@lespaulposted at 2022-09-25

ValueError: Layer "model" expects 1 input(s), but it received 8 input tensors.

Discussion

Python error DeepLearning TensorFlow Unet

deep learningでのエラー

pythonでdeep learningを実施している初心者です。
Unetを構築しアーチファクト除去を目指しており、とりあえず試しでデータセット10枚(512＊512)で学習を行ったところエラーが発生しました。
もう二週間手詰まりしています。どんな些細なことでもいいのでアドバイスください。

発生している問題・エラー

Epoch 1/2
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [3], in <cell line: 3>()
      1 #学習
      2 data_valid =(x_test, y_test)
----> 3 history = model.ﬁt(x_train, y_train, batch_size=2, epochs=2,verbose=2, validation_data=data_valid,shuffle=True)

File ~\anaconda3\lib\site-packages\keras\utils\traceback_utils.py:67, in filter_traceback.<locals>.error_handler(*args, **kwargs)
     65 except Exception as e:  # pylint: disable=broad-except
     66   filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67   raise e.with_traceback(filtered_tb) from None
     68 finally:
     69   del filtered_tb

File ~\AppData\Local\Temp\__autograph_generated_fileqpnspcz3.py:15, in outer_factory.<locals>.inner_factory.<locals>.tf__train_function(iterator)
     13 try:
     14     do_return = True
---> 15     retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
     16 except:
     17     do_return = False

ValueError: in user code:

    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 1051, in train_function  *
        return step_function(self, iterator)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 1040, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 1030, in run_step  **
        outputs = model.train_step(data)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 889, in train_step
        y_pred = self(x, training=True)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\input_spec.py", line 200, in assert_input_compatibility
        raise ValueError(f'Layer "{layer_name}" expects {len(input_spec)} input(s),'

    ValueError: Layer "model" expects 1 input(s), but it received 8 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(2, 512, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:1' shape=(2, 512, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:2' shape=(2, 512, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:3' shape=(2, 512, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:4' shape=(2, 512, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:5' shape=(2, 512, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:6' shape=(2, 512, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:7' shape=(2, 512, 1) dtype=float32>]

該当するソースコード

#dataset
ORG_DATA=os.path.join(DATASET,'data4')
SV_DATA=os.path.join(DATASET,'data5')

#Unet
model=Unet()

#netの中身
model.summary()

#np画像
x=ImageLoder(ORG_DATA).load()
y=ImageLoder(SV_DATA).load()

#train,validationに分ける
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)

#学習
history = model.ﬁt(x_train, y_train, batch_size=1, epochs=2,verbose=2, validation_data=(x_test, y_test),shuffle=True)

model.fitでエラーが生じている状態です。

Unetのコード

from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, Concatenate,BatchNormalization,Activation

#U-Netの定義
def Unet(class_num = 2, gpu_num = 1):
    input_layer = Input(shape=(512,512,1))

    conv11 = Conv2D(32,(3,3),padding='same')(input_layer)
    batch11 = BatchNormalization()(conv11)
    acti11 = Activation('relu')(batch11)
    conv12 = Conv2D(32,(3,3), padding='same')(acti11)
    batch12 = BatchNormalization()(conv12)
    acti12 = Activation('relu')(batch12)
    conv13 = Conv2D(32,(3,3),padding='same')(acti12)
    batch13 = BatchNormalization()(conv13)
    acti13 = Activation('relu')(batch13)
    conv14 = Conv2D(32,(3,3), padding='same')(acti13)
    batch14 = BatchNormalization()(conv14)
    acti14 = Activation('relu')(batch14)
    pool1 = MaxPooling2D()(acti14)
    
    conv21 = Conv2D(64, (3,3), padding = 'same')(pool1)
    batch21 = BatchNormalization()(conv21)
    acti21 = Activation('relu')(batch21)
    conv22 = Conv2D(64, (3,3), padding = 'same')(acti21)
    batch22 = BatchNormalization()(conv22)
    acti22 = Activation('relu')(batch22)
    conv23 = Conv2D(64, (3,3), padding = 'same')(acti22)
    batch23 = BatchNormalization()(conv23)
    acti23 = Activation('relu')(batch23)
    conv24 = Conv2D(64, (3,3), padding = 'same')(acti23)
    batch24 = BatchNormalization()(conv24)
    acti24 = Activation('relu')(batch24)
    pool2 = MaxPooling2D()(acti24)
    
