Python keras预测成功训练后的发电机投掷误差
我正试图从头开始在自己的数据集上实现。在将代码更改为我的需求和一次试用培训之后，我试图通过keras中的predict_生成器函数验证预测。然而，它抛出了一个错误Python keras预测成功训练后的发电机投掷误差,python,tensorflow,keras,deep-learning,yolo,Python,Tensorflow,Keras,Deep Learning,Yolo,我正试图从头开始在自己的数据集上实现。在将代码更改为我的需求和一次试用培训之后，我试图通过keras中的predict_生成器函数验证预测。然而，它抛出了一个错误 model.compile(optimizer=Adam(lr=1e-4), loss={'yolo_loss': lambda y_true, y_pred: y_pred},metrics=['accuracy']) # recompile to apply the change print('Unfreeze a
model.compile(optimizer=Adam(lr=1e-4), loss={'yolo_loss': lambda y_true, y_pred: y_pred},metrics=['accuracy']) # recompile to apply the change
print('Unfreeze all of the layers.')
batch_size = 2
print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
model.fit_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, anchors, num_classes),
steps_per_epoch=max(1, num_train//batch_size),
validation_data=data_generator_wrapper(lines[num_train:], batch_size, input_shape, anchors, num_classes),
validation_steps=max(1, num_val//batch_size),
epochs=1,
initial_epoch=0,
callbacks=[logging, checkpoint, reduce_lr, early_stopping])
predict = model.predict_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, anchors, num_classes),verbose=1,steps=10)
model.save_weights(log_dir + 'trained_weights_final.h5')