我有一个基于ResNet. 我正在使用 25k 类似类型的图像。我的图像有文字和一些图表。当我使用欧几里得距离 + 二元损失时，我得到了 95% 的准确度，Inception但与 Triplet Hard/Semi Hard Loss 相同，我得到了损失，准确nan度几乎为 0。请告诉我代码结构是否有问题。
import tensorflow_addons as tfa
from tensorflow.keras.applications.resnet50 import preprocess_input as res50_pre, ResNet50
shape = (224,224,3)
lr = 0.001
loss = tfa.losses.TripletSemiHardLoss()
epochs = 50
batch_size = 128 #254 gives 'log' referenced before assignment error
datagen = ImageDataGenerator(preprocessing_function=res50_pre,validation_split=0.2)
train_data = datagen.flow_from_dataframe(df,x_col='path',y_col='label',class_mode='sparse',target_size=(224,224),
batch_size=batch_size,subset='training',seed=SEED)
val_data = datagen.flow_from_dataframe(df,x_col='path',y_col='label',class_mode='sparse',target_size=(224,224),
batch_size=batch_size,subset='validation',seed=SEED)
base_model = ResNet50(weights='imagenet',input_shape=shape,include_top=False,pooling='avg')
base_model.trainable = True
inputs = keras.Input(shape=shape)
x = base_model(inputs,training=True)
outputs = keras.layers.Lambda(lambda x: tf.math.l2_normalize(x, axis=1))(x) # L2 normalize embeddings
model = keras.Model(inputs, outputs)
for layer in model.layers: # set all the parameters trainable
layer.trainable = True
model.compile(optimizer=tf.keras.optimizers.Adam(lr),loss=loss,metrics=['accuracy'])
history = model.fit(train_data,epochs=epochs,steps_per_epoch=len(train_data)//batch_size,validation_data=val_data,verbose=2)
我group的值像 1,2,3 [不按顺序和一些缺失] 代表相同类型的数据。我Sparse在将值转换为str(1), str(3)等后使用。
我的DataFrame样子是这样的：