    conv31 = Conv2D(128, (3,3), padding = 'same')(pool2)
    batch31 = BatchNormalization()(conv31)
    acti31 = Activation('relu')(batch31)
    conv32 = Conv2D(128, (3,3), padding = 'same')(acti31)
    batch32 = BatchNormalization()(conv32)
    acti32 = Activation('relu')(batch32)
    conv33 = Conv2D(128, (3,3), padding = 'same')(acti32)
    batch33 = BatchNormalization()(conv33)
    acti33 = Activation('relu')(batch33)
    conv34 = Conv2D(128, (3,3), padding = 'same')(acti33)
    batch34 = BatchNormalization()(conv34)
    acti34 = Activation('relu')(batch34)
    pool3 = MaxPooling2D()(acti34)
    
    conv41 = Conv2D(256, (3,3), padding = 'same')(pool3)
    batch41 = BatchNormalization()(conv41)
    acti41 = Activation('relu')(batch41)
    conv42 = Conv2D(256, (3,3), padding = 'same')(acti41)
    batch42 = BatchNormalization()(conv42)
    acti42 = Activation('relu')(batch42)
    conv43 = Conv2D(256, (3,3), padding = 'same')(acti42)
    batch43 = BatchNormalization()(conv43)
    acti43 = Activation('relu')(batch43)
    conv44 = Conv2D(256, (3,3), padding = 'same')(acti43)
    batch44 = BatchNormalization()(conv44)
    acti44 = Activation('relu')(batch44)
    pool4 = MaxPooling2D()(acti44)
    
    conv01 = Conv2D(512, (3,3), padding = 'same')(pool4)
    batch01 = BatchNormalization()(conv01)
    acti01 = Activation('relu')(batch01)
    conv02 = Conv2D(512, (3,3), padding = 'same')(acti01)
    batch02 = BatchNormalization()(conv02)
    acti02 = Activation('relu')(batch02)
    conv03 = Conv2D(512, (3,3), padding = 'same')(acti02)
    batch03 = BatchNormalization()(conv03)
    acti03 = Activation('relu')(batch03)
    conv04 = Conv2D(512, (3,3), padding = 'same')(acti03)
    batch04 = BatchNormalization()(conv04)
    acti04 = Activation('relu')(batch04)
    pool0 = MaxPooling2D()(acti04)
    
    conv51 = Conv2D(1024, (3,3),padding = 'same')(pool0)
    batch51 = BatchNormalization()(conv51)
    acti51 = Activation('relu')(batch51)
    conv52 = Conv2D(1024, (3,3), padding = 'same')(acti51)
    batch52 = BatchNormalization()(conv52)
    acti52 = Activation('relu')(batch52)
    
    up6 = UpSampling2D()(acti52)
    concat6 = Concatenate()([up6,acti04])
    conv61 = Conv2D(512, (3,3), padding = 'same')(concat6)
    batch61 = BatchNormalization()(conv61)
    acti61 = Activation('relu')(batch61)
    conv62 = Conv2D(512, (3,3), padding = 'same')(acti61)
    batch62 = BatchNormalization()(conv62)
    acti62 = Activation('relu')(batch62)
    conv63 = Conv2D(512, (3,3), padding = 'same')(acti62)
    batch63 = BatchNormalization()(conv63)
    acti63 = Activation('relu')(batch63)
    conv64 = Conv2D(512, (3,3), padding = 'same')(acti63)
    batch64 = BatchNormalization()(conv64)
    acti64 = Activation('relu')(batch64)
    
    up10 = UpSampling2D()(acti64)
    concat10 = Concatenate()([up10,acti44])
    conv101 = Conv2D(256, (3,3), padding = 'same')(concat10)
    batch101 = BatchNormalization()(conv101)
    acti101 = Activation('relu')(batch101)
    conv102 = Conv2D(256, (3,3), padding = 'same')(acti101)
    batch102 = BatchNormalization()(conv102)
    acti102 = Activation('relu')(batch102)

