我正在尝试写一个简单的神经网络来分类狗的品种。下面是数据集的链接:https://www.kaggle.com/c/dog-breed-identification
这是我的代码:
import os
import pandas as pd
import numpy
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Dropout, BatchNormalization
from keras.models import Sequential
from keras.optimizers import Adam
from sklearn.model_selection import train_test_split
dogs = pd.read_csv('C:/Users/Natha/Downloads/dog-breed-identification/labels.csv')
ImageHeight = 128
ImageWidth = 128
Depth = 3
from PIL import Image
import os, sys
path = ('C:/Users/Natha/Downloads/dog-breed-identification/train')
def resize():
for item in os.listdir(path):
if os.path.isfile(item):
im = Image.open(item)
f, e = os.path.splitext(item)
imResize = im.resize((ImageHeight,ImageWidth), Image.ANTIALIAS)
imResize.save(f + ' resized.jpg', 'JPEG', quality=90)
return imResize
resize()
X = dogs['id']
y = dogs['breed']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(ImageHeight, ImageWidth, Depth)))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dense(2, activation='sigmoid'))
model.compile(optimizer=Adam(learning_rate=0.001), loss='categorical_crossentropy', metrics=['accuracy'])
history = model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test))
ValueError Traceback (most recent call last)
<ipython-input-83-bab577512e44> in <module>
----> 1 model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test))
~anaconda3libsite-packagestensorflowpythonkerasenginetraining.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
1098 _r=1):
1099 callbacks.on_train_batch_begin(step)
-> 1100 tmp_logs = self.train_function(iterator)
1101 if data_handler.should_sync:
1102 context.async_wait()
~anaconda3libsite-packagestensorflowpythoneagerdef_function.py in __call__(self, *args, **kwds)
826 tracing_count = self.experimental_get_tracing_count()
827 with trace.Trace(self._name) as tm:
--> 828 result = self._call(*args, **kwds)
829 compiler = "xla" if self._experimental_compile else "nonXla"
830 new_tracing_count = self.experimental_get_tracing_count()
~anaconda3libsite-packagestensorflowpythoneagerdef_function.py in _call(self, *args, **kwds)
869 # This is the first call of __call__, so we have to initialize.
870 initializers = []
--> 871 self._initialize(args, kwds, add_initializers_to=initializers)
872 finally:
873 # At this point we know that the initialization is complete (or less
~anaconda3libsite-packagestensorflowpythoneagerdef_function.py in _initialize(self, args, kwds, add_initializers_to)
723 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
724 self._concrete_stateful_fn = (
--> 725 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
726 *args, **kwds))
727
~anaconda3libsite-packagestensorflowpythoneagerfunction.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2967 args, kwargs = None, None
2968 with self._lock:
-> 2969 graph_function, _ = self._maybe_define_function(args, kwargs)
2970 return graph_function
2971
~anaconda3libsite-packagestensorflowpythoneagerfunction.py in _maybe_define_function(self, args, kwargs)
3359
3360 self._function_cache.missed.add(call_context_key)
-> 3361 graph_function = self._create_graph_function(args, kwargs)
3362 self._function_cache.primary[cache_key] = graph_function
3363
~anaconda3libsite-packagestensorflowpythoneagerfunction.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3194 arg_names = base_arg_names + missing_arg_names
3195 graph_function = ConcreteFunction(
-> 3196 func_graph_module.func_graph_from_py_func(
3197 self._name,
3198 self._python_function,
~anaconda3libsite-packagestensorflowpythonframeworkfunc_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
988 _, original_func = tf_decorator.unwrap(python_func)
989
--> 990 func_outputs = python_func(*func_args, **func_kwargs)
991
992 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~anaconda3libsite-packagestensorflowpythoneagerdef_function.py in wrapped_fn(*args, **kwds)
632 xla_context.Exit()
633 else:
--> 634 out = weak_wrapped_fn().__wrapped__(*args, **kwds)
635 return out
636
~anaconda3libsite-packagestensorflowpythonframeworkfunc_graph.py in wrapper(*args, **kwargs)
975 except Exception as e: # pylint:disable=broad-except
976 if hasattr(e, "ag_error_metadata"):
--> 977 raise e.ag_error_metadata.to_exception(e)
978 else:
979 raise
ValueError: in user code:
C:UsersNathaanaconda3libsite-packagestensorflowpythonkerasenginetraining.py:805 train_function *
return step_function(self, iterator)
C:UsersNathaanaconda3libsite-packagestensorflowpythonkerasenginetraining.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:UsersNathaanaconda3libsite-packagestensorflowpythondistributedistribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:UsersNathaanaconda3libsite-packagestensorflowpythondistributedistribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:UsersNathaanaconda3libsite-packagestensorflowpythondistributedistribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
C:UsersNathaanaconda3libsite-packagestensorflowpythonkerasenginetraining.py:788 run_step **
outputs = model.train_step(data)
C:UsersNathaanaconda3libsite-packagestensorflowpythonkerasenginetraining.py:754 train_step
y_pred = self(x, training=True)
C:UsersNathaanaconda3libsite-packagestensorflowpythonkerasenginebase_layer.py:998 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
C:UsersNathaanaconda3libsite-packagestensorflowpythonkerasengineinput_spec.py:234 assert_input_compatibility
raise ValueError('Input ' + str(input_index) + ' of layer ' +
ValueError: Input 0 of layer sequential_7 is incompatible with the layer: : expected min_ndim=4, found ndim=2. Full shape received: (None, 1)
这些是模块的版本:
Keras: 2.4.2
Tensorflow:测试盒框
熊猫:1.1.3
我是神经网络的新手，每当我尝试做一个项目时，当我尝试训练模型时就会出现这种情况。如果有人知道如何解决这个问题，请回答这个。提前谢谢你。
您需要检查您的数据维度。基于你的模型架构，我期望X_train是形状(n_samples,128,128,3), y_train是形状(n_samples,2)。考虑到这一点，我用这些图像大小的随机数据做了这个测试问题，并且模型训练没有任何错误。
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, BatchNormalization, MaxPooling2D, Dropout, Flatten, Dense
import numpy as np
X_train = np.random.rand(1000,128,128,3)
y_train = np.random.rand(1000,2)
X_test = np.random.rand(200,128,128,3)
y_test = np.random.rand(200,2)
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dense(2, activation='sigmoid'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
history = model.fit(X_train, y_train, epochs=10, validation_data=(X_test,y_test))
记住这一点，打印出你的数据的形状，以确保它符合你的期望，并记住，我上面使用的形状工作正常。