1. 系统环境

硬件环境(Ascend/GPU/CPU): Ascend/GPU/CPU

MindSpore版本: 不限

执行模式（动态图）: 不限模式

Python版本: 3.7.5

操作系统平台: Ubuntu 16.04

2. 报错信息

2.1报错信息

[ERROR] ANALYZER(8534,ffffb5cca780,python):2022-11-30-10:59:18.593.719 [mindspore/ccsrc/pipeline/jit/static_analysis/async_eval_result.cc:66] HandleException] Exception happened, check the information as below.

The function call stack (See file '/home/ma-user/work/rank_0/om/analyze_fail.dat' for more details):

# 0 In file /home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/wrap/cell_wrapper.py(373)

loss = self.network(*inputs)

^

# 1 In file /home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/wrap/cell_wrapper.py(111)

out = self._backbone(data)

^

# 2 In file /home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/layer/basic.py(323)

if len(x_shape) != 2:

# 3 In file /home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/layer/basic.py(326)

if self.has_bias:

# 4 In file /home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/layer/basic.py(325)

x = self.matmul(x, self.weight)

^

---------------------------------------------------------------------------

ValueError Traceback (most recent call last)

/tmp/ipykernel_8534/2891349598.py in

1 model = ms.train.Model(net, loss, opt, metrics={'acc', 'loss'})

----> 2 model.train(25, ds_train, callbacks=[LossMonitor(per_print_times=ds_train.get_dataset_size())], dataset_sink_mode=False)

3 metrics = model.eval(ds_test)

4 print(metrics)

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/train/model.py in train(self, epoch, train_dataset, callbacks, dataset_sink_mode, sink_size)

904 callbacks=callbacks,

905 dataset_sink_mode=dataset_sink_mode,

--> 906 sink_size=sink_size)

907

908 def build(self, train_dataset=None, valid_dataset=None, sink_size=-1, epoch=1, jit_config=None):

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/train/model.py in wrapper(self, *args, **kwargs)

85 raise e

86 else:

---> 87 func(self, *args, **kwargs)

88 return wrapper

89

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/train/model.py in _train(self, epoch, train_dataset, callbacks, dataset_sink_mode, sink_size)

540 self._check_reuse_dataset(train_dataset)

541 if not dataset_sink_mode:

--> 542 self._train_process(epoch, train_dataset, list_callback, cb_params)

543 elif context.get_context("device_target") == "CPU":

544 logger.info("The CPU cannot support dataset sink mode currently."

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/train/model.py in _train_process(self, epoch, train_dataset, list_callback, cb_params)

792 cb_params.train_dataset_element = next_element

793 list_callback.step_begin(run_context)

--> 794 outputs = self._train_network(*next_element)

795 cb_params.net_outputs = outputs

796 if self._loss_scale_manager and self._loss_scale_manager.get_drop_overflow_update():

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/cell.py in __call__(self, *args, **kwargs)

584 logger.warning(f"For 'Cell', it's not support hook function in graph mode. If you want to use hook "

585 f"function, please use context.set_context to set pynative mode.")

--> 586 out = self.compile_and_run(*args)

587 return out

588

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/cell.py in compile_and_run(self, *inputs)

962 """

963 self._auto_parallel_compile_and_run = True

--> 964 self.compile(*inputs)

965

966 new_inputs = []

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/cell.py in compile(self, *inputs)

935 """

936 if self._dynamic_shape_inputs is None or self._dynamic_shape_inputs[0] is None:

--> 937 _cell_graph_executor.compile(self, *inputs, phase=self.phase, auto_parallel_mode=self._auto_parallel_mode)

938 else:

939 self._check_compile_dynamic_shape(*inputs)

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/common/api.py in compile(self, obj, phase, do_convert, auto_parallel_mode, *args)

1004 enable_ge = context.get_context("enable_ge")

1005 self._graph_executor.set_weights_values(obj.parameters_dict())

-> 1006 result = self._graph_executor.compile(obj, args_list, phase, self._use_vm_mode())

1007 obj.compile_cache.add(phase)

1008 if not result:

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/ops/primitive.py in __check__(self, *args)

465 for track in tracks:

466 fn = getattr(self, 'check_' + track)

--> 467 fn(*(x[track] for x in args))

468

469

~/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/ops/operations/math_ops.py in check_shape(self, x1, x2)

1387 if np.all(np.array(x1) != -1) and np.all(np.array(x2) != -1):

1388 if x1_col != x2_row:

-> 1389 raise ValueError(f"For '{cls_name}', the input dimensions must be equal, but got 'x1_col': {x1_col} "

1390 f"and 'x2_row': {x2_row}. And 'x' shape {x1}(transpose_a={self.transpose_a}), "

1391 f"'y' shape {x2}(transpose_b={self.transpose_b}).")

