用于高分辨率图像的Inception V3模型

时间:2019-06-25 13:15:29

标签: python image tensorflow

Tensorflow for Poets Inception V3迁移学习培训脚本的代码包含以下代码:

if architecture == 'inception_v3':
    # pylint: disable=line-too-long
    data_url = 'http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz'
    # pylint: enable=line-too-long
    bottleneck_tensor_name = 'pool_3/_reshape:0'
    bottleneck_tensor_size = 2048
    input_width = 299
    input_height = 299
    input_depth = 3
    resized_input_tensor_name = 'Mul:0'
    model_file_name = 'classify_image_graph_def.pb'
    input_mean = 128
    input_std = 128

我假设脚本将图像大小调整为299x299像素。如何在不缩小尺寸的情况下将模型与更高分辨率的图像数据集一起使用?我尝试仅将这些数字修改为实际尺寸,但显然出现了错误:

Cannot feed value of shape (1, 1560, 1570, 3) for Tensor 'Mul:0', which has shape '(1, 299, 299, 3)'

有人碰巧知道我需要如何对脚本的体系结构进行修改以适应不同的尺寸?

0 个答案:

没有答案