0.17.21
-ruamel.yaml.clib==0.2.6
-ruamel-yaml-conda==0.17.21
+
scikit-learn==1.2.2
scipy==1.10.1
setuptools==65.6.3
@@ -146,4 +139,9 @@ win-inet-pton==1.1.0
wincertstore==0.2
wrapt==1.15.0
zipp==3.15.0
-zstandard==0.19.0
\ No newline at end of file
+zstandard==0.19.0
+Cython==0.29.35
+opencv-python
+resampy
+ruamel.yaml==0.17.21
+ruamel.yaml.clib==0.2.6
\ No newline at end of file
diff --git a/src/models.py b/src/models.py
index 443a00ab79c3978600069fa849f7b686b0b7c748..978201a0659979b37e87ca76bc00d1ef00eaa9ab 100644
--- a/src/models.py
+++ b/src/models.py
@@ -1629,7 +1629,7 @@ def get_model(resnest_config: dict, effnet_config: dict, weights_path: dict):
model = ResNestSED(**resnest_config)
else:
model = EfficientNetSED(**effnet_config)
- checkpoint = torch.load(path_dict[path_key])
+ checkpoint = torch.load(path_dict[path_key],map_location="cuda" if torch.cuda.is_available() else "cpu")
model_state_dict = {}
for key in checkpoint["model_state_dict"]:
if key == "n_averaged":