将模型中的Tensor转为numpy

Question

问题遇到的现象和发生背景

将tensor转换为numpy

用代码块功能插入代码，请勿粘贴截图

from keras import backend as K

in_shp = train_data.shape[1:]  # in_shap= （4096，2）
Xm_input = Input(in_shp)  
x1 = Lambda(slice,output_shape=(4096,1),arguments={'index':0})(Xm_input)
x2 = Lambda(slice,output_shape=(4096,1),arguments={'index':1})(Xm_input)
n1 = K.eval(x1)

model.compile(optimizer = Nadam(learning_rate=0.002),
loss= 'categorical_crossentropy',
metrics=[iou_coef],
run_eagerly=True)

运行结果及报错内容

('Some keys in session_kwargs are not supported at this time: %s', dict_keys(['run_eagerly']))

我的解答思路和尝试过的方法

想要将lambda层输出的Tensor转为numpy，刚开始会报placehold的错误，之后再compile中加了run_eagerly参数，又报了新的错误：('Some keys in session_kwargs are not supported at this time: %s', dict_keys(['run_eagerly']))

我想要达到的结果

将模型中的Tensor转为numpy

Answer 1

NumPy 数组转 Tensor：

import numpy as np
a = np.ones(7)
b = torch.from_numpy(a)
print(a, b)

a += 1
print(a, b)
b += 1
print(a, b)

[1. 1. 1. 1. 1. 1. 1.] tensor([1., 1., 1., 1., 1., 1., 1.], dtype=torch.float64)
[2. 2. 2. 2. 2. 2. 2.] tensor([2., 2., 2., 2., 2., 2., 2.], dtype=torch.float64)
[3. 3. 3. 3. 3. 3. 3.] tensor([3., 3., 3., 3., 3., 3., 3.], dtype=torch.float64)