python - 用于手语识别的 resnet 模型的准确性没有提高

Question

这是数据集：https ://www.kaggle.com/grassknoted/asl-alphabet

    def res_block(X, filter, stage):
    
      # Convolutional_block
      X_copy = X
    
      f1 , f2, f3 = filter
    
      # Main Path
      X = Conv2D(f1, (1,1),strides = (1,1), name ='res_'+str(stage)+'_conv_a', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = MaxPooling2D((2,2), padding='same')(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_conv_a')(X)
      X = Activation('relu')(X) 
    
      X = Conv2D(f2, kernel_size = (3,3), strides =(1,1), padding = 'same', name ='res_'+str(stage)+'_conv_b', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_conv_b')(X)
      X = Activation('relu')(X) 
    
      X = Conv2D(f3, kernel_size = (1,1), strides =(1,1),name ='res_'+str(stage)+'_conv_c', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_conv_c')(X)
    
    
      # Short path
      X_copy = Conv2D(f3, kernel_size = (1,1), strides =(1,1),name ='res_'+str(stage)+'_conv_copy', kernel_initializer= glorot_uniform(seed = 0))(X_copy)
      X_copy = MaxPooling2D((2,2), padding='same')(X_copy)
      X_copy = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_conv_copy')(X_copy)
    
      # ADD
      X = Add()([X,X_copy])
      X = Activation('relu')(X)
    
      # Identity Block 1
      X_copy = X
    
    
      # Main Path
      X = Conv2D(f1, (1,1),strides = (1,1), name ='res_'+str(stage)+'_identity_1_a', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_identity_1_a')(X)
      X = Activation('relu')(X) 
    
      X = Conv2D(f2, kernel_size = (3,3), strides =(1,1), padding = 'same', name ='res_'+str(stage)+'_identity_1_b', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_identity_1_b')(X)
      X = Activation('relu')(X) 
    
      X = Conv2D(f3, kernel_size = (1,1), strides =(1,1),name ='res_'+str(stage)+'_identity_1_c', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_identity_1_c')(X)
    
      # ADD
      X = Add()([X,X_copy])
      X = Activation('relu')(X)
    
      # Identity Block 2
      X_copy = X
    
    
      # Main Path
      X = Conv2D(f1, (1,1),strides = (1,1), name ='res_'+str(stage)+'_identity_2_a', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_identity_2_a')(X)
      X = Activation('relu')(X) 
    
      X = Conv2D(f2, kernel_size = (3,3), strides =(1,1), padding = 'same', name ='res_'+str(stage)+'_identity_2_b', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_identity_2_b')(X)
      X = Activation('relu')(X) 
    
      X = Conv2D(f3, kernel_size = (1,1), strides =(1,1),name ='res_'+str(stage)+'_identity_2_c', kernel_initializer= glorot_uniform(seed = 0))(X)
      X = BatchNormalization(axis =3, name = 'bn_'+str(stage)+'_identity_2_c')(X)
    
      # ADD
      X = Add()([X,X_copy])
      X = Activation('relu')(X)
    
      return X

    
input_shape = (64, 64, 3)

X_input = Input(input_shape)

# Zero-padding
X = ZeroPadding2D((3,3))(X_input)

# 1 - stage
X = Conv2D(64, (7,7), strides= (2,2), name = 'conv1', kernel_initializer= glorot_uniform(seed = 0))(X)
X = BatchNormalization(axis =3, name = 'bn_conv1')(X)
X = Activation('relu')(X)
X = MaxPooling2D((3,3), strides= (2,2), padding='same')(X)

# 2 - stage
X = res_block(X, filter= [64,64,256], stage= 2)

# 3 - stage
X = res_block(X, filter= [128,128,512], stage= 3)

# 4 - stage
X = res_block(X, filter= [256,256,1024], stage= 4)

# 5 - stage
X = res_block(X, filter= [512,512,2048], stage= 5)


# Average Pooling
X = AveragePooling2D((2,2), name = 'Averagea_Pooling', padding='same')(X)

# Final layer
X = Flatten()(X)
X = Dense(4096, activation = 'relu')(X)
X = Dropout(0.2)(X)
X = Dense(2048, activation = 'relu')(X)
X = Dropout(0.1)(X)
X = Dense(29, activation = 'relu')(X)


my_model = Model( inputs= X_input, outputs = X)
my_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
my_model.summary()

history = my_model.fit(train_gen, epochs=10, validation_data=val_gen)

任何人都可以告诉技术如何提高此代码的准确性，一段时间后，损失到达 nan.will 应用诸如 earlystopping 或 modelcheckpoint 之类的回调有助于提高准确性。对于第一个 epoch，损失：8.6760 - 准确度：0.0637 - val_loss：7.9905 - val_accuracy：0.1003，对于第二个 epoch，损失变为 nan

标签： pythondeep-learningconv-neural-networkdata-science