I trained GoogLeNet model from scratch. But it didn't give me the promising results.
As an alternative, I would like to do fine tuning of GoogLeNet model on my dataset. Does anyone know what are the steps should I follow?
When finetuning a model, you can train ALL model's weights or choose to fix some weights (usually filters of the lower/deeper layers) and train only the weights of the top-most layers. This choice is up to you and it ususally depends on the amount of training data available (the more examples you have the more weights you can afford to finetune).
3. How extensive a finetuning you want? When finetuning a model, you can train ALL model's weights or choose to fix some weights (usually filters of the lower/deeper layers) and train only the weights of the top-most layers.
Fine-tuning is one of the most common way to solve problems using AI and Deep learning. That’s why Keras provides us weights without the top along with complete imagenet weights. This is how we call the above code for VGG16 model.
In this section, we will introduce a common technique in transfer learning: fine-tuning. As shown in Fig. 14.2.1 , fine-tuning consists of the following four steps: Pretrain a neural network model, i.e., the source model, on a source dataset (e.g., the ImageNet dataset). Create a new neural network model, i.e., the target model.
Assuming you are trying to do image classification. These should be the steps for finetuning a model:
The original classification layer "loss3/classifier"
outputs predictions for 1000 classes (it's mum_output
is set to 1000). You'll need to replace it with a new layer with appropriate num_output
. Replacing the classification layer:
num_output
to the right number of output classes you are trying to predict."loss1/classifier"
, "loss2/classifier"
and "loss3/classifier"
.You need to make a new training dataset with the new labels you want to fine tune to. See, for example, this post on how to make an lmdb dataset.
When finetuning a model, you can train ALL model's weights or choose to fix some weights (usually filters of the lower/deeper layers) and train only the weights of the top-most layers. This choice is up to you and it ususally depends on the amount of training data available (the more examples you have the more weights you can afford to finetune).
Each layer (that holds trainable parameters) has param { lr_mult: XX }
. This coefficient determines how susceptible these weights to SGD updates. Setting param { lr_mult: 0 }
means you FIX the weights of this layer and they will not be changed during the training process.
Edit your train_val.prototxt
accordingly.
Run caffe train
but supply it with caffemodel weights as an initial weights:
~$ $CAFFE_ROOT/build/tools/caffe train -solver /path/to/solver.ptototxt -weights /path/to/orig_googlenet_weights.caffemodel
Fine-tuning is a very useful trick to achieve a promising accuracy compared to past manual feature. @Shai already posted a good tutorial for fine-tuning the Googlenet using Caffe, so I just want to give some recommends and tricks for fine-tuning for general cases.
In most of time, we face a task classification problem that new dataset (e.g. Oxford 102 flower dataset or Cat&Dog) has following four common situations CS231n:
In practice, most of time we do not have enough data to train the network from scratch, but may be enough for pre-trained model. Whatever which cases I mentions above only thing we must care about is that do we have enough data to train the CNN?
If yes, we can train the CNN from scratch. However, in practice it is still beneficial to initialize the weight from pre-trained model.
If no, we need to check whether data is very different from original datasets? If it is very similar, we can just fine-tune the fully connected neural network or fine-tune with SVM. However, If it is very different from original dataset, we may need to fine-tune the convolutional neural network to improve the generalization.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With