機械学習のディープラーニングでエラー

Question

機械学習でエラーが起きます。
エラー内容やどこを直せばいいかわかる方いましたら教えてください

ソース

import tensorflow as tf
import tensorflow.keras as keras###変更
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np

# データの読み込み --- (*1)
analysisresults_data = pd.read_csv("analysis_resultstableZZZ.csv",encoding="utf-8")

# データをラベルと入力データに分離する
y = analysisresults_data.loc[:,"analysis_result"]
x = analysisresults_data.loc[:,["id","signatures_id","hit_count"]]


# 学習用とテスト用に分割する --- (*2)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, train_size = 0.8, shuffle = True)

# モデル構造を定義 --- (*3)
Dense = keras.layers.Dense
model = keras.models.Sequential()
model.add(Dense(10, activation='relu', input_shape=(3,)))
model.add(Dense(2, activation='softmax')) # ---(*3a)

# モデルを構築 --- (*4)
model.compile(
    loss='categorical_crossentropy',
    optimizer='adam',
    metrics=['accuracy'])

# 学習を実行 --- (*5)
model.fit(x_train, y_train,
    batch_size=20,
    epochs=300)

# モデルを評価 --- (*6)
score = model.evaluate(x_test, y_test, verbose=1)
print('正解率=', score[1], 'loss=', score[0])

2019-11-30 15:12:46.613774: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-11-30 15:12:46.625817: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa07afcb160 executing computations on platform Host. Devices:
2019-11-30 15:12:46.625834: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Host, Default Version
WARNING:tensorflow:Falling back from v2 loop because of error: Failed to find data adapter that can handle input: <class 'pandas.core.frame.DataFrame'>, <class 'NoneType'>
Traceback (most recent call last):
File "deep2.py", line 33, in <module>
epochs=300)
File "/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 728, in fit
use_multiprocessing=use_multiprocessing)
File "/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_arrays.py", line 642, in fit
shuffle=shuffle)
File "/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 2538, in _standardize_user_data
y, self._feed_loss_fns, feed_output_shapes)
File "/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_utils.py", line 717, in check_loss_and_target_compatibility
' while using as loss categorical_crossentropy. '
ValueError: You are passing a target array of shape (7999, 1) while using as loss categorical_crossentropy. categorical_crossentropy expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via:

from keras.utils import to_categorical
y_binary = to_categorical(y_int)

Alternatively, you can use the loss function sparse_categorical_crossentropy instead, which does expect integer targets.

Comments

[fiveHundred]

エラーの内容にそのまま解決方法が記載されていますが、読んで試しましたか？

[Rondon7251]

どの部分のエラー内容ですか？

Answer 1

どの部分のエラー内容ですか？

以下の通りです。

ValueError: You are passing a target array of shape (7999, 1) while using as loss categorical_crossentropy. categorical_crossentropy expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via:

from keras.utils import to_categorical
y_binary = to_categorical(y_int)

Alternatively, you can use the loss function sparse_categorical_crossentropy instead, which does expect integer targets.

要するに、to_categorical()で変換するか、sparse_categorical_crossentropyを使ってくれ、ということです。

Comments

[Rondon7251]

loss='categorical_crossentropy',の部分を
loss=='sparse_categorical_crossentropy'
に変更するという意味であっていますでしょうか

[fiveHundred]

それで試してみてください。