How to disable keras warnings?

问题:

When I run the following code:

init = "he_uniform"

inp = Input(shape=(1800, 1))
norm1 = BatchNormalization(mode=0)(inp)
conv1 = Convolution1D(16, 5,  border_mode='same', init=init, activation="relu")(norm1)
pool1 = MaxPooling1D(pool_size=3)(conv1)
norm2 = BatchNormalization(mode=0)(pool1)
flat1 = Flatten()(norm2)
dens1 = Dense(128, init=init, activation="relu")(flat1)
#norm3 = BatchNormalization(mode=0)(dens1)
output = Dense(2, init=init, activation="softmax")(dens1)
from keras.models import *
model = Model(input=[inp], output=output)

I had the warnings:

root/miniconda/envs/jupyterhub_py3/lib/python3.4/site-packages/ipykernel/__main__.py:4: UserWarning: Update your `BatchNormalization` call to the Keras 2 API: `BatchNormalization()`
/root/miniconda/envs/jupyterhub_py3/lib/python3.4/site-packages/ipykernel/__main__.py:5: UserWarning: Update your `Conv1D` call to the Keras 2 API: `Conv1D(16, 5, activation="relu", kernel_initializer="he_uniform", padding="same")`
/root/miniconda/envs/jupyterhub_py3/lib/python3.4/site-packages/ipykernel/__main__.py:7: UserWarning: Update your `BatchNormalization` call to the Keras 2 API: `BatchNormalization()`
/root/miniconda/envs/jupyterhub_py3/lib/python3.4/site-packages/ipykernel/__main__.py:9: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(128, activation="relu", kernel_initializer="he_uniform")`

The following approach did not help.

with warnings.catch_warnings():
    warnings.simplefilter("ignore")

How to disable this warning?

回答1:

You can tell tensorflow using environment variables. From within python:

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

The warnings indicate you are using keras 1.x code with a keras 2.x installation. Maybe it would be easier to fix them, instead of ignoring.

回答2:

You can use this code at the top of the main.py:

def warn(*args, **kwargs):
    pass
import warnings
warnings.warn = warn