【发布时间】：2020-04-16 06:33:08
【问题描述】：
是否可以训练具有大量类别的图像分类器网络？ （比如 300k 类），每个类至少有 10 张图像在训练/测试/验证之间拆分（即 >30 万张 250x250x3 图像）。
我尝试使用 ResNet50 模型训练数据集并将批量大小降低到 1，但仍然遇到 OOM 问题（2080 Ti）。我发现 OOM 是由太多参数引起的，因此我试图在一个非常基本的 10 层模型上训练网络，批量大小为 1。它可以运行，但是速度/准确度是不出所料的糟糕透顶。
无论如何我可以将训练集分成更小的类，这样：
1st .h5 = 1 ~ 20,000 类
2nd .h5 = 20,001 ~ 40,000 类
3rd .h5 = 40,001 ~ 60,000 类等。
然后合并成一个单独的 h5 文件，可以加载该文件以识别所有 300k 不同的类？
根据 ASHISH 的建议进行编辑：
我（我认为）成功地将 2 个模型合并为一个，但是合并后的模型的层数增加了一倍……
源代码：
model1 = load_model('001.h5')
model2 = load_model('002.h5')
for layer in model1.layers:
layer._name = layer._name + "_1" # avoid duplicate layer names, which would otherwise throw an error
layer.trainable = False
for layer in model2.layers:
layer._name = layer._name + "_2"
layer.trainable = False
x1 = model1.layers[-1].output
classes = x1.shape[1]
x1 = Dense(classes, activation='relu', name='out1')(x1)
x2 = model2.layers[-1].output
x2 = Dense(x2.shape[1], activation='relu', name='out2')(x2)
classes += x2.shape[1]
x = concatenate([x1, x2])
output_layer = Dense(classes, activation='softmax', name='combined_layer')(x)
new_model = Model(inputs=[model1.inputs, model2.inputs], outputs=output_layer)
new_model.summary()
new_model.save('new_model.h5', overwrite=True)
生成的模型如下所示：
Model: "model"
_________________________________________________________________________
Layer (type) Output Shape Param # Connected to
=========================================================================
input_1_1 (InputLayer) [(None, 224, 224, 3) 0
_________________________________________________________________________
input_1_2 (InputLayer) [(None, 224, 224, 3) 0
_________________________________________________________________________
conv1_pad_1 (ZeroPadding2D) (None, 230, 230, 3) 0 input_1_1[0][0]
_________________________________________________________________________
conv1_pad_2 (ZeroPadding2D) (None, 230, 230, 3) 0 input_1_2[0][0]
_________________________________________________________________________
conv1_conv_1 (Conv2D) (None, 112, 112, 64) 9472 conv1_pad_1[0][0]
_________________________________________________________________________
conv1_conv_2 (Conv2D) (None, 112, 112, 64) 9472 conv1_pad_2[0][0]
...
...
conv5_block3_out_1 (Activation) (None, 7, 7, 2048) 0 conv5_block3_add_1[0][0]
_________________________________________________________________________
conv5_block3_out_2 (Activation) (None, 7, 7, 2048) 0 conv5_block3_add_2[0][0]
_________________________________________________________________________
avg_pool_1 (GlobalAveragePoolin (None, 2048) 0 conv5_block3_out_1[0][0]
_________________________________________________________________________
avg_pool_2 (GlobalAveragePoolin (None, 2048) 0 conv5_block3_out_2[0][0]
_________________________________________________________________________
probs_1 (Dense) (None, 953) 1952697 avg_pool_1[0][0]
_________________________________________________________________________
probs_2 (Dense) (None, 3891) 7972659 avg_pool_2[0][0]
_________________________________________________________________________
out1 (Dense) (None, 953) 909162 probs_1[0][0]
_________________________________________________________________________
out2 (Dense) (None, 3891) 15143772 probs_2[0][0]
_________________________________________________________________________
concatenate (Concatenate) (None, 4844) 0 out1[0][0]
out2[0][0]
_________________________________________________________________________
combined_layer (Dense) (None, 4844) 23469180 concatenate[0][0]
=========================================================================
Total params: 96,622,894
Trainable params: 39,522,114
Non-trainable params: 57,100,780
如您所见，由于 Model(inputs=[input1, input2])，所有层都翻了一番。当我想使用这个模型来预测图像时，这会给我带来问题。无论如何我可以在不将所有先前层加倍而只添加尾随密集层的情况下做到这一点吗？以这种速度，我会比以前更快地承受参数数量的重载......
【问题讨论】：
标签： python tensorflow machine-learning deep-learning resnet