Created by: 1286667673

大神好，我这里报的问题还是elementwise_sub error.之前尺寸不一样，我加了padding，我看着我通过网络计算出来的维度尺寸和标签的维度尺寸是一样的，我的图片维度是（1,1,307,409），经过网络计算后的维度是（1,1,76,102），然后标签的维度也是（1,1,76,102），为什么loss还是不能计算呢？或者说我的维度看的有问题？帮我看一下，代码及输出信息如下： import random import cv2 import os import math import paddle import numpy as np import paddle.fluid as fluid

class FCNN: def init(self,dataset): self.dataset = dataset self.LEARNING_RATE = 1e-4 # 对图片进行预处理 def load_image(self,path): img = cv2.imread(path) # 转灰度 img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) # 转换成numpy值 img = np.array(img).astype(np.float32) height, width = img.shape[:2] size = (int(width * 0.4), int(height * 0.4)) img = cv2.resize(img, size, interpolation=cv2.INTER_AREA) img = (img - 127.5) / 128 return img def data_pre_train(self,kind,dataset): img_path = './data/data8297/formatted_trainval_gray_resize1/shanghaitech_part_' + dataset + 'patches_9/' + kind + '/' print(img_path) den_path = './data/data8297/formatted_trainval_gray_resize1/shanghaitech_part' + dataset + '_patches_9/' + kind + '_den/' img_names = os.listdir(img_path) img_num = len(img_names)

    data = []
    for i in range(1, img_num + 1):
        print(i)
        if i % 100 == 0:
            print(i, '/', img_num)
        name = img_names[i - 1]
        img = self.load_image(img_path + name)
        #img = (img - 127.5) / 128
        #img = np.array(img)
        den = np.loadtxt(open(den_path + name[:-4] + '.csv'), delimiter=",")
        den_quarter = np.zeros((math.floor(den.shape[0] / 4),math.floor(den.shape[1] / 4)))
        for i in range(len(den_quarter)-1):
            for j in range(len(den_quarter[0])-1):
                for p in range(4):
                    for q in range(4):
                        den_quarter[i][j] += den[i * 4 + p][j * 4 + q]
        data.append([img, den_quarter])
    print('load dataset finished')
    return data
def conv2d_neural_network(self,img):
    # 第一个卷积-池化层
    S_conv_1 = fluid.layers.conv2d(input=img,filter_size=5,num_filters=24,padding=4,act="relu") 
    S_conv_pool_1 = fluid.layers.pool2d(input=S_conv_1, pool_size=2, pool_stride=2)
     # 第二个卷积-池化层
    S_conv_2 = fluid.layers.conv2d(input=S_conv_pool_1,filter_size=3,num_filters=48,padding=4,act="relu")
    S_conv_pool_2 = fluid.layers.pool2d(input=S_conv_2, pool_size=2, pool_stride=2)
    # 第三个卷积
    S_conv_pool_3 = fluid.layers.conv2d(input =S_conv_pool_2,num_filters=24,filter_size=3,act="relu")
    # 第四个卷积  
    S_conv_pool_4 = fluid.layers.conv2d(input =S_conv_pool_3,num_filters=12,filter_size=3,act="relu")
    
    
    y_predict = fluid.layers.conv2d(input =S_conv_pool_4,num_filters=1,filter_size=1,stride=1)
    return y_predict


def train(self,max_epoch):
    model_save_dir = '/home/aistudio/data/data8297/MODELA/'
    #定义输入数据的占位符
    image= fluid.layers.data(name = 'image',shape = [-1,1,10000,10000], dtype='float32')
    y_act = fluid.layers.data(name='y_act', shape=[-1,1,10000,10000], dtype='float32')
    y_pre = self.conv2d_neural_network(image)
    print(y_act.shape)
    print(y_pre.shape)
    loss =fluid.layers.sqrt(fluid.layers.reduce_mean(fluid.layers.square_error_cost(input=y_pre,label=y_act)))
    #avg_loss = fluid.layers.mean(loss)
    act_sum = fluid.layers.reduce_mean(y_act)
    pre_sum = fluid.layers.reduce_mean(y_pre)
    MAE = fluid.layers.abs(act_sum - pre_sum)
    #定义损失函数
    optimizer = fluid.optimizer.Adam(learning_rate=0.001)
    optimizer.minimize(loss)
    
    data_train = self.data_pre_train('train', self.dataset)
    data_val = self.data_pre_train('val', self.dataset)
    
