1
我正在使用keras來訓練具有3層的我的順序模型,並且想要在TensorBoard中可視化梯度直方圖。爲此,在keras.callbacks.Tensorboard中有函數「write_grads」,如果您定義的histogram_freq大於0(keras docu),它應該可以工作。我所做的:如何使用TensorBoard write_grads函數?
### tensorboard call
callback_tb = keras.callbacks.TensorBoard(log_dir="logs/"+ name, write_graph = True, write_grads = True, histogram_freq=10)
### some other callbacks
reduce_lr = keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=10, min_lr=0.001, verbose = 1)
early = keras.callbacks.EarlyStopping(monitor='val_loss', min_delta=5, patience=10, verbose=1, mode='auto')
checkpointer = keras.callbacks.ModelCheckpoint(filepath='tmp/'+name+'.hdf5', verbose=1, save_best_only=True)
### model fit
model.fit(
X_train, y_train,
batch_size=1, nb_epoch=epochs, validation_split=0.05, verbose = 1,class_weight ={0: 1, 1: 0.5}, callbacks = [callback_tb, reduce_lr, early, checkpointer])
我有這個模型configuartion:
model = Sequential()
layers = [1, 100, 100, 100, 1]
model.add(GRU(
layers[1],
#batch_size = 209,
input_shape=(sequence_length, anzahl_features),
return_sequences=True))
model.add(Dropout(dropout_1))
model.add(LSTM(
layers[2],
#batch_size = 209,
return_sequences=True))
model.add(Dropout(dropout_2))
model.add(GRU(
layers[3],
#batch_size = 209,
return_sequences=False))
model.add(Dropout(dropout_3))
model.add(Dense(
layers[4]))
model.add(Activation('sigmoid'))
print(model.summary())
和錯誤消息我得到的是以下之一:
TypeError: init() got an unexpected keyword argument 'write_grads'
是不是有什麼毛病我configuartion ?我可以使用此模型並獲取梯度直方圖 ?或者這些直方圖僅適用於某種類型的模型?
只是另一個問題出現在那個話題上。目前只有偏移和內核在直方圖中可視化。我怎樣才能得到重量? –
那麼內核就是權重。 – Francesco
謝謝......現在也在文檔中找到它。 –