Reload weights into fc layer after converting to csr_matrix - deep-learning

I am trying to store weights in a the fc layers in a compressed sparse row format. When I retrieve the weights and convert them to CSR matrix format, its size in memory reduces drastically but when I load it back into caffe my model size remains the same. Basically this is what I'm doing:
temp2 = net.params['ip1'][0].data.shape
sparse_csr1 = sparse.scr_matrix(temp2, shape)
net.params['ip1'][0].data[...] = sparse_csr1
net.save('compressed.caffemodel')
Any suggestions will be appreciated.

Caffe does not support sparse matices, therefore you cannot benefit from sparse compression of weights.

Looks like these repos does exactly this for both inner-product and conv layers:
https://github.com/IntelLabs/SkimCaffe
https://github.com/valeriifilevsc/caffe

Related

How can you increase the accuracy of ResNet50?

I'm using Resnet50 model to classify images into two classes: normal cells and cancer cells.
so I want to to increase the accuracy but i don't know what to modify.
# we are using resnet50 for transfer learnin here. So we have imported it
from tensorflow.keras.applications import resnet50
# initializing model with weights='imagenet'i.e. we are carring its original weights
model_name='resnet50'
base_model=resnet50.ResNet50(include_top=False, weights="imagenet",input_shape=img_shape, pooling='max')
last_layer=base_model.output # we are taking last layer of the model
# Add flatten layer: we are extending Neural Network by adding flattn layer
flatten=layers.Flatten()(last_layer)
# Add dense layer
dense1=layers.Dense(100,activation='relu')(flatten)
# Add dense layer to the final output layer
output_layer=layers.Dense(class_count,activation='softmax')(flatten)
# Creating modle with input and output layer
model=Model(inputs=base_model.inputs,outputs=output_layer)
model.compile(Adamax(learning_rate=.001), loss='categorical_crossentropy', metrics=['accuracy'])
There were 48 errors in 534 test cases Model accuracy= 91.01 %
Also what do you think about the results of the graph?
this is the classification report
i got good results but is there a possibility to increase accuracy more than that?
This is a broad question as there are many ways one can attempt to generally improve the network's accuracy. some of which may be
Increase the dimension of the layers that are learned in transfer learning (make sure not to overfit)
Use transfer learning with Convolution layers and not MLP
let the optimization algorithm choose the learning rate on its own
Play with additional augmentations to the dataset
and the list goes on.
Also, if possible, I would suggest comparing your results to other publicly available benchmarks - by doing so you might understand the upper bounds of the accuracies better

Should we train the original data point when we do data augmentation?

I am confused about the definition of data augmentation. Should we train the original data points and the transformed ones or just the transformed? If we train both, then we will increase the size of the dataset while the second approach won't.
I got this question when using the function RandomResizedCrop.
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
If we resize and crop some of the dataset randomly, we don't actually increase the size of the dataset for data augmentation. Is that correct? Or data augmentation just requires the change/modification of original dataset rather than increase the size of it?
Thanks.
By definition, or at least the influential paper AlexNet from 2012 that popularized data augmentation in computer vision, increases the size of the training set. Hence the word augmentation. Go ahead and have a look at Section 4.1 from the AlexNet paper. But, here is the gist of it, which I'm quoting from the paper:
The easiest and most common method to reduce overfitting on image data is to artificially enlarge the dataset using label-preserving transformations. The first form of data augmentation consists of generating image translations and horizontal reflections. We do this by extracting random 224 × 224 patches (and their horizontal reflections) from the 256×256 images and training our network on these extracted patches. This increases the size of our training set by a factor of 2048, though the resulting training examples are, of course, highly interdependent.
As for the specific implementation, it depends on your use case and most importantly the size of your training data. If you're short in quantity in the latter case, you should consider training on original and transformed images, by sufficiently taking care to preserve the labels.
transform.compose is just as preprocessing an image ,convert one form to particular suiatable form
On apply transformation on single image means changing it pixel value and it does not increases dataset size
for more dataset you have to perform operation such below:
final_train_data = []
final_target_train = []
for i in tqdm(range(train_x.shape[0])):
final_train_data.append(train_x[i])
final_train_data.append(rotate(train_x[i], angle=45, mode = 'wrap'))
final_train_data.append(np.fliplr(train_x[i]))
final_train_data.append(np.flipud(train_x[i]))
final_train_data.append(random_noise(train_x[i],var=0.2**2))
for j in range(5):
final_target_train.append(train_y[i])
for more detail pytorch

