TensorFlow Graph Execution Error解决：类别维度不匹配问题求助

在Google Colab中使用TensorFlow开发图像分类项目，调用model.fit()训练模型时触发Graph Execution Error，核心报错显示logits_size=[32,49]与labels_size=[32,42]无法广播匹配。以下是问题相关代码、报错信息及解决方法：

数据加载代码 #

from tensorflow.keras.preprocessing.image import ImageDataGenerator
#rescaling
train_datagen_augmented=ImageDataGenerator(rescale=1/255.,
                                           rotation_range=20,
                                           width_shift_range=0.2,
                                           height_shift_range=0.2,
                                           zoom_range=0.2,
                                           horizontal_flip=True)
train_data_augmented=train_datagen_augmented.flow_from_directory(train_dir,
                                                                 target_size=(224,224),
                                                                 batch_size=32,
                                                                 class_mode="categorical")
val_datagen=ImageDataGenerator(rescale=1/255.)
test_datagen=ImageDataGenerator(rescale=1/255.)
val_data=val_datagen.flow_from_directory(val_dir,
                                             target_size=(224,224),
                                             batch_size=32,
                                             class_mode="categorical")
test_data=test_datagen.flow_from_directory(test_dir,
                                             target_size=(224,224),
                                             batch_size=32,
                                             class_mode="categorical")

模型构建与训练代码 #

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D,MaxPool2D,Flatten,Dense
from tensorflow.keras.optimizers.legacy import Adam
model_2=Sequential([
    Conv2D(10,3,activation="relu",input_shape=(224,224,3)),
    Conv2D(10,3,activation="relu"),
    MaxPool2D(),
    Conv2D(10,3,activation="relu"),
    Conv2D(10,3,activation="relu"),
    MaxPool2D(),
    Conv2D(10,3,activation="relu"),
    Conv2D(10,3,activation="relu"),
    MaxPool2D(),
    Conv2D(10,3,activation="relu"),
    Conv2D(10,3,activation="relu"),
    MaxPool2D(),
    Flatten(),
    Dense(49,activation="softmax")

])

model_2.compile(loss="categorical_crossentropy",
                optimizer=Adam(),
                metrics=["accuracy"])

history_2=model_2.fit(train_data_augmented,
                      epochs=5,
                      steps_per_epoch=len(train_data_augmented),
                      validation_data=val_data,
                      validation_steps=len(val_data))

