I just completed the implementation of A Guide to TF Layers: Building a Convolutional Neural Network for the MNIST data set. The training model successfully ran and gave accuracy of 97.3%.
However, the tutorial does not mention how to use this new trained model to supply own images and see the predictions. Does anyone know how to use the output of the training model to make predictions? I see in the tmp/mnist_convnet_model$ folder, there are some output files like .pbtxt , meta files and index files. But I can't find instructions to use them for making predictions on my own images.
y_pred = tf.nn.softmax(your_final_layer)
y_pred_cls = tf.argmax(y_pred, dimension=1)
and for prediction
feed_dict = {x: [your_image]}
classification = tf.run(y_pred_cls, feed_dict)
print classification
This applies to just about any model you create
Related
I want to extract features using a pretrained CNN model(ResNet50, VGG, etc) and use the features with a CTC loss function.
I want to build it as a text recognition model.
Anyone on how can i achieve this ?
I'm not sure if you are looking to finetune the pretrained models or to use the models for feature extraction. To do the latter freeze the petrained model weights (there are several ways to do this in PyTorch, the simplest being calling .eval() on the model), and feed the logits from the last layer of the model to your new output head. See the PyTorch tutorial here for a more in depth guide.
I am learning Pytorch and trying to understand how the library works for semantic segmentation.
What I've understood so far is that we can use a pre-trained model in pytorch. I've found an article which was using this model in the .eval() mode but I have not been able to find any tutorial on using such a model for training on our own dataset. I have a very small dataset and I need transfer learning to get results. My goal is to only train the FC layers with my own data. How is that achievable in Pytorch without complicating the code with OOP or so many .py files. I have been having a hard time figuring out such repos in github as I am not the most proficient person when it comes to OOP. I have been using Keras for Deep Learning until recently and there everything is easy and straightforward. Do I have the same options in Pycharm?
I appreciate any guidance on this. I need to run a piece of code that does the semantic segmentation and I am really confused about many of the steps I need to take.
Assume you start with a pretrained model called model. All of this occurs before you pass the model any data.
You want to find the layers you want to train by looking at all of them and then indexing them using model.children(). Running this command will show you all of the blocks and layers.
list(model.children())
Suppose you have now found the layers that you want to finetune (your FC layers as you describe). If the layers you want to train are the last 5 you can grab all of the layers except for the last 5 in order to set their requires_grad params to False so they don't train when you run the training algorithm.
list(model.children())[-5:]
Remove those layers:
layer_list = list(model.children())[-5:]
Rebuild model using sequential:
model_small = nn.Sequential(*list(model.children())[:-5])
Set requires_grad params to False:
for param in model_small.parameters():
param.requires_grad = False
Now you have a model called model_small that has all of the layers except the layers you want to train. Now you can reattach the layers that your removed and they will intrinsically have the requires_grad param set to True. Now when you train the model it will only update the weights on those layers.
model_small.avgpool_1 = nn.AdaptiveAvgPool2d()
model_small.lin1 = nn.Linear()
model_small.logits = nn.Linear()
model_small.softmax = nn.Softmax()
model = model_small.to(device)
# define the model
model = MaskRCNN(mode='training', model_dir='./', config=config)
# load weights (mscoco) and exclude the output layers
model.load_weights('mask_rcnn_coco.h5', by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox", "mrcnn_mask"])
# train weights (output layers or 'heads')
model.train(train_set, test_set, learning_rate=config.LEARNING_RATE, epochs=2, layers='heads')
I have certain medical images containing fibroids.
I wish to apply instance segmentation or object detection.
I may have to use mask Rcnn for instance segmentation and object detection. Is it possible to design the network from scratch instead of using transfer learning?
What I mean here is random initialization of weights for my data, instead of using weights derived from imagenet data or coco data.
From the command line,instead of training a model starting from pre-trained COCO weights like this
python my_model.py train --dataset=/path/dataset --weights=coco
execute the following line.
python my_model.py train --dataset=/path/dataset
And to start training from the first layer execute the following code.
model.train(dataset_train, dataset_val,learning_rate=config.LEARNING_RATE,epochs=10, layers='all')
Can't you just run the training without doing the model.load_weights() line? It seems to be running fine for me when I do that. I assume that runs it with randomized initial weights. It didn't result in quite as good results as starting with coco does, but I'm sure that's expected behavior for some datasets.
I built a LSTM model for text classification using Keras. Now I have new data to be trained. instead of appending to the original data and retrain the model, I thought of training the data using the model weights. i.e. making the weights to get trained with the new data.
However, irrespective of the volume i train, the model is not predicting the correct classification (even if i give the same sentence for prediction). What could be the reason?
Kindly help me.
Are you using the following to save the trained model?
model.save('model.h5')
model.save_weights('model_weights.h5')
And the following to load it?
from keras.models import load_model
model = load_model('model.h5') # Load the architecture
model = model.load_weights('model_weights.h5') # Set the weights
# train on new data
model.compile...
model.fit...
The model loaded is the exact same as the model being saved here. If you are doing this, then there must be something different in the data (in comparison with what it is trained on).
I'm trying to modify Keras Siamese Network example to get image feature.
The problem is, how can I get image features? The output of last layer is only a number. What should I do to get the feature before euclidean_distance?
You can try to first train the model on the entire dataset and save it.
Load the model back again, now set the output layers to be processed_a and processed_b
Now call the model.predict() function on the entire dataset once again and you'll have the features for each image in the dataset.
Have a look at this
Hope this helps!
To get the embeddings from the Keras siamese network MNIST example after training:
model_a = Model(inputs=model.input, outputs=processed_a)
model_a.predict([tr_pairs[:, 0], tr_pairs[:, 1]])
I did it as follows (reference from my github post):
My trained siamese model looked like this:
siamese_model.summary()
Note that my newly redefined model is basically the same as the one highlighted in yellow
I then redefined my model which I wanted to use for extracting embeddings (It should be the same model you defined except now it will not have those multiple inputs like siamese) which looked like this:
siamese_embeddings_model = build_siamese_model(input_shape)
siamese_embeddings_model .summary()
Then I just extracted the weights from my trained siamese model and set them into my new model
embeddings_weights = siamese_model.layers[-3].get_weights()
siamese_embeddings_model.set_weights(embeddings_weights )
Then you can supply the new Image to extract the embeddings from the new model
vector = siamese.predict(image)
len(vector[0]) it will print 150 because of my fine dense layer (which are the output vector)