Created by: yeyupiaoling

环境

• Ubuntu 26.04
• PaddlePaddle 1.2 GPU

问题

代码：https://github.com/yeyupiaoling/LearnPaddle2/blob/master/note13/train.py

调试方式：把包含图片文件的文件夹放在note13的datasets目录下，如note13/datasets/n02086079-Pekinese/n02086079_146.jpg。接着执行训练程序，就会出现以下的错误，默认设置的训练图片大小为224，请问如何解决呢？

图片大小设置为32是没有问题的，超过这个就会报错，是不是我的生成器有问题，对应生成224大小的图片，应该如何修改呢？

错误信息：

Traceback (most recent call last):
  File "/media/test/5C283BCA283BA1C6/yeyupiaoling/LearnPaddle2/note13/train.py", line 109, in <module>
    p_fake = Discriminator(Generator(z))
  File "/media/test/5C283BCA283BA1C6/yeyupiaoling/LearnPaddle2/note13/train.py", line 33, in Generator
    y = deconv(x=y, num_filters=3, act='sigmoid', output_size=[image_size, image_size])
  File "/media/test/5C283BCA283BA1C6/yeyupiaoling/LearnPaddle2/note13/train.py", line 19, in deconv
    act=act)
  File "/usr/local/lib/python3.5/dist-packages/paddle/fluid/layers/nn.py", line 2988, in conv2d_transpose
    'use_cudnn': use_cudnn
  File "/usr/local/lib/python3.5/dist-packages/paddle/fluid/layer_helper.py", line 50, in append_op
    return self.main_program.current_block().append_op(*args, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/paddle/fluid/framework.py", line 1208, in append_op
    op = Operator(block=self, desc=op_desc, *args, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/paddle/fluid/framework.py", line 657, in __init__
    self.desc.infer_shape(self.block.desc)
paddle.fluid.core.EnforceNotMet: ConvTransposeOp output_size should be in appropriate range. at [/home/test/Downloads/Paddle/paddle/fluid/operators/conv_transpose_op.cc:70]
PaddlePaddle Call Stacks: 
0       0x7f5a23450a27p paddle::platform::EnforceNotMet::EnforceNotMet(std::__exception_ptr::exception_ptr, char const*, int) + 727
1       0x7f5a23cb0549p paddle::operators::ConvTransposeOp::InferShape(paddle::framework::InferShapeContext*) const + 5241
2       0x7f5a235298a0p
3       0x7f5a2352dc5ap paddle::framework::OpDesc::InferShape(paddle::framework::BlockDesc const&) const + 1050
4       0x7f5a234d7e24p
5       0x7f5a2347f16dp
6             0x4ea137p PyCFunction_Call + 119
7             0x53c176p PyEval_EvalFrameEx + 23030
8             0x540b0bp PyEval_EvalCodeEx + 315
9             0x4ec3f7p
10            0x5c20e7p PyObject_Call + 71
11            0x4fbfcep
12            0x5c20e7p PyObject_Call + 71
13            0x574c19p
14            0x57f58cp
15            0x5c20e7p PyObject_Call + 71
16            0x538cabp PyEval_EvalFrameEx + 9515
17            0x540b0bp PyEval_EvalCodeEx + 315
18            0x4ec3f7p
19            0x5c20e7p PyObject_Call + 71
20            0x538cabp PyEval_EvalFrameEx + 9515
21            0x53fc97p
22            0x53bc93p PyEval_EvalFrameEx + 21779
23            0x53fc97p
24            0x53b83fp PyEval_EvalFrameEx + 20671
25            0x53fc97p
26            0x53b83fp PyEval_EvalFrameEx + 20671
27            0x53fc97p
28            0x53b83fp PyEval_EvalFrameEx + 20671
29            0x53fc97p
30            0x5409bfp PyEval_EvalCode + 31
31            0x60cb42p
32            0x60efeap PyRun_FileExFlags + 154
33            0x60f7dcp PyRun_SimpleFileExFlags + 444
34            0x640256p Py_Main + 1110
35            0x4d0001p main + 225
36      0x7f5a71820830p __libc_start_main + 240
37            0x5d6999p _start + 41


Process finished with exit code 1