无法将 NumPy 数组转换为张量（不支持的对象类型列表

Question

我正在尝试构建一个图像分类模型，该模型可以识别您是否戴着口罩，但在训练模型时遇到了问题。

    return ops.EagerTensor(value, ctx.device_name, dtype)
ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type list).

这是我的代码

import numpy as np

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.optimizers import SGD
import os
import cv2
import random

def getData():
     training = []

     for image in os.listdir("src/data/with_mask"):
          img = cv2.imread(f"src/data/with_mask/{image}",0)
          training.append([img.tolist(),1])

     for image in os.listdir("src/data/without_mask"):
          img = cv2.imread(f"src/data/without_mask/{image}",0)
          training.append([img.tolist(),0])

     random.shuffle(training)
     train_x = np.array([x[0] for x in training])
     train_y = np.array([x[1] for x in training])
     return (train_x ,train_y)


train_x , train_y = getData()

model = Sequential()

model.add(Dense(128,input_shape=(len(train_x[0]),),activation="relu"))
model.add(Flatten())
model.add(Dense(64,activation="relu"))
model.add(Dense(64,activation="relu"))
model.add(Dense(1,activation="softmax"))

sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss="categorical_crossentropy",
              optimizer=sgd, metrics=["accuracy"])



hist = model.fit(
    train_x,train_y,
    epochs=100, batch_size=8, verbose=1)
model.save("model.h5", hist)

我尝试将 np.array([...]) 更改为 np.array([...],dtype=np.float32) 但随后出现错误 ValueError: setting an array element with a sequence.

我的训练数据形状是

[[[
 [...]
 [...]
 [...]
 [...]
],1],...]

如果有人在下面发布答案，我将非常感激。

Answer 1

好的，感谢@SanchritJain，我解决了问题是我没有调整图像大小。