如何在不同形状的数据集上实现 VGG-net？
How can I implement VGG-net on a dataset of different shape?
我正在尝试使用 VGG16 模型的一部分通过 Fashion MNIST 数据集进行迁移学习。处理数据并指定模型如下：
data = keras.datasets.fashion_mnist
(train_img, train_labels), (test_img, test_labels) = data.load_data()
train_img.shape, train_labels.shape, test_img.shape, test_labels.shape
#((60000, 28, 28), (60000,), (10000, 28, 28), (10000,))
# transform to rgb as required by VGG
train_img=tf.image.grayscale_to_rgb(tf.expand_dims(train_img, axis=3))
test_img=tf.image.grayscale_to_rgb(tf.expand_dims(test_img, axis=3))
#resize to minimum size of (32x32
train_img=tf.image.resize_with_pad(train_img,32,32)
test_img=tf.image.resize_with_pad(train_img,32,32)
train_img = train_img / 255.
test_img = test_img / 255.
from keras.applications.vgg16 import preprocess_input
train_img = tf.expand_dims(train_img, axis=0)
test_img = tf.expand_dims(test_img, axis=0)
#preprocessing as required by VGG16
train_img=preprocess_input(train_img)
test_img=preprocess_input(test_img)
#using model without last layers
vgg16=tf.keras.applications.VGG16(include_top=False, weights='imagenet', input_shape=(32,32,3))
layer_dict = dict([(layer.name, layer) for layer in vgg16.layers])
#stop at block3_pool and get output
output = layer_dict['block3_pool'].output
x = keras.layers.Flatten()(output)
...add some fully connected layers here...
x = keras.layers.Dense(10, activation='softmax')(x)
final = keras.models.Model(inputs=vgg16.input, outputs=model)
for layer in final.layers[:7]:
layer.trainable = False
final.fit(train_img, train_labels, epochs=50, validation_split=0.2)
当我尝试拟合模型时出现以下错误：
UnboundLocalError Traceback (most recent call last)
<ipython-input-65-6a0b99b56337> in <module>()
1 early_stopping_cb=keras.callbacks.EarlyStopping(patience=3, verbose=1,restore_best_weights=True)
----> 2 vgg16_1.fit(train_img, train_labels, epochs=50, validation_split=0.2, callbacks=[early_stopping_cb])
1 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.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, **kwargs)
857 logs = tmp_logs # No error, now safe to assign to logs.
858 callbacks.on_train_batch_end(step, logs)
--> 859 epoch_logs = copy.copy(logs)
860
861 # Run validation.
UnboundLocalError: local variable 'logs' referenced before assignment
我认为这可能是由于训练集形状有问题，但如果我改用 train_img[0]，其形状为 (60000,32,32,3)，那么我得到而是以下错误：
ValueError Traceback (most recent call last)
<ipython-input-66-2b893ccd9ac9> in <module>()
1 early_stopping_cb=keras.callbacks.EarlyStopping(patience=3, verbose=1,restore_best_weights=True)
----> 2 vgg16_1.fit(train_img[0], train_labels, epochs=50, validation_split=0.2, callbacks=[early_stopping_cb])
10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
64 def _method_wrapper(self, *args, **kwargs):
65 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
---> 66 return method(self, *args, **kwargs)
67
68 # Running inside `run_distribute_coordinator` already.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.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, **kwargs)
849 batch_size=batch_size):
850 callbacks.on_train_batch_begin(step)
--> 851 tmp_logs = train_function(iterator)
852 # Catch OutOfRangeError for Datasets of unknown size.
853 # This blocks until the batch has finished executing.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
578 xla_context.Exit()
579 else:
--> 580 result = self._call(*args, **kwds)
581
582 if tracing_count == self._get_tracing_count():
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
625 # This is the first call of __call__, so we have to initialize.