    place = fluid.CPUPlace()
    exe = fluid.Executor(place)
    # 进行参数初始化
    exe.run(fluid.default_startup_program())
    main_program = fluid.default_main_program()
    best_mae = 10000
    for epoch in range(max_epoch):
        #training process
        epoch_mae = 0
        random.shuffle(data_train)
        # 创建一个使用CPU的执行器
    
        for i in range(len(data_train)):
            data = data_train[i]
            print(data[1].shape)
            x_in = np.reshape(data[0], [-1,1, data[0].shape[0], data[0].shape[1]])
            y_ground = np.reshape(data[1], [-1,1,data[1].shape[0], data[1].shape[1]])
            print(x_in.shape)
            print(y_ground.shape)
            loss,y_pre, act_sum, pre_sum,MAE = exe.run(main_program,
                                feed={image.name:x_in,y_act.name:y_ground},
                                fetch_list=[loss,y_pre, act_sum, pre_sum,MAE])
            
            print(loss.shape)
            if i % 500 == 0:        
                    print('epoch', epoch, 'step', i, 'mae:', m)
            epoch_mae += m
        epoch_mae /= len(data_train)
        print('epoch', epoch + 1, 'train_mae:', epoch_mae)
        
        #validation process
        val_mae = 0
        val_mse = 0
        for i in range(len(data_val)):
            data = data_val[i]
            x_in = fluid.layers.reshape(data[0], (1, data[0].shape[0], data[0].shape[1], 1))
            y_ground = fluid.layers.reshape(data[1], (1, data[1].shape[0], data[1].shape[1], 1))
            
            act_s, pre_s, m = exe.run(main_program,
                feed=feeder.feed(x_in,y_ground),
                fetch_list=[act_sum, pre_sum,MAE])
            val_mae += m
            val_mse += (act_s - pre_s) * (act_s - pre_s)
        val_mae /= len(data_val)
        val_mse = math.sqrt(val_mse / len(data_val))
        print('epoch', epoch, 'valid_mae:', val_mae, 'valid_mse:', val_mse)
        if val_mae < best_mae:
            best_mae = val_mae
            print('best mae so far, saving model.')
            if not os.path.exists(model_save_dir):
                os.makedirs(model_save_dir)
            #print 'save models to %s' % (model_path)
            # 保存模型
            fluid.io.save_inference_model(model_path, ['img'], [predict], exe)

        else:
            print('best mae:', best_mae)
        print('**************************')

EPOCH = 100 fcnn = FCNN('A') fcnn.train(EPOCH)

