我正在研究FrançoisChollet（publisher webpage，notebooks on github）的“ Python深度学习”。复制第6章中的示例时，我遇到了GRU层（经常丢失）的问题（我相信）。
我最初观察到这些错误的代码很长，所以我决定坚持最简单的问题，该问题可以复制该错误：将IMDB评论分为“正”和“负”类别。
[当我使用具有经常性辍学的GRU层时，训练损失（在几个批次的第一个时期之后）取nan的“值”，而训练精度（从第二个时期开始）取值为0。
64/12000 [..............................] - ETA: 3:05 - loss: 0.6930 - accuracy: 0.4844
128/12000 [..............................] - ETA: 2:09 - loss: 0.6926 - accuracy: 0.4766
192/12000 [..............................] - ETA: 1:50 - loss: 0.6910 - accuracy: 0.5573
(...)
3136/12000 [======>.......................] - ETA: 59s - loss: 0.6870 - accuracy: 0.5635
3200/12000 [=======>......................] - ETA: 58s - loss: 0.6862 - accuracy: 0.5650
3264/12000 [=======>......................] - ETA: 58s - loss: 0.6860 - accuracy: 0.5650
3328/12000 [=======>......................] - ETA: 57s - loss: nan - accuracy: 0.5667
3392/12000 [=======>......................] - ETA: 57s - loss: nan - accuracy: 0.5560
3456/12000 [=======>......................] - ETA: 56s - loss: nan - accuracy: 0.5457
(...)
11840/12000 [============================>.] - ETA: 1s - loss: nan - accuracy: 0.1593
11904/12000 [============================>.] - ETA: 0s - loss: nan - accuracy: 0.1584
11968/12000 [============================>.] - ETA: 0s - loss: nan - accuracy: 0.1576
12000/12000 [==============================] - 83s 7ms/step - loss: nan - accuracy: 0.1572 - val_loss: nan - val_accuracy: 0.0000e+00
Epoch 2/20
64/12000 [..............................] - ETA: 1:16 - loss: nan - accuracy: 0.0000e+00
128/12000 [..............................] - ETA: 1:15 - loss: nan - accuracy: 0.0000e+00
192/12000 [..............................] - ETA: 1:16 - loss: nan - accuracy: 0.0000e+00
(...)
11840/12000 [============================>.] - ETA: 1s - loss: nan - accuracy: 0.0000e+00
11904/12000 [============================>.] - ETA: 0s - loss: nan - accuracy: 0.0000e+00
11968/12000 [============================>.] - ETA: 0s - loss: nan - accuracy: 0.0000e+00
12000/12000 [==============================] - 82s 7ms/step - loss: nan - accuracy: 0.0000e+00 - val_loss: nan - val_accuracy: 0.0000e+00
Epoch 3/20
64/12000 [..............................] - ETA: 1:18 - loss: nan - accuracy: 0.0000e+00
128/12000 [..............................] - ETA: 1:18 - loss: nan - accuracy: 0.0000e+00
192/12000 [..............................] - ETA: 1:16 - loss: nan - accuracy: 0.0000e+00
(...)
为了找到解决方案，我编写了下面提供的代码，该代码经过几种模型（GRU / LSTM，{无辍学，仅“正常”辍学，仅经常性辍学，“正常”和经常性辍学，rmsprop / adam}）并提出所有这些模型的损失和准确性。 （它还会为每个模型创建较小的单独图形。）
# Based on examples from "Deep Learning with Python" by François Chollet:
## Constants, modules:
VERSION = 2
import os
from keras import models
from keras import layers
import matplotlib.pyplot as plt
import pylab
## Loading data:
from keras.datasets import imdb
(x_train, y_train), (x_test, y_test) = \
imdb.load_data(num_words=10000)
from keras.preprocessing import sequence
x_train = sequence.pad_sequences(x_train, maxlen=500)
x_test = sequence.pad_sequences(x_test, maxlen=500)
## Dictionary with models' hyperparameters:
MODELS = [
# GRU:
{"no": 1,
"layer_type": "GRU",
"optimizer": "rmsprop",
"dropout": None,
"recurrent_dropout": None},
{"no": 2,
"layer_type": "GRU",
"optimizer": "rmsprop",
"dropout": 0.3,
"recurrent_dropout": None},
{"no": 3,
"layer_type": "GRU",
"optimizer": "rmsprop",
"dropout": None,
"recurrent_dropout": 0.3},
{"no": 4,
"layer_type": "GRU",
"optimizer": "rmsprop",
"dropout": 0.3,
"recurrent_dropout": 0.3},
{"no": 5,
"layer_type": "GRU",
"optimizer": "adam",
"dropout": None,
"recurrent_dropout": None},
{"no": 6,
"layer_type": "GRU",
"optimizer": "adam",
"dropout": 0.3,
"recurrent_dropout": None},
{"no": 7,
"layer_type": "GRU",
"optimizer": "adam",
"dropout": None,
"recurrent_dropout": 0.3},
{"no": 8,
"layer_type": "GRU",
"optimizer": "adam",
"dropout": 0.3,
"recurrent_dropout": 0.3},
# LSTM:
{"no": 9,
"layer_type": "LSTM",
"optimizer": "rmsprop",
"dropout": None,
"recurrent_dropout": None},
{"no": 10,
"layer_type": "LSTM",
"optimizer": "rmsprop",
"dropout": 0.3,
"recurrent_dropout": None},
{"no": 11,
"layer_type": "LSTM",
"optimizer": "rmsprop",
"dropout": None,
"recurrent_dropout": 0.3},
{"no": 12,
"layer_type": "LSTM",
"optimizer": "rmsprop",
