我对基于流行的皮肤癌图像数据集开发的模型存在困境。我必须指出我想要一些指导 -
一个。
原始数据集包含超过 10K 图像，其中近 7000 张图像属于七个类别之一。我创建了 4948 个随机图像的子集，我使用它运行了一个函数将图像转换为列表列表 - 第一个列表包含图像，后者包含类以及关闭任何属于类的图像（5 - +6800K 图像的类）。思考过程是规范跨类的分布。
使用输出（6 个神经元而不是 7 个神经元的密集层）重新运行原始模型 - 检索错误。
我是否错过了向模型“指示”只有六个可能的类的步骤？该模型仅在输出层有七个神经元时运行。
错误：
Train on 1245 samples, validate on 312 samples
Epoch 1/30
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-138-8a3b40a69e37> in <module>
25 metrics=["accuracy"])
26
---> 27 model.fit(X_train, y_train, batch_size=32, epochs=30, validation_split=0.2)
/anaconda3/lib/python3.7/site-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_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
778 validation_steps=validation_steps,
779 validation_freq=validation_freq,
--> 780 steps_name='steps_per_epoch')
781
782 def evaluate(self,
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_arrays.py in model_iteration(model, inputs, targets, sample_weights, batch_size, epochs, verbose, callbacks, val_inputs, val_targets, val_sample_weights, shuffle, initial_epoch, steps_per_epoch, validation_steps, validation_freq, mode, validation_in_fit, prepared_feed_values_from_dataset, steps_name, **kwargs)
361
362 # Get outputs.
--> 363 batch_outs = f(ins_batch)
364 if not isinstance(batch_outs, list):
365 batch_outs = [batch_outs]
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/backend.py in __call__(self, inputs)
3290
3291 fetched = self._callable_fn(*array_vals,
-> 3292 run_metadata=self.run_metadata)
3293 self._call_fetch_callbacks(fetched[-len(self._fetches):])
3294 output_structure = nest.pack_sequence_as(
/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)
1456 ret = tf_session.TF_SessionRunCallable(self._session._session,
1457 self._handle, args,
-> 1458 run_metadata_ptr)
1459 if run_metadata:
1460 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
InvalidArgumentError: Received a label value of 6 which is outside the valid range of [0, 6). Label values: 1 1 2 4 2 1 2 1 2 1 2 2 4 2 2 1 3 1 4 6 0 2 4 2 0 4 2 4 4 0 2 4
[[{{node loss_15/activation_63_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits}}]]
B.
我正在尝试添加数据增强，因为考虑到类的数量和跨类图像的稀疏性，数据集相对较小。一旦我尝试运行生成器，我就会收到下面的错误消息，表明validation_data元组中的一个变量有问题。我无法理解问题所在。
测试集的示例值如下所示：
[[[[0.41568627]
[0.4 ]
[0.43137255]
...
[0.54509804]
[0.54901961]
[0.54509804]]
[[0.42352941]
[0.43137255]
[0.43921569]
...
[0.56078431]
[0.54117647]
[0.55294118]]
[[0.41960784]
[0.41960784]
[0.45490196]
...
[0.51764706]
[0.57254902]
[0.50588235]]
...
[[0.30980392]
[0.36470588]
[0.36470588]
...
[0.47058824]
[0.44705882]
[0.41960784]]
[[0.29803922]
[0.31764706]
[0.34509804]
...
[0.45098039]
[0.43921569]
[0.4 ]]
[[0.25882353]
[0.30196078]
[0.31764706]
...
[0.45490196]
[0.42745098]
[0.36078431]]]
[[[0.60784314]
[0.59215686]
[0.56862745]
...
[0.59607843]
[0.63921569]
[0.63529412]]
[[0.6627451 ]
[0.63137255]
[0.62352941]
...
[0.67843137]
[0.60784314]
[0.63529412]]
[[0.62745098]
[0.65098039]
[0.6 ]
...
[0.61568627]
[0.63921569]
[0.67058824]]
...
[[0.62352941]
[0.6 ]
[0.59607843]
...
[0.6627451 ]
[0.71372549]
[0.6745098 ]]
[[0.61568627]
[0.58431373]
[0.61568627]
...
[0.67058824]
[0.65882353]
[0.68235294]]
[[0.61176471]
[0.60392157]
[0.61960784]
...