    
    up7 = UpSampling2D()(acti102)
    concat7 = Concatenate()([up7,acti34])
    conv71 = Conv2D(128, (3,3), padding = 'same')(concat7)
    batch71 = BatchNormalization()(conv71)
    acti71 = Activation('relu')(batch71)
    conv72 = Conv2D(128, (3,3), padding = 'same')(acti71)
    batch72 = BatchNormalization()(conv72)
    acti72 = Activation('relu')(batch72)

    
    up8 = UpSampling2D()(acti72)
    concat8 = Concatenate()([up8,acti24])
    conv81 = Conv2D(64, (3,3), padding = 'same')(concat8)
    batch81 = BatchNormalization()(conv81)
    acti81 = Activation('relu')(batch81)
    conv82 = Conv2D(64, (3,3), padding = 'same')(acti81)
    batch82 = BatchNormalization()(conv82)
    acti82 = Activation('relu')(batch82)
    
    up9 = UpSampling2D()(acti82)
    concat9 = Concatenate()([up9,acti14])
    conv91 = Conv2D(32, (3,3), padding = 'same')(concat9)
    batch91 = BatchNormalization()(conv91)
    acti91 = Activation('relu')(batch91)
    conv92 = Conv2D(32, (3,3), padding = 'same')(acti91)
    batch92 = BatchNormalization()(conv92)
    acti92 = Activation('relu')(batch92)

    
    output_layer = Conv2D(1,(3,3), activation='sigmoid',padding='same')(acti92)
    
    model = Model(inputs = input_layer, outputs = output_layer)
    
    
    if gpu_num >= 2:
        model = multi_model(model,gpus=gpu_num)
        
    adam = Adam(lr=0.0001)
    model.compile(optimizer=adam, loss='mean_squared_error',metrics=['acc'])
    
    return model

ImageLoderのコード

import numpy as np
import cv2,os,glob
from PIL import Image

class ImageLoder():
    def __init__(self,dl_path,image_size=512*512):
        self.dl_path=dl_path
        self.image_size=image_size
    
    def load(self):
        image=[]
        file=glob.glob(os.path.join(self.dl_path,'*.png'))#パス内にあるPNGを持ってくる
        for file_path in file:
            
            ############
            ###np配列###
            ############
            img=Image.open(file_path)
            img=np.array(img)#np配列
            
            ############
            ###正規化###
            ############
            if np.max(img)==0:#ゼロの時はそのまま
                m=1
            else:#それ以外は最大値で除算
                m=np.max(img)
            img=img/m
            
            img=img.reshape(512,512,-1)#512の形に
            img = img.astype(np.float32)
            image.append(img)#image[]内に格納
        return image

0 likes

@PondVillege posted at 2022-09-25

ImageLoad().load()した後に得られたxとyにおいてx.shapeやy.shapeはどのようになっていますか？

0Like

@lespaul posted at 2022-09-25

@PondVillegeさん
両方とも(512, 512, 1)です

0Like

@PondVillege posted at 2022-09-25

1画像のみで，縦横512ピクセル，1チャンネルということですか？

0Like

@lespaul posted at 2022-09-25

そうです！
print(x[0].shape)、print(y[0].shape)の答えです。
[1]でも同様の結果でした。

0Like

@PondVillege posted at 2022-09-25

[0]なしでx.shapeとy.shapeを出したらどうなりますか？

0Like

@lespaul posted at 2022-09-25

エラーが生じました。
AttributeError: 'list' object has no attribute 'shape'

0Like

@PondVillege posted at 2022-09-25

ImageLoader()に問題があることがわかりました．

            image.append(img)#image[]内に格納
-       image=np.array(img)
+       image=np.array(image)
        image=image.astype('float32')

のように変更してください．また，その後に得られたx.shapeとy.shapeも教えていただけるとありがたいです．

0Like

@lespaul posted at 2022-09-25

(10, 512, 512, 1)
x,yともにこのようになりました！

1Like

@PondVillege posted at 2022-09-25

すみません，ImageLoader()を拝見して返信内容を全部書き換えました．参照お願いします．

0Like

@lespaul posted at 2022-09-25

image=np.array(image)

に直したところ

print(x.shape)
>>>AttributeError:'list' object has no attribute 'shape'

同様のエラーが発生いたしました。

0Like

@lespaul posted at 2022-09-25

すみません。
ImageLoderの記載したコードが間違っていました。
編集いたしましたので確認お願いいたします。

0Like

@PondVillege posted at 2022-09-25

であればImageLoader().load()の最後のところ，

-       return image
+       return np.array(image)