"dropout": 0.3,
"recurrent_dropout": 0.3},
{"no": 13,
"layer_type": "LSTM",
"optimizer": "adam",
"dropout": None,
"recurrent_dropout": None},
{"no": 14,
"layer_type": "LSTM",
"optimizer": "adam",
"dropout": 0.3,
"recurrent_dropout": None},
{"no": 15,
"layer_type": "LSTM",
"optimizer": "adam",
"dropout": None,
"recurrent_dropout": 0.3},
{"no": 16,
"layer_type": "LSTM",
"optimizer": "adam",
"dropout": 0.3,
"recurrent_dropout": 0.3},
]
## Adding name:
for model_dict in MODELS:
model_dict["name"] = f"{model_dict['layer_type']}"
model_dict["name"] += f"_d{model_dict['dropout']}" if model_dict['dropout'] is not None else f"_dN"
model_dict["name"] += f"_rd{model_dict['recurrent_dropout']}" if model_dict['recurrent_dropout'] is not None else f"_rdN"
model_dict["name"] += f"_{model_dict['optimizer']}"
## Fucntion - defing and training model:
def train_model(model_dict):
"""Defines and trains a model, outputs history."""
## Defining:
model = models.Sequential()
model.add(layers.Embedding(10000, 32))
recurrent_layer_kwargs = dict()
if model_dict["dropout"] is not None:
recurrent_layer_kwargs["dropout"] = model_dict["dropout"]
if model_dict["recurrent_dropout"] is not None:
recurrent_layer_kwargs["recurrent_dropout"] = model_dict["recurrent_dropout"]
if model_dict["layer_type"] == 'GRU':
model.add(layers.GRU(32, **recurrent_layer_kwargs))
elif model_dict["layer_type"] == 'LSTM':
model.add(layers.LSTM(32, **recurrent_layer_kwargs))
else:
raise ValueError("Wrong model_dict['layer_type'] value...")
model.add(layers.Dense(1, activation='sigmoid'))
## Compiling:
model.compile(
optimizer=model_dict["optimizer"],
loss='binary_crossentropy',
metrics=['accuracy'])
## Training:
history = model.fit(x_train, y_train,
epochs=20,
batch_size=64,
validation_split=0.2)
return history
## Multi-model graphs' parameters:
graph_all_nrow = 4
graph_all_ncol = 4
graph_all_figsize = (20, 20)
assert graph_all_nrow * graph_all_nrow >= len(MODELS)
## Figs and axes of multi-model graphs:
graph_all_loss_fig, graph_all_loss_axs = plt.subplots(graph_all_nrow, graph_all_ncol, figsize=graph_all_figsize)
graph_all_acc_fig, graph_all_acc_axs = plt.subplots(graph_all_nrow, graph_all_ncol, figsize=graph_all_figsize)
## Loop trough all models:
for i, model_dict in enumerate(MODELS):
history = train_model(model_dict)
## Metrics extraction:
loss = history.history['loss']
val_loss = history.history['val_loss']
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
epochs = range(1, len(loss) + 1)
## Single-model grph - loss:
graph_loss_fname = fr"{os.path.basename(__file__).replace('.py', '')}"
graph_loss_fname += fr"_v{VERSION}_{model_dict['no']}_{model_dict['name']}_loss_graph.png"
graph_loss_fig, graph_loss_ax = plt.subplots()
graph_loss_ax.plot(epochs, loss, 'bo', label='Training loss')
graph_loss_ax.plot(epochs, val_loss, 'b', label='Validation loss')
graph_loss_ax.legend()
graph_loss_fig.suptitle("Training and validation loss")
graph_loss_fig.savefig(graph_loss_fname)
pylab.close(graph_loss_fig)
## Single-model grph - accuracy:
graph_acc_fname = fr"{os.path.basename(__file__).replace('.py', '')}"
graph_acc_fname += fr"_v{VERSION}_{model_dict['no']}_{model_dict['name']}_acc_graph.png"
graph_acc_fig, graph_acc_ax = plt.subplots()
graph_acc_ax.plot(epochs, acc, 'bo', label='Training accuracy')
graph_acc_ax.plot(epochs, val_acc, 'b', label='Validation accuracy')
graph_acc_ax.legend()
graph_acc_fig.suptitle("Training and validation acc")
graph_acc_fig.savefig(graph_acc_fname)
pylab.close(graph_acc_fig)
## Position of axes on multi-model graph:
i_row = i // graph_all_ncol
i_col = i % graph_all_ncol
## Adding model metrics to multi-model graph - loss:
graph_all_loss_axs[i_row, i_col].plot(epochs, loss, 'bo', label='Training loss')
graph_all_loss_axs[i_row, i_col].plot(epochs, val_loss, 'b', label='Validation loss')
graph_all_loss_axs[i_row, i_col].set_title(fr"{model_dict['no']}. {model_dict['name']}")
## Adding model metrics to multi-model graph - accuracy:
graph_all_acc_axs[i_row, i_col].plot(epochs, acc, 'bo', label='Training acc')
graph_all_acc_axs[i_row, i_col].plot(epochs, val_acc, 'b', label='Validation acc')
graph_all_acc_axs[i_row, i_col].set_title(fr"{model_dict['no']}. {model_dict['name']}")