ValueError: For 'MatMul', the input dimensions must be equal, but got 'x1_col': 817920 and 'x2_row': 272640. And 'x' shape [32, 817920](transpose_a=False), 'y' shape [3, 272640](transpose_b=True).

2.2脚本代码

import os

# os.environ['DEVICE_ID'] = '6'

import numpy as np

import mindspore as ms

from mindspore import nn

from mindspore import context

from mindspore import dataset

from mindspore.train.callback import LossMonitor

from mindspore.common.api import ms_function

from mindspore.ops import operations as P

from PIL import Image

#当前实验选择算力为Ascend，如果在本地体验，参数device_target设置为"CPU”

context.set_context(mode=context.GRAPH_MODE, device_target="Ascend")

#要筛选的分辨率条件

targetWidth=426

targetHeight=640

targetChannal=3

#读取animal文件夹下所有文件的名字

rootDir='animal'

fileNameList=['cat','elephant','sheep']

label_map = {

'cat': 0,

'elephant': 1,

'sheep': 2

}

X,Y=[],[]

for fileName in fileNameList:

fileDir=rootDir+'/'+fileName

#print(fileDir)

imgNameList=os.listdir(fileDir)

#print(imgNameList)

for imgName in imgNameList:

imgDir=fileDir+'/'+imgName

img=Image.open(imgDir)

img=np.array(img)

if(len(img.shape)==3):

width,height,channal=img.shape

if width==targetWidth and height==targetHeight and channal==targetChannal:#符合筛选条件的样本留下放到X，其标签放到Y

X.append(img.flatten())

Y.append(label_map[fileName])#类别

#print(X,Y)

#划分训练集和测试集合

sampleNum=len(X)

train_idx = np.random.choice(sampleNum, int(sampleNum*0.8), replace=False)#取80%的样本作为训练集

test_idx = np.array(list(set(range(sampleNum)) - set(train_idx)))#剩下的样本作为测试集

X_train=[X[i].astype(np.float32) for i in range(len(X)) if i in train_idx]

Y_train=[Y[i] for i in range(len(Y)) if i in train_idx]

X_test=[X[i].astype(np.float32) for i in range(len(X)) if i in test_idx]

Y_test=[Y[i] for i in range(len(Y)) if i in test_idx]

XY_train = list(zip(X_train, Y_train))

ds_train = dataset.GeneratorDataset(XY_train, ['x', 'y'])

# ds_train.set_dataset_size(sampleNum)

ds_train = ds_train.shuffle(buffer_size=sampleNum).batch(32, drop_remainder=True)

XY_test = list(zip(X_test, Y_test))

ds_test = dataset.GeneratorDataset(XY_test, ['x', 'y'])

ds_test = ds_test.batch(30)#具体作用

#print(XY_test)

for e in X_train:

print(e.shape)

net = nn.Dense(targetWidth*targetHeight, 3)

loss = nn.loss.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')

opt = nn.optim.Momentum(net.trainable_params(), learning_rate=0.05, momentum=0.9)

model = ms.train.Model(net, loss, opt, metrics={'acc', 'loss'})

model.train(25, ds_train, callbacks=[LossMonitor(per_print_times=ds_train.get_dataset_size())], dataset_sink_mode=False)

metrics = model

.eval(ds_test)

print(metrics)

3. 根因分析

******此处由用户补充详细的定位过程******

net = nn.Dense(targetWidth*targetHeight, 3) 这个地方的第一个维度应该是targetWidth*targetHeight * 3，要保持和输入的数据一致。

4. 解决方案

******此处由用户填写******

包含文字方案和最终脚本代码

支持上传附件