报错信息 #

InvalidArgumentError: graph execution error: detected at node categorical_crossentropy/softmax_cross_entropy_with_logits defined at (most recent call last): file /usr/lib/python3.9/runpy.py, line 197, in _run_module_as_main return _run_code(code, main_globals, none, file /usr/lib/python3.9/runpy.py, line 87, in _run_code exec(code, run_globals) file /usr/local/lib/python3.9/dist-packages/ipykernel_launcher.py, line 16, in <module> app.launch_new_instance() file /usr/local/lib/python3.9/dist-packages/traitlets/config/application.py, line 992, in launch_instance app.start() file /usr/local/lib/python3.9/dist-packages/ipykernel/kernelapp.py, line 612, in start self.io_loop.start() file /usr/local/lib/python3.9/dist-packages/tornado/platform/asyncio.py, line 215, in start self.asyncio_loop.run_forever() file /usr/lib/python3.9/asyncio/base_events.py, line 601, in run_forever self._run_once() file /usr/lib/python3.9/asyncio/base_events.py, line 1905, in _run_once handle._run() file /usr/lib/python3.9/asyncio/events.py, line 80, in _run self._context.run(self._callback, *self._args) file /usr/local/lib/python3.9/dist-packages/tornado/ioloop.py, line 687, in <lambda> lambda f: self._run_callback(functools.partial(callback, future)) file /usr/local/lib/python3.9/dist-packages/tornado/ioloop.py, line 740, in _run_callback ret = callback() file /usr/local/lib/python3.9/dist-packages/tornado/gen.py, line 821, in inner self.ctx_run(self.run) file /usr/local/lib/python3.9/dist-packages/tornado/gen.py, line 782, in run yielded = self.gen.send(value) file /usr/local/lib/python3.9/dist-packages/ipykernel/kernelbase.py, line 365, in process_one yield gen.maybe_future(dispatch(*args)) file /usr/local/lib/python3.9/dist-packages/tornado/gen.py, line 234, in wrapper yielded = ctx_run(next, result) file /usr/local/lib/python3.9/dist-packages/ipykernel/kernelbase.py, line 268, in dispatch_shell yield gen.maybe_future(handler(stream, idents, msg)) file /usr/local/lib/python3.9/dist-packages/tornado/gen.py, line 234, in wrapper yielded = ctx_run(next, result) file /usr/local/lib/python3.9/dist-packages/ipykernel/kernelbase.py, line 543, in execute_request self.do_execute( file /usr/local/lib/python3.9/dist-packages/tornado/gen.py, line 234, in wrapper yielded = ctx_run(next, result) file /usr/local/lib/python3.9/dist-packages/ipykernel/ipkernel.py, line 306, in do_execute res = shell.run_cell(code, store_history=store_history, silent=silent) file /usr/local/lib/python3.9/dist-packages/ipykernel/zmqshell.py, line 536, in run_cell return super(zmqinteractiveshell, self).run_cell(*args, **kwargs) file /usr/local/lib/python3.9/dist-packages/ipython/core/interactiveshell.py, line 2854, in run_cell result = self._run_cell( file /usr/local/lib/python3.9/dist-packages/ipython/core/interactiveshell.py, line 2881, in _run_cell return runner(coro) file /usr/local/lib/python3.9/dist-packages/ipython/core/async_helpers.py, line 68, in _pseudo_sync_runner coro.send(none) file /usr/local/lib/python3.9/dist-packages/ipython/core/interactiveshell.py, line 3057, in run_cell_async has_raised = await self.run_ast_nodes(code_ast.body, cell_name, file /usr/local/lib/python3.9/dist-packages/ipython/core/interactiveshell.py, line 3249, in run_ast_nodes if (await self.run_code(code, result, async_=asy)): file /usr/local/lib/python3.9/dist-packages/ipython/core/interactiveshell.py, line 3326, in run_code exec(code_obj, self.user_global_ns, self.user_ns) file <ipython-input-32-58037f05cff1>, line 26, in <module> history_2=model_2.fit(train_data, file /usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py, line 65, in error_handler return fn(*args, **kwargs) file /usr/local/lib/python3.9/dist-packages/keras/engine/training.py, line 1694, in fit val_logs = self.evaluate( file /usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py, line 65, in error_handler return fn(*args, **kwargs) file /usr/local/lib/python3.9/dist-packages/keras/engine/training.py, line 2040, in evaluate tmp_logs = self.test_function(iterator) file /usr/local/lib/python3.9/dist-packages/keras/engine/training.py, line 1820, in test_function return step_function(self, iterator) file /usr/local/lib/python3.9/dist-packages/keras/engine/training.py, line 1804, in step_function outputs = model.distribute_strategy.run(run_step, args=(data,)) file /usr/local/lib/python3.9/dist-packages/keras/engine/training.py, line 1792, in run_step outputs = model.test_step(data) file /usr/local/lib/python3.9/dist-packages/keras/engine/training.py, line 1758, in test_step self.compute_loss(x, y, y_pred, sample_weight) file /usr/local/lib/python3.9/dist-packages/keras/engine/training.py, line 1082, in compute_loss return self.compiled_loss( file /usr/local/lib/python3.9/dist-packages/keras/engine/compile_utils.py, line 265, in __call__ loss_value = loss_obj(y_t, y_p, sample_weight=sw) file /usr/local/lib/python3.9/dist-packages/keras/losses.py, line 152, in __call__ losses = call_fn(y_true, y_pred) file /usr/local/lib/python3.9/dist-packages/keras/losses.py, line 284, in call return ag_fn(y_true, y_pred, **self._fn_kwargs) file /usr/local/lib/python3.9/dist-packages/keras/losses.py, line 2004, in categorical_crossentropy return backend.categorical_crossentropy( file /usr/local/lib/python3.9/dist-packages/keras/backend.py, line 5538, in categorical_crossentropy return tf.nn.softmax_cross_entropy_with_logits( node: categorical_crossentropy/softmax_cross_entropy_with_logits logits and labels must be broadcastable: logits_size=[32,49] labels_size=[32,42] [[{{node categorical_crossentropy/softmax_cross_entropy_with_logits}}]] [op:__inference_test_function_31195] site:stackoverflow.com

解决方法 #

问题根源 #

模型输出层手动设置了49个神经元，但数据集实际类别数为42。flow_from_directory会自动扫描数据集目录下的子文件夹数量作为类别数，两者维度不匹配导致损失计算时无法广播。

修复步骤 #

1. 确认数据集真实类别数：
   数据加载完成后，执行以下代码获取训练集的类别数：

   print("训练集类别数:", train_data_augmented.num_classes)
   

   运行后会输出实际类别数（此处应为42）。

2. 修改模型输出层：
   将模型最后一层的Dense(49, activation="softmax")替换为动态获取的类别数，避免手动设置错误：

   model_2=Sequential([
       # 前面的卷积、池化层保持不变
       Flatten(),
       Dense(train_data_augmented.num_classes, activation="softmax")
   ])
   

3. 重新编译并训练：
   重新编译模型，再执行model.fit()即可解决维度不匹配问题。

额外检查 #

确保训练集、验证集、测试集的目录结构一致，子文件夹数量（类别数）完全相同，避免出现跨数据集类别数不一致的情况。

内容的提问来源于stack exchange，提问作者enesergen