运行报错信息： 149 fcnn.train(EPOCH) in train(self, max_epoch) 107 loss,y_pre, act_sum, pre_sum,MAE = exe.run(main_program, 108 feed={image.name:x_in,y_act.name:y_ground}, --> 109 fetch_list=[loss,y_pre, act_sum, pre_sum,MAE]) 110 111 print(loss.shape) /opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/paddle/fluid/executor.py in run(self, program, feed, fetch_list, feed_var_name, fetch_var_name, scope, return_numpy, use_program_cache) 563 scope=scope, 564 return_numpy=return_numpy, --> 565 use_program_cache=use_program_cache) 566 else: 567 if fetch_list and program.is_data_parallel and program.program and ( /opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/paddle/fluid/executor.py in run(self, program, exe, feed, fetch_list, feed_var_name, fetch_var_name, scope, return_numpy, use_program_cache) 640 641 self.feed_data(program, feed, feed_var_name, scope) --> 642 exe.run(program.desc, scope, 0, True, True, fetch_var_name) 643 outs = self.fetch_data(fetch_list, fetch_var_name, scope) 644 if return_numpy: EnforceNotMet: Invoke operator elementwise_sub error. Python Callstacks: File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/paddle/fluid/framework.py", line 1654, in append_op attrs=kwargs.get("attrs", None)) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op return self.main_program.current_block().append_op(*args, kwargs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/paddle/fluid/layers/nn.py", line 1580, in square_error_cost outputs={'Out': [minus_out]}) File "", line 76, in train loss =fluid.layers.sqrt(fluid.layers.reduce_mean(fluid.layers.square_error_cost(input=y_pre,label=y_act))) File "", line 149, in fcnn.train(EPOCH) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 3265, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 3189, in run_ast_nodes if (yield from self.run_code(code, result)): File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 3018, in run_cell_async interactivity=interactivity, compiler=compiler, result=result) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/IPython/core/async_helpers.py", line 67, in _pseudo_sync_runner coro.send(None) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2843, in _run_cell return runner(coro) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2817, in run_cell raw_cell, store_history, silent, shell_futures) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/ipykernel/zmqshell.py", line 536, in run_cell return super(ZMQInteractiveShell, self).run_cell(args, kwargs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/ipykernel/ipkernel.py", line 294, in do_execute res = shell.run_cell(code, store_history=store_history, silent=silent) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/gen.py", line 326, in wrapper yielded = next(result) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 534, in execute_request user_expressions, allow_stdin, File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/gen.py", line 326, in wrapper yielded = next(result) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 267, in dispatch_shell yield gen.maybe_future(handler(stream, idents, msg)) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/gen.py", line 326, in wrapper yielded = next(result) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 357, in process_one yield gen.maybe_future(dispatch(args)) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/gen.py", line 1147, in run yielded = self.gen.send(value) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/gen.py", line 1233, in inner self.run() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/stack_context.py", line 300, in null_wrapper return fn(args, kwargs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/ioloop.py", line 758, in _run_callback ret = callback() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/asyncio/events.py", line 127, in _run self._callback(self._args) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/asyncio/base_events.py", line 1425, in _run_once handle._run() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/asyncio/base_events.py", line 421, in run_forever self._run_once() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/tornado/platform/asyncio.py", line 132, in start self.asyncio_loop.run_forever() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/ipykernel/kernelapp.py", line 505, in start self.io_loop.start() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/traitlets/config/application.py", line 658, in launch_instance app.start() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/site-packages/ipykernel_launcher.py", line 16, in app.launch_new_instance() File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/runpy.py", line 85, in _run_code exec(code, run_globals) File "/opt/conda/envs/python35-paddle120-env/lib/python3.5/runpy.py", line 193, in _run_module_as_main "main", mod_spec) C++ Callstacks: Tensor holds the wrong type, it holds double at [/paddle/paddle/fluid/framework/tensor_impl.h:29] PaddlePaddle Call Stacks: 0 0x7fd5492d4740p void paddle::platform::EnforceNotMet::Init<char const>(char const, char const, int) + 352 1 0x7fd5492d4ab9p paddle::platform::EnforceNotMet::EnforceNotMet(std::__exception_ptr::exception_ptr, char