626 initializers = []
--> 627 self._initialize(args, kwds, add_initializers_to=initializers)
628 finally:
629 # At this point we know that the initialization is complete (or less
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
504 self._concrete_stateful_fn = (
505 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 506 *args, **kwds))
507
508 def invalid_creator_scope(*unused_args, **unused_kwds):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2444 args, kwargs = None, None
2445 with self._lock:
-> 2446 graph_function, _, _ = self._maybe_define_function(args, kwargs)
2447 return graph_function
2448
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
2775
2776 self._function_cache.missed.add(call_context_key)
-> 2777 graph_function = self._create_graph_function(args, kwargs)
2778 self._function_cache.primary[cache_key] = graph_function
2779 return graph_function, args, kwargs
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
2665 arg_names=arg_names,
2666 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2667 capture_by_value=self._capture_by_value),
2668 self._function_attributes,
2669 # Tell the ConcreteFunction to clean up its graph once it goes out of
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_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)
979 _, original_func = tf_decorator.unwrap(python_func)
980
--> 981 func_outputs = python_func(*func_args, **func_kwargs)
982
983 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
439 # __wrapped__ allows AutoGraph to swap in a converted function. We give
440 # the function a weak reference to itself to avoid a reference cycle.
--> 441 return weak_wrapped_fn().__wrapped__(*args, **kwds)
442 weak_wrapped_fn = weakref.ref(wrapped_fn)
443
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
966 except Exception as e: # pylint:disable=broad-except
967 if hasattr(e, "ag_error_metadata"):
--> 968 raise e.ag_error_metadata.to_exception(e)
969 else:
970 raise
ValueError: in user code:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function *
outputs = self.distribute_strategy.run(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run **
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:533 train_step **
y, y_pred, sample_weight, regularization_losses=self.losses)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:143 __call__
losses = self.call(y_true, y_pred)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:246 call
return self.fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1527 categorical_crossentropy
return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4561 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (32, 1) and (32, 10) are incompatible
这些错误的来源以及我做错了什么的任何线索？感觉我可能错过了一些明显的东西，但作为 Keras 的新手，我无法理解它是什么。非常感谢帮助。
扩展dims需要注释两行如下。发生的事情是它将 train_img 的形状更新为 (1,60000,32,32,3) 并且 model.fit 抱怨您正在使用单个图像进行训练。
#train_img = tf.expand_dims(train_img, axis=0)
#test_img = tf.expand_dims(test_img, axis=0)
我更新了您的代码并分享了 Here. You need to update the architecture to improve it for better accuracy. Follow transfer learning approach mentioned here 并更新了您的代码以提高准确性。谢谢！
似乎问题是我有一个大小为 10 的密集输出层，而标签的大小为 1。解决方案是使用稀疏分类交叉熵损失函数而不是简单分类损失函数。
我正在尝试使用 VGG16 模型的一部分通过 Fashion MNIST 数据集进行迁移学习。处理数据并指定模型如下：
data = keras.datasets.fashion_mnist
(train_img, train_labels), (test_img, test_labels) = data.load_data()
train_img.shape, train_labels.shape, test_img.shape, test_labels.shape
#((60000, 28, 28), (60000,), (10000, 28, 28), (10000,))
# transform to rgb as required by VGG
train_img=tf.image.grayscale_to_rgb(tf.expand_dims(train_img, axis=3))
test_img=tf.image.grayscale_to_rgb(tf.expand_dims(test_img, axis=3))
#resize to minimum size of (32x32
train_img=tf.image.resize_with_pad(train_img,32,32)
test_img=tf.image.resize_with_pad(train_img,32,32)
train_img = train_img / 255.
test_img = test_img / 255.
from keras.applications.vgg16 import preprocess_input
train_img = tf.expand_dims(train_img, axis=0)
test_img = tf.expand_dims(test_img, axis=0)
#preprocessing as required by VGG16
train_img=preprocess_input(train_img)
test_img=preprocess_input(test_img)
#using model without last layers
vgg16=tf.keras.applications.VGG16(include_top=False, weights='imagenet', input_shape=(32,32,3))
layer_dict = dict([(layer.name, layer) for layer in vgg16.layers])
#stop at block3_pool and get output
output = layer_dict['block3_pool'].output
x = keras.layers.Flatten()(output)
...add some fully connected layers here...
x = keras.layers.Dense(10, activation='softmax')(x)
final = keras.models.Model(inputs=vgg16.input, outputs=model)
for layer in final.layers[:7]:
layer.trainable = False
final.fit(train_img, train_labels, epochs=50, validation_split=0.2)
当我尝试拟合模型时出现以下错误：
UnboundLocalError Traceback (most recent call last)
<ipython-input-65-6a0b99b56337> in <module>()
1 early_stopping_cb=keras.callbacks.EarlyStopping(patience=3, verbose=1,restore_best_weights=True)
----> 2 vgg16_1.fit(train_img, train_labels, epochs=50, validation_split=0.2, callbacks=[early_stopping_cb])
1 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.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, **kwargs)
857 logs = tmp_logs # No error, now safe to assign to logs.