One Hot Encoding dimension - Model Compexity

I will explain my problem:
I have around 50.000 samples, each of one described by a list of codes representing "events"
The number of unique codes are around 800.
The max number of codes that a sample could have is around 600.
I want to represent each sample using one-hot encoding. The representation should be, if we consider the operation of padding for those samples that has fewer codes, a 800x600 matrix.
Giving this new representation as input of a network, means to flatten each matrix to a vector of size 800x600 (460.000 values).
At the end the dataset should consist in 50.000 vectors of size 460.000 .
Now, I have two considerations:
How is it possible to handle a dataset of that size?(I tried data generator to obtain the representation on-the-fly but they are really slow).
Having a vector of size 460.000 as input for each sample, means that the complexity of my model( number of parameters to learn ) is extremely high ( around 15.000.000 in my case ) and, so, I need an huge dataset to train the model properly. Doesn't it?
Why do not you use the conventional model used in NLP?
These events can be translated as you say by embedding matrix.
Then you can represent the chains of events using LSTM (or GRU or RNN o Bilateral LSTM), the difference of using LSTM instead of a conventional network is that you use the same module repeated by N times.
So your input really is not 460,000, but internally an event A indirectly helps you learn about an event B. That's because the LSTM has a module that repeats itself for each event in the chain.
You have an example here:
https://www.kaggle.com/ngyptr/lstm-sentiment-analysis-keras
Broadly speaking what I would do would be the following (in Keras pseudo-code):
Detect the number of total events. I generate a unique list.
unique_events = list (set ([event_0, ..., event_n]))
You can perform the translation of a sequence with:
seq_events_idx = map (unique_events.index, seq_events)
Add the necessary pad to each sequence:
sequences_pad = pad_sequences (sequences, max_seq)
Then you can directly use an embedding to carry out the transfer of the event to an associated vector of the dimension that you consider.
input_ = Input (shape = (max_seq,), dtype = 'int32')
embedding = Embedding (len(unique_events),
                    dimensions,
                    input_length = max_seq,
                    trainable = True) (input_)
Then you define the architecture of your LSTM (For example):
lstm = LSTM (128, input_shape = (max_seq, dimensions), dropout = 0.2, recurrent_dropout = 0.2, return_sequences = True) (embedding)
Add the dense and the result you want:
out = Dense (10, activation = 'softmax') (lstm)
I think that this type of model can help you and give better results.

How to reshape a pytorch matrix without mixing elements of items in a batch

In my Neural network model, I represent an 8 word-sentence with a 8x256 dimensional embedding matrix. I want to give it to a LSTM as a input where LSTM takes a single word embedding at a time as input and process it. According to pytorch documentation, the input should be in the shape of (seq_len, batch, input_size). What is the correct way to convert my input to desired shape ? I don't want to mixup the numbers by mistake. I am quite new in PyTorch and row-major calculations, therefore I wanted to ask it here. I do it as follows, is it correct ?
x = torch.rand(8,256)
lstm_input = torch.reshape(x,(8,1,256))
Your solution is correct: you added a Singleton dimension for the "batch" dimension, leaving x to be with temporal dimension 8 and input dimension 256.
Since you are new to pytorch, here are a few equivalent ways of doing the same thing:
x = x[:, None, :]
Putting None in the dim=1 indicates to pytorch to add a singelton dimension.
Another way is to use view:
x = x.view(8, 1, 256)

How to modify the Imagenet Caffe Model?

I would like to modify the ImageNet caffe model as described bellow:
As the input channel number for temporal nets is different from that
of spatial nets (20 vs. 3), we average the ImageNet model filters of
first layer across the channel, and then copy the average results 20
times as the initialization of temporal nets.
My question is how can I achive the above results? How can I open the caffe model to be able to do those changes to it?
I read the net surgery tutorial but it doesn't cover the procedure needed.
Thank you for your assistance!
AMayer
The Net Surgery tutorial should give you the basics you need to cover this. But let me explain the steps you need to do in more detail:
Prepare the .prototxt network architectures: You need two files: the existing ImageNet .prototxt file, and your new temporal network architecture. You should make all layers except the first convolutional layers identical in both networks, including the names of the layers. That way, you can use the ImageNet .caffemodel file to initialize the weights automatically.
As the first conv layer has a different size, you have to give it a different name in your .prototxt file than it has in the ImageNet file. Otherwise, Caffe will try to initialize this layer with the existing weights too, which will fail as they have different shapes. (This is what happens in the edit to your question.) Just name it e.g. conv1b and change all references to that layer accordingly.
Load the ImageNet network for testing, so you can extract the parameters from the model file:
net = caffe.Net('imagenet.prototxt', 'imagenet.caffemodel', caffe.TEST)
Extract the weights from this loaded model.
conv_1_weights = old_net.params['conv1'][0].data
conv_1_biases = old_net.params['conv1'][1].data
Average the weights across the channels:
conv_av_weights = np.mean(conv_1_weights, axis=1, keepdims=True)
Load your new network together with the old .caffemodel file, as all layers except for the first layer directly use the weights from ImageNet:
new_net = caffe.Net('new_network.prototxt', 'imagenet.caffemodel', caffe.TEST)
Assign your calculated average weights to the new network
new_net.params['conv1b'][0].data[...] = conv_av_weights
new_net.params['conv1b'][1].data[...] = conv_1_biases
Save your weights to a new .caffemodel file:
new_net.save('new_weights.caffemodel')