CNTK python API：如何从经过训练的模型中获取预测？

本文介绍了CNTK python API：如何从经过训练的模型中获取预测？的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 问题描述 29岁程序员，3月因学历无情被辞！ 我有一个训练有素的模型，正在使用 CNTK.load_model（）函数加载。我正在看CNTK git repo上的 MNIST教程作为模型评估代码的参考。我创建了一个数据读取器（这是一个 MinibatchSource 对象），并尝试运行 model.eval（mb），其中 mb = minibatch_source.next_minibatch（...）（类似于此答案）I have a trained model which I am loading using CNTK.load_model() function. I was looking at the MNIST Tutorial on the CNTK git repo as reference for model evaluation code. I have created a data reader (which is a MinibatchSource object) and trying to run model.eval(mb) where mb = minibatch_source.next_minibatch(...) (Similar to this answer)但是，我收到以下错误消息But, I'm getting the following error messageTraceback (most recent call last): File "LID_test.py", line 162, in <module> test_and_evaluate() File "LID_test.py", line 159, in test_and_evaluate predictions = model.eval(mb) File "/home/t-asbahe/anaconda3/envs/cntk-py35/lib/python3.5/site-packages/cntk/ops/functions.py", line 228, in eval _, output_map = self.forward(arguments, self.outputs, device=device, as_numpy=as_numpy) File "/home/t-asbahe/anaconda3/envs/cntk-py35/lib/python3.5/site-packages/cntk/utils/swig_helper.py", line 62, in wrapper result = f(*args, **kwds) File "/home/t-asbahe/anaconda3/envs/cntk-py35/lib/python3.5/site-packages/cntk/ops/functions.py", line 354, in forward None, device) File "/home/t-asbahe/anaconda3/envs/cntk-py35/lib/python3.5/site-packages/cntk/utils/__init__.py", line 393, in sanitize_var_map if len(arguments) < len(op_arguments):TypeError: object of type 'Variable' has no len()我的模型中没有名为'Variable'的 input_variable ，并且我看不到出现此错误的任何原因。I have no input_variable named 'Variable' in my model and I don't see any reason to get this error. PS：我的输入是稀疏输入（一次性）P.S.: My inputs are sparse inputs (one-hots)推荐答案您有一些选择： 将一组数据作为numpy数组传递（在CNTK 202教程中的实例），其中Pass a set of data as numpy array (instance in CNTK 202 tutorial) where onehot data is passed in as a numpy array. pred = model.eval（{model.arguments [0]：[onehot]}）pred = model.eval({model.arguments[0]:[onehot]})读取小批量数据并将其传递给eval函数Read the minibatch data and pass it to the eval function eval_input_map = {输入：reader_eval.streams.features} eval_data = reader_eval.next_minibatch（eval_minibatch_size， input_map = eval_input_map） mydata = eval_data [input] .value 预测= model.eval（mydata）eval_input_map = { input : reader_eval.streams.features }eval_data = reader_eval.next_minibatch(eval_minibatch_size, input_map = eval_input_map)mydata = eval_data[input].valuepredicted= model.eval(mydata) 这篇关于CNTK python API：如何从经过训练的模型中获取预测？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！ 上岸，阿里云！