我試圖從我制作的模型中制作一個混淆矩陣，在制作模型之前一切似乎都很好，直到我接近一個錯誤
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-8-23313a51ba02> in <module>()
3 y_test=np.argmax(Y_test, axis=0)
4 from sklearn.metrics import confusion_matrix
----> 5 confusion_matrix(y_test, y_pred)
6 import seaborn as sns
7 import matplotlib.pyplot as plt
2 frames
/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_classification.py in confusion_matrix(y_true, y_pred, labels, sample_weight, normalize)
300
301 """
--> 302 y_type, y_true, y_pred = _check_targets(y_true, y_pred)
303 if y_type not in ("binary", "multiclass"):
304 raise ValueError("%s is not supported" % y_type)
/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_classification.py in _check_targets(y_true, y_pred)
82 y_pred : array or indicator matrix
83 """
---> 84 check_consistent_length(y_true, y_pred)
85 type_true = type_of_target(y_true)
86 type_pred = type_of_target(y_pred)
/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py in check_consistent_length(*arrays)
331 raise ValueError(
332 "Found input variables with inconsistent numbers of samples: %r"
--> 333 % [int(l) for l in lengths]
334 )
335
ValueError: Found input variables with inconsistent numbers of samples: [4, 304]
這是我使用的代碼
# Convert List to numpy array, for Keras use
Train_label = np.eye(n_labels)[label] # One-hot encoding by np array function
Train_data = np.array(data)
print("Dataset shape is",Train_data.shape, "(size, timestep, column, row, channel)")
print("Label shape is",Train_label.shape,"(size, label onehot vector)")
# shuffling dataset for input fit function
# if don`t, can`t train model entirely
x = np.arange(Train_label.shape[0])
np.random.shuffle(x)
# same order shuffle is needed
Train_label = Train_label[x]
Train_data = Train_data[x]
train_size = 0.9
X_train=Train_data[:int(Totalnb * 0.9),:]
Y_train=Train_label[:int(Totalnb * 0.9)]
X_test=Train_data[int(Totalnb * 0.1):,:]
Y_test=Train_label[int(Totalnb * 0.1):]
# 2. Buliding a Model
# declare input layer for CNN LSTM architecture
video = Input(shape=(timesteps,img_col,img_row,img_channel))
STEPS_PER_EPOCH = 120
#AlexNet Layer
model = tf.keras.models.Sequential([
# 1st conv
tf.keras.layers.Conv2D(96, (11,11),strides=(4,4), activation='relu', input_shape=(img_col, img_row, img_channel)),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.MaxPooling2D(2, strides=(2,2)),
# 2nd conv
tf.keras.layers.Conv2D(256, (5,5),strides=(1,1), activation='relu',padding="same"),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.MaxPooling2D(2, strides=(2,2)),
# 3rd conv
tf.keras.layers.Conv2D(384, (3,3),strides=(1,1), activation='relu',padding="same"),
tf.keras.layers.BatchNormalization(),
# 4th conv
tf.keras.layers.Conv2D(384, (3,3),strides=(1,1), activation='relu',padding="same"),
tf.keras.layers.BatchNormalization(),
# 5th Conv
tf.keras.layers.Conv2D(256, (3, 3), strides=(1, 1), activation='relu',padding="same"),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.MaxPooling2D(2, strides=(2,2)),
])
model.trainable = True
# FC Dense Layer
x = model.output
x = Flatten()(x)
cnn_out = Dense(128)(x)
# Construct CNN model
Lstm_inp = Model(model.input, cnn_out)
# Distribute CNN output by timesteps
encoded_frames = TimeDistributed(Lstm_inp)(video)
# Contruct LSTM model
encoded_sequence = LSTM(256)(encoded_frames)
hidden_Drop = Dropout(0.2)(encoded_sequence)
hidden_layer = Dense(128)(hidden_Drop)
outputs = Dense(n_labels, activation="softmax")(hidden_layer)
# Contruct CNN LSTM model
model = Model([video], outputs)
# 3. Setting up the Model Learning Process
# Model Compile
opt = SGD(lr=0.01)
model.compile(loss = "categorical_crossentropy", optimizer = opt, metrics=['accuracy'])
model.summary()
# 4. Training the Model
hist = model.fit(X_train, Y_train, batch_size=batch_size, validation_split=validation_ratio, shuffle=True, epochs=num_epochs)
Y_pred2 = model.predict(X_test)
y_pred= np.argmax(Y_pred2, axis=1) # prediksi
y_test=np.argmax(Y_test, axis=0)
from sklearn.metrics import confusion_matrix
confusion_matrix(y_test, y_pred)
import seaborn as sns
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize=(8,5))
sns.heatmap(confusion_matrix(y_test, y_pred), annot=True, fmt=".0f", ax=ax)
plt.xlabel("Y_head")
plt.ylabel("Y_true")
plt.show()
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))
一切似乎都很好并且作業但是當我嘗試在行中制作混淆矩陣時出現錯誤 confusion_matrix(y_test, y_pred)
我仍然無法弄清楚可能是什么問題
希望任何人都可以幫助我
十分感謝大家
uj5u.com熱心網友回復：
發布我的評論作為完整性的答案：
看起來有點怪一個可能的事情是，你計算的argmax時采取不同的軸y_pred和y_test。但這可能沒問題，具體取決于您的資料布局。
y_test并且y_pred似乎是不同的長度。您可以檢查的形狀Y_pred2和Y_test，看看是否在你計算argmax軸是正確的。
轉載請註明出處，本文鏈接：https://www.uj5u.com/gongcheng/374938.html
上一篇：投射多個相似性的ML模型