const, int) + 137 2 0x7fd5492dbbd2p float const paddle::framework::Tensor::data() const + 194 3 0x7fd549b3e261p void paddle::operators::ElementwiseComputeEx<paddle::operators::SubFunctor, paddle::platform::CPUDeviceContext, float, float>(paddle::framework::ExecutionContext const&, paddle::framework::Tensor const, paddle::framework::Tensor const, int, paddle::operators::SubFunctor, paddle::framework::Tensor) + 65 4 0x7fd549ef2db5p paddle::operators::ElementwiseSubKernel<paddle::platform::CPUDeviceContext, float>::Compute(paddle::framework::ExecutionContext const&) const + 421 5 0x7fd549ef3013p std::_Function_handler<void (paddle::framework::ExecutionContext const&), paddle::framework::OpKernelRegistrarFunctor<paddle::platform::CPUPlace, false, 0ul, paddle::operators::ElementwiseSubKernel<paddle::platform::CPUDeviceContext, float>, paddle::operators::ElementwiseSubKernel<paddle::platform::CPUDeviceContext, double>, paddle::operators::ElementwiseSubKernel<paddle::platform::CPUDeviceContext, int>, paddle::operators::ElementwiseSubKernel<paddle::platform::CPUDeviceContext, long> >::operator()(char const, char const, int) const::{lambda(paddle::framework::ExecutionContext const&)#1 (closed)}>::M_invoke(std::Any_data const&, paddle::framework::ExecutionContext const&) + 35 6 0x7fd54a480a96p paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&, paddle::framework::RuntimeContext*) const + 662 7 0x7fd54a481594p paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&) const + 292 8 0x7fd54a47f76bp paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&) + 267 9 0x7fd549439f3ep paddle::framework::Executor::RunPreparedContext(paddle::framework::ExecutorPrepareContext*, paddle::framework::Scope*, bool, bool, bool) + 158 10 0x7fd54943cf1fp paddle::framework::Executor::Run(paddle::framework::ProgramDesc const&, paddle::framework::Scope*, int, bool, bool, std::vector<std::string, std::allocatorstd::string > const&, bool) + 143 11 0x7fd5492c53cep 12 0x7fd5493040fep 13 0x7fd58c863199p PyCFunction_Call + 233 14 0x7fd58c8fe3f9p PyEval_EvalFrameEx + 33545 15 0x7fd58c9004b6p 16 0x7fd58c8fd5b5p PyEval_EvalFrameEx + 29893 17 0x7fd58c9004b6p 18 0x7fd58c8fd5b5p PyEval_EvalFrameEx + 29893 19 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 20 0x7fd58c9004b6p 21 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 22 0x7fd58c9005ebp PyEval_EvalCode + 59 23 0x7fd58c8f3c5dp 24 0x7fd58c863179p PyCFunction_Call + 201 25 0x7fd58c8fddbep PyEval_EvalFrameEx + 31950 26 0x7fd58c837410p _PyGen_Send + 128 27 0x7fd58c8fc953p PyEval_EvalFrameEx + 26723 28 0x7fd58c837410p _PyGen_Send + 128 29 0x7fd58c8fc953p PyEval_EvalFrameEx + 26723 30 0x7fd58c837410p _PyGen_Send + 128 31 0x7fd58c8fdd60p PyEval_EvalFrameEx + 31856 32 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 33 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 34 0x7fd58c9004b6p 35 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 36 0x7fd58c83fc33p 37 0x7fd58c80e33ap PyObject_Call + 106 38 0x7fd58c8f86eep PyEval_EvalFrameEx + 9726 39 0x7fd58c9004b6p 40 0x7fd58c8fd5b5p PyEval_EvalFrameEx + 29893 41 0x7fd58c8366bap 42 0x7fd58c8f1af6p 43 0x7fd58c863179p PyCFunction_Call + 201 44 0x7fd58c8fddbep PyEval_EvalFrameEx + 31950 45 0x7fd58c9004b6p 46 0x7fd58c8fd5b5p PyEval_EvalFrameEx + 29893 47 0x7fd58c8366bap 48 0x7fd58c8f1af6p 49 0x7fd58c863179p PyCFunction_Call + 201 50 0x7fd58c8fddbep PyEval_EvalFrameEx + 31950 51 0x7fd58c9004b6p 52 0x7fd58c8fd5b5p PyEval_EvalFrameEx + 29893 53 0x7fd58c8366bap 54 0x7fd58c8f1af6p 55 0x7fd58c863179p PyCFunction_Call + 201 56 0x7fd58c8fddbep PyEval_EvalFrameEx + 31950 57 0x7fd58c9004b6p 58 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 59 0x7fd58c83fb56p 60 0x7fd58c80e33ap PyObject_Call + 106 61 0x7fd58c8f86eep PyEval_EvalFrameEx + 9726 62 0x7fd58c837410p _PyGen_Send + 128 63 0x7fd58c8fdd60p PyEval_EvalFrameEx + 31856 64 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 65 0x7fd58c9004b6p 66 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 67 0x7fd58c83fc33p 68 0x7fd58c80e33ap PyObject_Call + 106 69 0x7fd58c8f86eep PyEval_EvalFrameEx + 9726 70 0x7fd58c9004b6p 71 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 72 0x7fd58c83fb56p 73 0x7fd58c80e33ap PyObject_Call + 106 74 0x7fd58c973ccap 75 0x7fd58c80e33ap PyObject_Call + 106 76 0x7fd58c8fa4c5p PyEval_EvalFrameEx + 17365 77 0x7fd58c9004b6p 78 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 79 0x7fd58c83fb56p 80 0x7fd58c80e33ap PyObject_Call + 106 81 0x7fd58c8f86eep PyEval_EvalFrameEx + 9726 82 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 83 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 84 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 85 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 86 0x7fd58c8fe1d0p PyEval_EvalFrameEx + 32992 87 0x7fd58c9004b6p 88 0x7fd58c8fd5b5p PyEval_EvalFrameEx + 29893 89 0x7fd58c9004b6p 90 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 91 0x7fd58c9005ebp PyEval_EvalCode + 59 92 0x7fd58c8f3c5dp 93 0x7fd58c863179p PyCFunction_Call + 201 94 0x7fd58c8fddbep PyEval_EvalFrameEx + 31950 95 0x7fd58c9004b6p 96 0x7fd58c8fd5b5p PyEval_EvalFrameEx + 29893 97 0x7fd58c9004b6p 98 0x7fd58c9005a8p PyEval_EvalCodeEx + 72 99 0x7fd58c83fb56p