Created by: Tangzixia

Python Call Stacks (More useful to users):

File "/home/vis/kangshuai/apps/anaconda3/lib/python3.6/site-packages/paddle/fluid/framework.py", line 2610, in append_op attrs=kwargs.get("attrs", None)) File "/home/vis/kangshuai/apps/anaconda3/lib/python3.6/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op return self.main_program.current_block().append_op(*args, **kwargs) File "/home/vis/kangshuai/apps/anaconda3/lib/python3.6/site-packages/paddle/fluid/layers/nn.py", line 12225, in _elementwise_op 'use_mkldnn': use_mkldnn}) File "/home/vis/kangshuai/apps/anaconda3/lib/python3.6/site-packages/paddle/fluid/layers/nn.py", line 12404, in elementwise_add return elementwise_op(LayerHelper('elementwise_add', **locals())) File "/home/vis/kangshuai/procedure/PaddleSegInit/pdseg/models/modeling/ocnet.py", line 84, in fuse_layers residual = fluid.layers.elementwise_add(x=residual, y=y, act=None) File "/home/vis/kangshuai/procedure/PaddleSegInit/pdseg/models/modeling/ocnet.py", line 112, in high_resolution_module out = fuse_layers(residual, channels, multi_scale_output=multi_scale_output, name=name) File "/home/vis/kangshuai/procedure/PaddleSegInit/pdseg/models/modeling/ocnet.py", line 139, in stage out = high_resolution_module(out, channels, name=name + '' + str(i + 1)) File "/home/vis/kangshuai/procedure/PaddleSegInit/pdseg/models/modeling/ocnet.py", line 276, in high_resolution_ocr_net st2 = stage(tr1, num_modules_2, channels_2, name='st2') File "/home/vis/kangshuai/procedure/PaddleSegInit/pdseg/models/modeling/ocnet.py", line 302, in ocnet logit = high_resolution_ocr_net(input, num_classes) File "/home/vis/kangshuai/procedure/PaddleSegInit/pdseg/models/model_builder.py", line 89, in seg_model logits = ocnet.ocnet(image, class_num) File "/home/vis/kangshuai/procedure/PaddleSegInit/pdseg/models/model_builder.py", line 168, in build_model logits = seg_model(image, class_num) File "pdseg/export_model.py", line 88, in export_inference_model infer_prog, startup_prog, phase=ModelPhase.PREDICT) File "pdseg/export_model.py", line 130, in main export_inference_model(args) File "pdseg/export_model.py", line 134, in main()

Error Message Summary:

InvalidArgumentError: Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [1, 32, 128, 128] and the shape of Y = [1, 32, 270, 480]. Received [128] in X is not equal to [270] in Y at i:2. [Hint: Expected x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1 == true, but received x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1:0 != true:1.] at (/home/scmbuild/workspaces_cluster.dev/baidu.lib.paddlepaddle/baidu/lib/paddlepaddle/Paddle/paddle/fluid/operators/elementwise/elementwise_op_function.h:157)

你好，我这边报了数据不匹配的问题，麻烦帮看一下这个怎么解决