858 callbacks.on_train_batch_end(step, logs)
--> 859 epoch_logs = copy.copy(logs)
860
861 # Run validation.
UnboundLocalError: local variable 'logs' referenced before assignment
我认为这可能是由于训练集形状有问题，但如果我改用 train_img[0]，其形状为 (60000,32,32,3)，那么我得到而是以下错误：
ValueError Traceback (most recent call last)
<ipython-input-66-2b893ccd9ac9> in <module>()
1 early_stopping_cb=keras.callbacks.EarlyStopping(patience=3, verbose=1,restore_best_weights=True)
----> 2 vgg16_1.fit(train_img[0], train_labels, epochs=50, validation_split=0.2, callbacks=[early_stopping_cb])
10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
64 def _method_wrapper(self, *args, **kwargs):
65 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
---> 66 return method(self, *args, **kwargs)
67
68 # Running inside `run_distribute_coordinator` already.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.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, **kwargs)
849 batch_size=batch_size):
850 callbacks.on_train_batch_begin(step)
--> 851 tmp_logs = train_function(iterator)
852 # Catch OutOfRangeError for Datasets of unknown size.
853 # This blocks until the batch has finished executing.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
578 xla_context.Exit()
579 else:
--> 580 result = self._call(*args, **kwds)
581
582 if tracing_count == self._get_tracing_count():
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
625 # This is the first call of __call__, so we have to initialize.
626 initializers = []
--> 627 self._initialize(args, kwds, add_initializers_to=initializers)
628 finally:
629 # At this point we know that the initialization is complete (or less
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
504 self._concrete_stateful_fn = (
505 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 506 *args, **kwds))
507
508 def invalid_creator_scope(*unused_args, **unused_kwds):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2444 args, kwargs = None, None
2445 with self._lock:
-> 2446 graph_function, _, _ = self._maybe_define_function(args, kwargs)
2447 return graph_function
2448
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
2775
2776 self._function_cache.missed.add(call_context_key)
-> 2777 graph_function = self._create_graph_function(args, kwargs)
2778 self._function_cache.primary[cache_key] = graph_function
2779 return graph_function, args, kwargs
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
2665 arg_names=arg_names,
2666 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2667 capture_by_value=self._capture_by_value),
2668 self._function_attributes,
2669 # Tell the ConcreteFunction to clean up its graph once it goes out of
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_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)
979 _, original_func = tf_decorator.unwrap(python_func)
980
--> 981 func_outputs = python_func(*func_args, **func_kwargs)
982
983 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
439 # __wrapped__ allows AutoGraph to swap in a converted function. We give
440 # the function a weak reference to itself to avoid a reference cycle.
--> 441 return weak_wrapped_fn().__wrapped__(*args, **kwds)
442 weak_wrapped_fn = weakref.ref(wrapped_fn)
443
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
966 except Exception as e: # pylint:disable=broad-except
967 if hasattr(e, "ag_error_metadata"):
--> 968 raise e.ag_error_metadata.to_exception(e)
969 else:
970 raise
ValueError: in user code:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function *
outputs = self.distribute_strategy.run(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run **
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:533 train_step **
y, y_pred, sample_weight, regularization_losses=self.losses)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:143 __call__
losses = self.call(y_true, y_pred)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:246 call
return self.fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1527 categorical_crossentropy
return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4561 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (32, 1) and (32, 10) are incompatible
这些错误的来源以及我做错了什么的任何线索？感觉我可能错过了一些明显的东西，但作为 Keras 的新手，我无法理解它是什么。非常感谢帮助。
扩展dims需要注释两行如下。发生的事情是它将 train_img 的形状更新为 (1,60000,32,32,3) 并且 model.fit 抱怨您正在使用单个图像进行训练。
#train_img = tf.expand_dims(train_img, axis=0)
#test_img = tf.expand_dims(test_img, axis=0)
我更新了您的代码并分享了 Here. You need to update the architecture to improve it for better accuracy. Follow transfer learning approach mentioned here 并更新了您的代码以提高准确性。谢谢！
似乎问题是我有一个大小为 10 的密集输出层，而标签的大小为 1。解决方案是使用稀疏分类交叉熵损失函数而不是简单分类损失函数。