我正在尝试使用TensorFlow中的分类脚本找到分类预测的概率,但是无法做到。这是我正在使用的代码:
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')
predictions = sess.run(softmax_tensor, \
{'DecodeJpeg/contents:0': image_data})
我遇到以下错误:
TypeError: Cannot interpret feed_dict key as Tensor: The name 'DecodeJpeg/contents:0' refers toa Tensor which does not exist. The operation, 'DecodeJpeg/contents', does not exist in the graph
我正在使用TensorFlow的Inception V3模型和retrain.py
脚本来训练该模型。