add big files

SERVER_CODE/cnn_classifier.py

@@ -0,0 +1,57 @@
+import librosa
+import librosa.display
+import os
+import numpy as np
+import matplotlib.pyplot as plt
+from keras.models import model_from_json
+from keras import optimizers
+from keras_preprocessing.image import ImageDataGenerator
+
+class classifier(object):
+    def __init__(self, model, weight):
+        json_file = open(model, 'r')
+        loaded_model_json = json_file.read()
+        json_file.close()
+        self.loaded_model = model_from_json(loaded_model_json)
+        self.loaded_model.load_weights(weight)
+        self.datagen=ImageDataGenerator(rescale=1./255.,validation_split=0.25)
+        self.loaded_model.compile(optimizers.rmsprop(lr=0.0005, decay=1e-6),loss="categorical_crossentropy",metrics=["accuracy"])
+        self.loaded_model.summary()
+
+    def predict(self,wav_to_predict):
+        image = self.create_spectrogram(wav_to_predict)
+        predict_generator = self.datagen.flow_from_directory(
+                directory="images_to_predict/",
+                batch_size=128,
+                seed=42,
+                shuffle=False,
+                class_mode="categorical",
+                target_size=(64,64))
+        prediction = self.loaded_model.predict_generator(predict_generator,steps=1)
+        os.remove(image)
+        predicted_class_indices=np.argmax(prediction,axis=1)
+        labels = {'anser': 0, 'columba': 1, 'hirundo': 2, 'passer': 3, 'sturnus': 4, 'turdus': 5, 'upupa': 6}
+        labels = dict((v,k) for k,v in labels.items())
+        predictions = [labels[k] for k in predicted_class_indices]
+        print("The sound was a : ", predictions[0])
+        return predictions
+    
+    def create_spectrogram(self, wav):
+        plt.interactive(False)
+        clip, sample_rate = librosa.load(wav, sr=None)
+        fig = plt.figure(figsize=[0.72,0.72])
+        ax = fig.add_subplot(111)
+        ax.axes.get_xaxis().set_visible(False)
+        ax.axes.get_yaxis().set_visible(False)
+        ax.set_frame_on(False)
+        spectogram = librosa.feature.melspectrogram(y=clip, sr=sample_rate)
+        librosa.display.specshow(librosa.power_to_db(spectogram, ref=np.max))
+        if not os.path.exists("images_to_predict/unknown/"):
+            os.makedirs("images_to_predict/unknown/")
+        file_name  = "images_to_predict/unknown/"+wav[:-4]+ '.jpg'
+        plt.savefig(file_name, dpi=400, bbox_inches='tight',pad_inches=0)
+        plt.close()    
+        fig.clf()
+        plt.close(fig)
+        plt.close('all')
+        return file_name