RNNが実行できない(zsh: abort)

RNNの学習中になぜかRNNのみ実行できません。CNNなどは普通にできたのですが...
私の環境:
・M1 MacBookAir
miniforgeで構築
python 3.8.12
TensorFlow 2.7

色々調べると以下のような解決策がありましたが、だめでした。
・miniforge環境を再構築(https://github.com/apple/tensorflow_macos/issues/210)
・仮想環境を再構築

おそらく最後のmodel.fitの部分が影響しています。

from tensorflow import keras
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl


np.random.seed(42)

#時系列データの作製
def generate_time_series(batch_size, n_steps):
    freq1, freq2, offsets1, offsets2 = np.random.rand(4, batch_size, 1)
    time = np.linspace(0, 1, n_steps)
    series = 0.5 * np.sin((time - offsets1) * (freq1 * 10 + 10)) # wave 1
    series += 0.2 * np.sin((time - offsets2) * (freq2 * 20 + 20)) # + wave 2
    series += 0.1 * (np.random.rand(batch_size, n_steps) - 0.5)   # + noise
    return series[..., np.newaxis].astype(np.float32)

n_steps = 50
series = generate_time_series(10000, n_steps + 1)
X_train, y_train = series[:7000, :n_steps], series[:7000, -1]
X_valid, y_valid = series[7000:9000, :n_steps], series[7000:9000, -1]
X_test, y_test = series[9000:, :n_steps], series[9000:, -1]

#データをプロットする関数の作成
def plot_series(series, y=None, y_pred=None, x_label='$t$', y_label="$x(t)$", legend=True):
    plt.plot(series, '.-')
    plt.grid(True)
    if y is not None:
        plt.plot(n_steps, y, 'bo', label='Target')
    if y_pred is not None:
        plt.plot(n_steps, y_pred, 'rx', markersize=10, label='Prediction')
    if x_label:
        plt.xlabel(x_label, fontsize=16)
    if y_label:
        plt.ylabel(y_label, fontsize=16, rotation=0)
    plt.hlines(0, 0, 100, linewidth=1)
    plt.axis([0, n_steps + 1, -1, 1])
    if legend and (y or y_pred):
        plt.legend(fontsize=14, loc='upper left')

#学習過程の損失関数をプロットする関数の作製
def plot_learning_curve(loss, val_loss):
    plt.plot(np.arange(len(loss)) + 0.5, loss, 'b.-', label='Training loss')
    plt.plot(np.arange(len(val_loss)) + 1, val_loss, 'r.-', label='Validation loss')
    plt.gca().xaxis.set_major_locator(mpl.ticker.MaxNLocator(integer=True))
    plt.axis([1, 20, 0, 0.05])
    plt.xlabel('Epochs')
    plt.ylabel('MSE')
    plt.grid(True)
    plt.legend()

#単純なRNNを作製
model = keras.models.Sequential([
    keras.layers.SimpleRNN(1, input_shape=[None, 1]) #The most simple RNN
])

#コンパイルと学習
optimizer = keras.optimizers.Adam(learning_rate=0.005)
model.compile(loss='mse', optimizer=optimizer)
history = model.fit(X_train, y_train, epochs=20, validation_data=(X_valid, y_valid))
model.evaluate(X_valid, y_valid)
plot_learning_curve(history.history['loss'], history.history['val_loss'])
plt.show()

systemMemory: 16.00 GB
maxCacheSize: 5.33 GB

2022-01-08 15:45:36.944693: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support.
2022-01-08 15:45:36.944803: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: <undefined>)
2022-01-08 15:45:37.010815: W tensorflow/core/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz
Epoch 1/20
2022-01-08 15:45:37.206878: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:112] Plugin optimizer for device_type GPU is enabled.
2022-01-08 15:45:37.269560: F tensorflow/core/framework/tensor.cc:681] Check failed: IsAligned() ptr = 0x14dcf2150
zsh: abort      /Users/name/miniforge3/envs/Python3.8/bin/python

退会済みユーザー

2022/01/09 00:38

Teratailはマルチポストを禁止はしていませんが、マルチポストですよという通知はするように――となっているはずです。 https://stackoverflow.com/questions/70630367/i-dont-understand-why-rnn-only-is-not-working