[0.65490196]
[0.6627451 ]
[0.66666667]]]]
[2, 1, 4, 4, 2]
错误：
Epoch 1/10
1/155 [..............................] - ETA: 11s - loss: 1.7916 - acc: 0.3000
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-139-8f19a958861f> in <module>
12 history = model.fit_generator(trainAug.flow(X_train, y_train, batch_size=batch_size)
13 ,epochs = 10, validation_data = (X_test, y_test),
---> 14 steps_per_epoch= X_train.shape[0]// batch_size
15 )
16 #epochs = epochs, validation_data = (X_test, y_test),
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1431 shuffle=shuffle,
1432 initial_epoch=initial_epoch,
-> 1433 steps_name='steps_per_epoch')
1434
1435 def evaluate_generator(self,
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_generator.py in model_iteration(model, data, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch, mode, batch_size, steps_name, **kwargs)
262
263 is_deferred = not model._is_compiled
--> 264 batch_outs = batch_function(*batch_data)
265 if not isinstance(batch_outs, list):
266 batch_outs = [batch_outs]
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics)
1173 self._update_sample_weight_modes(sample_weights=sample_weights)
1174 self._make_train_function()
-> 1175 outputs = self.train_function(ins) # pylint: disable=not-callable
1176
1177 if reset_metrics:
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/backend.py in __call__(self, inputs)
3290
3291 fetched = self._callable_fn(*array_vals,
-> 3292 run_metadata=self.run_metadata)
3293 self._call_fetch_callbacks(fetched[-len(self._fetches):])
3294 output_structure = nest.pack_sequence_as(
/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)
1456 ret = tf_session.TF_SessionRunCallable(self._session._session,
1457 self._handle, args,
-> 1458 run_metadata_ptr)
1459 if run_metadata:
1460 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
InvalidArgumentError: Received a label value of 6 which is outside the valid range of [0, 6). Label values: 0 1 6 4 2 4 2 0 1 2
[[{{node loss_15/activation_63_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits}}]]
代码：
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import sys
import os
import cv2
DATA_DIR = "/Users/namefolder/PycharmProjects/skin-cancer/HAM10000_images_part_1"
metadata = pd.read_csv(os.path.join(DATA_DIR, 'HAM10000_metadata.csv'))
lesion_type_dict = {'nv': 'Melanocytic nevi',
'mel': 'Melanoma',
'bkl': 'Benign keratosis-like lesions ',
'bcc': 'Basal cell carcinoma',
'akiec': 'Actinic keratoses',
'vasc': 'Vascular lesions',
'df': 'Dermatofibroma'}
metadata['cell_type'] = metadata['dx'].map(lesion_type_dict.get)
metadata['dx_code'] = pd.Categorical(metadata['dx']).codes
# save array of image-id and diagnosis-type (categorical)
metadata = metadata[['image_id', 'dx', 'dx_type', 'dx_code']]
training_data = []
IMG_SIZE=50
# preparing training data
def creating_training_data(path):
for img in os.listdir(path):
try:
img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)
new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
for index, row in metadata.iterrows():
if (img == row['image_id']+'.jpg') & (row['dx_code'] != 5):
try:
training_data.append([new_array, row['dx_code']])
except Exception as ee:
pass
except Exception as e:
pass
return training_data
training_data = creating_training_data(DATA_DIR)
import random
random.shuffle(training_data)
# Splitting data into X features and Y label
X_train = []
y_train = []
for features, label in training_data:
X_train.append(features)
y_train.append(label)
# Reshaping of the data - required by Tensorflow and Keras (*necessary step of deep-learning using these repos)
X_train = np.array(X_train).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
# Normalize data - to reduce processing requirements
X_train = X_train/255.0
# model configuration
model = Sequential()
model.add(Conv2D(64, (3,3), input_shape = X_train.shape[1:]))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3,3)))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Dense(6))
model.add(Activation("softmax"))
model.compile(loss="mean_squared_error",
optimizer="adam",
metrics=["accuracy"])
# Data Augmentation - Repo enabler
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ReduceLROnPlateau
# initialize the training training data augmentation object
trainAug = ImageDataGenerator(
rescale=1 / 255.0,
rotation_range=20,
zoom_range=0.05,
width_shift_range=0.05,
height_shift_range=0.05,
shear_range=0.05,
horizontal_flip=True,
fill_mode="nearest")
# initialize the validation (and testing) data augmentation object
valAug = ImageDataGenerator(rescale=1 / 255.0)
#set a leraning rate annealer
learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc',
patience=3,
verbose=1,
factor=0.5,
min_lr=0.00001)
#Augmented Images model development
)
trainAug.fit(X_train)
#Fit the model
epochs = 10
batch_size= 10
history = model.fit_generator(trainAug.flow(X_train, y_train, batch_size=batch_size),epochs = 10, validation_data = (X_test, y_test), steps_per_epoch= X_train.shape[0]// batch_size)