## Saving multi-model graphs:
# Output files are quite big (8000x8000 PNG), you may want to decrease DPI.
graph_all_loss_fig.savefig(fr"{os.path.basename(__file__).replace('.py', '')}_ALL_loss_graph.png", dpi=400)
graph_all_acc_fig.savefig(fr"{os.path.basename(__file__).replace('.py', '')}_ALL_acc_graph.png", dpi=400)
[请在下面找到两个主要图形：Loss - binary crossentropy，Accuracy（由于信誉低，我不允许在图像中嵌入图像）。
我在回归模型中也获得了类似的奇怪问题-MAE在数以千计的范围内-在$ y $范围可能在数以千计的问题内。 （我决定在此处不包括此模型，因为这会使这个问题变得更长。）模块和库的版本，硬件模块：
Keras 2.3.1
Keras-Applications 1.0.8
Keras-Preprocessing 1.1.0
matplotlib 3.1.3
tensorflow-estimator 1.14.0
tensorflow-gpu 2.1.0
tensorflow-gpu-estimator 2.1.0
[keras.json文件：{
"floatx": "float32",
"epsilon": 1e-07,
"backend": "tensorflow",
"image_data_format": "channels_last"
}
CUDA-我的系统上安装了CUDA 10.0和CUDA 10.1。
# remotes::install_github("rstudio/keras#1032")
library(keras)
reticulate::py_config()
#> python: /home/clanera/anaconda3/envs/r-tensorflow/bin/python
#> libpython: /home/clanera/anaconda3/envs/r-tensorflow/lib/libpython3.6m.so
#> pythonhome: /home/clanera/anaconda3/envs/r-tensorflow:/home/clanera/anaconda3/envs/r-tensorflow
#> version: 3.6.10 |Anaconda, Inc.| (default, Jan 7 2020, 21:14:29) [GCC 7.3.0]
#> numpy: /home/clanera/anaconda3/envs/r-tensorflow/lib/python3.6/site-packages/numpy
#> numpy_version: 1.18.1
#> tensorflow: /home/clanera/anaconda3/envs/r-tensorflow/lib/python3.6/site-packages/tensorflow
#>
#> NOTE: Python version was forced by RETICULATE_PYTHON
tensorflow::tf_config()
#> TensorFlow v2.0.0 (~/anaconda3/envs/r-tensorflow/lib/python3.6/site-packages/tensorflow)
#> Python v3.6 (~/anaconda3/envs/r-tensorflow/bin/python)
tensorflow::tf_gpu_configured()
#> TensorFlow built with CUDA: FALSE
#> GPU device name:
#> [1] FALSE
n <- 100
t <- 80 # with 72- seams have no problem
q <- 10
x <- array(sample(n*t*q), c(n, t, q))
y <- sample(0:1, n, replace = TRUE)
input <- layer_input(c(t, q))
output <- input %>%
# ## no problem using LSTM
# layer_lstm(units = 2, recurrent_dropout = 0.5) %>%
layer_gru(units = 2, recurrent_dropout = 0.5) %>%
layer_dense(units = 1, activation = "sigmoid")
model <- keras_model(input, output)
summary(model)
#> Model: "model"
#> ________________________________________________________________________________
#> Layer (type) Output Shape Param #
#> ================================================================================
#> input_1 (InputLayer) [(None, 80, 10)] 0
#> ________________________________________________________________________________
#> gru (GRU) (None, 2) 78
#> ________________________________________________________________________________
#> dense (Dense) (None, 1) 3
#> ================================================================================
#> Total params: 81
#> Trainable params: 81
#> Non-trainable params: 0
#> ________________________________________________________________________________
history <- model %>%
compile(optimizer = "adam", loss = "binary_crossentropy") %>%
fit(x, y, 2, 3)
history
#> Trained on 100 samples (batch_size=2, epochs=3)
#> Final epoch (plot to see history):
#> loss: NaN