としてください．その上で

#np画像
x=ImageLoder(ORG_DATA).load()
y=ImageLoder(SV_DATA).load()

print(x.shape, y.shape)

の出力結果を教えてください．おそらく(10, 512, 512, 1)が得られるはずです．

0Like

@lespaul posted at 2022-09-25

(10, 512, 512, 1)になりました。

0Like

@PondVillege posted at 2022-09-25

弊環境ではそのようにできた時点でエラーは消えて学習できましたが，どうでしょうか．まだ同じエラーが出ますか？

参考の為再現例を示しておきます．

import numpy as np
from sklearn.model_selection import train_test_split

from unet import Unet

def error_producing_data(): # エラーを再現するデータ
    x, y = list(), list()
    for i in range(10):
        x.append(np.zeros((512, 512, 1), dtype = np.float32))
        y.append(np.zeros((512, 512, 1), dtype = np.float32))
    return x, y

def no_error_data(): # エラーが起きないデータ
    x, y = list(), list()
    for i in range(10):
        x.append(np.zeros((512, 512, 1), dtype = np.float32))
        y.append(np.zeros((512, 512, 1), dtype = np.float32))
    return np.array(x), np.array(y)

x, y = error_producing_data() # エラーが起きる方を採用する
#x, y = no_error_data() # コメントアウトを外してエラーが起きない方を採用する

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)

model = Unet()
model.fit(x_train, y_train, batch_size = 1, validation_data = (x_test, y_test), shuffle=True)

x, yの定義をno_error_data()の方でやるとエラーは消えます．

0Like

@lespaul posted at 2022-09-25

同じではないのですがエラーが出てしまいました、、、

---------------------------------------------------------------------------
UnimplementedError                        Traceback (most recent call last)
Input In [8], in <cell line: 2>()
      1 #学習
----> 2 history = model.ﬁt(x_train, y_train, batch_size=1, epochs=2,verbose=1, validation_data=(x_test, y_test),shuffle=True)

File ~\anaconda3\lib\site-packages\keras\utils\traceback_utils.py:67, in filter_traceback.<locals>.error_handler(*args, **kwargs)
     65 except Exception as e:  # pylint: disable=broad-except
     66   filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67   raise e.with_traceback(filtered_tb) from None
     68 finally:
     69   del filtered_tb

File ~\anaconda3\lib\site-packages\tensorflow\python\eager\execute.py:54, in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     52 try:
     53   ctx.ensure_initialized()
---> 54   tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
     55                                       inputs, attrs, num_outputs)
     56 except core._NotOkStatusException as e:
     57   if name is not None:

UnimplementedError: Graph execution error:

Detected at node 'model_2/conv2d_70/Conv2D' defined at (most recent call last):
    File "C:\Users\+\anaconda3\lib\runpy.py", line 197, in _run_module_as_main
      return _run_code(code, main_globals, None,
    File "C:\Users\+\anaconda3\lib\runpy.py", line 87, in _run_code
      exec(code, run_globals)
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel_launcher.py", line 16, in <module>
      app.launch_new_instance()
    File "C:\Users\+\anaconda3\lib\site-packages\traitlets\config\application.py", line 846, in launch_instance
      app.start()
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 677, in start
      self.io_loop.start()
    File "C:\Users\+\anaconda3\lib\site-packages\tornado\platform\asyncio.py", line 199, in start
      self.asyncio_loop.run_forever()
    File "C:\Users\+\anaconda3\lib\asyncio\base_events.py", line 601, in run_forever
      self._run_once()
    File "C:\Users\+\anaconda3\lib\asyncio\base_events.py", line 1905, in _run_once
      handle._run()
    File "C:\Users\+\anaconda3\lib\asyncio\events.py", line 80, in _run
      self._context.run(self._callback, *self._args)
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 471, in dispatch_queue
      await self.process_one()
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 460, in process_one
      await dispatch(*args)
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 367, in dispatch_shell
      await result
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 662, in execute_request
      reply_content = await reply_content
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 360, in do_execute
      res = shell.run_cell(code, store_history=store_history, silent=silent)
    File "C:\Users\+\anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 532, in run_cell
      return super().run_cell(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2863, in run_cell
      result = self._run_cell(
    File "C:\Users\+\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2909, in _run_cell
      return runner(coro)
    File "C:\Users\+\anaconda3\lib\site-packages\IPython\core\async_helpers.py", line 129, in _pseudo_sync_runner
      coro.send(None)
    File "C:\Users\+\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 3106, in run_cell_async
      has_raised = await self.run_ast_nodes(code_ast.body, cell_name,
    File "C:\Users\+\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 3309, in run_ast_nodes
      if await self.run_code(code, result, async_=asy):
    File "C:\Users\lespa\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 3369, in run_code
      exec(code_obj, self.user_global_ns, self.user_ns)
    File "C:\Users\+\AppData\Local\Temp\ipykernel_18604\3103197915.py", line 2, in <cell line: 2>
      history = model.ﬁt(x_train, y_train, batch_size=1, epochs=2,verbose=1, validation_data=(x_test, y_test),shuffle=True)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 64, in error_handler
      return fn(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 1409, in fit
      tmp_logs = self.train_function(iterator)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 1051, in train_function
      return step_function(self, iterator)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 1040, in step_function
      outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 1030, in run_step
      outputs = model.train_step(data)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 889, in train_step
      y_pred = self(x, training=True)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 64, in error_handler
      return fn(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\training.py", line 490, in __call__
      return super().__call__(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 64, in error_handler
      return fn(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\base_layer.py", line 1014, in __call__
      outputs = call_fn(inputs, *args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 92, in error_handler
      return fn(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\functional.py", line 458, in call
      return self._run_internal_graph(
    File "C:\Users\+\anaconda3\lib\site-packages\keras\engine\functional.py", line 596, in _run_internal_graph
      outputs = node.layer(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 64, in error_handler
      return fn(*args, **kwargs)
    File "C:\Users\lespa\anaconda3\lib\site-packages\keras\engine\base_layer.py", line 1014, in __call__
      outputs = call_fn(inputs, *args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 92, in error_handler
      return fn(*args, **kwargs)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\layers\convolutional\base_conv.py", line 250, in call
      outputs = self.convolution_op(inputs, self.kernel)
    File "C:\Users\+\anaconda3\lib\site-packages\keras\layers\convolutional\base_conv.py", line 225, in convolution_op
      return tf.nn.convolution(
Node: 'model_2/conv2d_70/Conv2D'
DNN library is not found.
	 [[{{node model_2/conv2d_70/Conv2D}}]] [Op:__inference_train_function_25175]

1Like

@PondVillege posted at 2022-09-25

関数Unet内ではモデルは1つしか定義されていないので，model_2の出どころが不明です．gpu_numを3にしてmulti_model()を適用されたのでしょうか？それとも3度目のmodel = Unet()がどこかに記述されているのでしょうか．

いずれにしろ，調べたところcuDNNに原因があるようですので，コードが間違っていないか確認するためCPU環境での実行をお願いします．CPU環境でエラーが起きないのであれば，そちらのGPU環境に原因がありますので，コードに関して改善するべき案はもうありません．

0Like

@lespaul posted at 2022-09-26

if gpu_num >= 2:
        model = multi_model(model,gpus=gpu_num)

の部分でしょうか？
テキストを参考にUnetを書いたのでそこまで理解できていないです、、、、

ちなみにこの部分をコメントアウトしても同様のエラーが発生いたしました。

0Like

@PondVillege posted at 2022-09-26

恐らく自動でGPU環境を使っているのでエラーが変わらないのだと思います．

コードの初めに

import os
os.environ["CUDA_VISIBLE_DEVICES"]="-1"

とするなり

with tf.device("/cpu:0"):
    model = Unet()
    model.fit(...)

のようにしてCPU環境で実行してみてください．

0Like

@lespaul posted at 2022-09-26

学習できました！

1Like

@PondVillege posted at 2022-09-26

では，GPUを使いたいときには2つ前の解答を参照して解決なさってください．お疲れ様でした．

0Like

@lespaul posted at 2022-09-26

本当に助かりました。
何から何までありがとうございました、

1Like

Are you sure you want to delete the question?

ValueError: Layer "model" expects 1 input(s), but it received 8 input tensors.

deep learningでのエラー

発生している問題・エラー

該当するソースコード

Unetのコード

ImageLoderのコード

Your answer might help someone💌