I am using CLIP to determine the similarity between words and images.
For now I am using this repo and the following code and for classification it gives great results. I would need it for multi label classification in which I would need to use sigmoid instead of softmax.
import torch
from PIL import Image
import open_clip
model, _, preprocess = open_clip.create_model_and_transforms('ViT-B-32-quickgelu', pretrained='laion400m_e32')
tokenizer = open_clip.get_tokenizer('ViT-B-32-quickgelu')
image = preprocess(Image.open("CLIP.png")).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat"])
with torch.no_grad(), torch.cuda.amp.autocast():
image_features = model.encode_image(image)
text_features = model.encode_text(text)
image_features /= image_features.norm(dim=-1, keepdim=True)
text_features /= text_features.norm(dim=-1, keepdim=True)
text_probs = (100.0 * image_features # text_features.T).softmax(dim=-1)
print("Label probs:", text_probs) # prints: [[1., 0., 0.]]
Now I would like to use it for multi-class. For example if we have on the image dog and cat I would like to have high probabilities for both, so I would need to run it with sigmoid. But this gives me results all around 0.55 with the correct classes being 0.56 and the wrong 0.54, so something like this [0.54, 0.555, 0.56]. I would like to have something like [0.01, 0.98, 0.99] after using the sigmoid.
What am I doing wrong there? How can I get the results I want?
Related
I have a final project in my first degree and I want to build a Neural Network that gonna take the first 13 mfcc coeffs of a wav file and return who talked in the audio file from a banch of talkers.
I want you to notice that:
My audio files are text independent, therefore they have different length and words
I have trained the machine on about 35 audio files of 10 speaker ( the first speaker had about 15, the second 10, and the third and fourth about 5 each )
I defined :
X=mfcc(sound_voice)
Y=zero_array + 1 in the i_th position ( where i_th position is 0 for the first speaker, 1 for the second, 2 for the third... )
And than trained the machine, and than checked the output of the machine for some files...
So that’s what I did... but unfortunately it’s look like the results are completely random...
Can you help me understand why?
This is my code in python -
from sklearn.neural_network import MLPClassifier
import python_speech_features
import scipy.io.wavfile as wav
import numpy as np
from os import listdir
from os.path import isfile, join
from random import shuffle
import matplotlib.pyplot as plt
from tqdm import tqdm
winner = [] # this array count how much Bingo we had when we test the NN
for TestNum in tqdm(range(5)): # in every round we build NN with X,Y that out of them we check 50 after we build the NN
X = []
Y = []
onlyfiles = [f for f in listdir("FinalAudios/") if isfile(join("FinalAudios/", f))] # Files in dir
names = [] # names of the speakers
for file in onlyfiles: # for each wav sound
# UNESSECERY TO UNDERSTAND THE CODE
if " " not in file.split("_")[0]:
names.append(file.split("_")[0])
else:
names.append(file.split("_")[0].split(" ")[0])
names = list(dict.fromkeys(names)) # names of speakers
vector_names = [] # vector for each name
i = 0
vector_for_each_name = [0] * len(names)
for name in names:
vector_for_each_name[i] += 1
vector_names.append(np.array(vector_for_each_name))
vector_for_each_name[i] -= 1
i += 1
for f in onlyfiles:
if " " not in f.split("_")[0]:
f_speaker = f.split("_")[0]
else:
f_speaker = f.split("_")[0].split(" ")[0]
(rate, sig) = wav.read("FinalAudios/" + f) # read the file
try:
mfcc_feat = python_speech_features.mfcc(sig, rate, winlen=0.2, nfft=512) # mfcc coeffs
for index in range(len(mfcc_feat)): # adding each mfcc coeff to X, meaning if there is 50000 coeffs than
# X will be [first coeff, second .... 50000'th coeff] and Y will be [f_speaker_vector] * 50000
X.append(np.array(mfcc_feat[index]))
Y.append(np.array(vector_names[names.index(f_speaker)]))
except IndexError:
pass
Z = list(zip(X, Y))
shuffle(Z) # WE SHUFFLE X,Y TO PERFORM RANDOM ON THE TEST LEVEL
X, Y = zip(*Z)
X = list(X)
Y = list(Y)
X = np.asarray(X)
Y = np.asarray(Y)
Y_test = Y[:50] # CHOOSE 50 FOR TEST, OTHERS FOR TRAIN
X_test = X[:50]
X = X[50:]
Y = Y[50:]
clf = MLPClassifier(solver='lbfgs', alpha=1e-2, hidden_layer_sizes=(5, 3), random_state=2) # create the NN
clf.fit(X, Y) # Train it
for sample in range(len(X_test)): # add 1 to winner array if we correct and 0 if not, than in the end it plot it
if list(clf.predict([X[sample]])[0]) == list(Y_test[sample]):
winner.append(1)
else:
winner.append(0)
# plot winner
plot_x = []
plot_y = []
for i in range(1, len(winner)):
plot_y.append(sum(winner[0:i])*1.0/len(winner[0:i]))
plot_x.append(i)
plt.plot(plot_x, plot_y)
plt.xlabel('x - axis')
# naming the y axis
plt.ylabel('y - axis')
# giving a title to my graph
plt.title('My first graph!')
# function to show the plot
plt.show()
This is my zip file that contains the code and the audio file : https://ufile.io/eggjm1gw
You have a number of issues in your code and it will be close to impossible to get it right in one go, but let's give it a try. There are two major issues:
Currently you're trying to teach your neural network with very few training examples, as few as a single one per speaker (!). It's impossible for any machine learning algorithm to learn anything.
To make matters worse, what you do is that you feed to the ANN only MFCC for the first 25 ms of each recording (25 comes from winlen parameter of python_speech_features). In each of these recordings, first 25 ms will be close to identical. Even if you had 10k recordings per speaker, with this approach you'd not get anywhere.
I will give you concrete advise, but won't do all the coding - it's your homework after all.
Use all MFCC, not just first 25 ms. Many of these should be skipped, simply because there's no voice activity. Normally there should be VOD (Voice Activity Detector) telling you which ones to take, but in this exercise I'd skip it for starter (you need to learn basics first).
Don't use dictionaries. Not only it won't fly with more than one MFCC vector per speaker, but also it's very inefficient data structure for your task. Use numpy arrays, they're much faster and memory efficient. There's a ton of tutorials, including scikit-learn that demonstrate how to use numpy in this context. In essence, you create two arrays: one with training data, second with labels. Example: if omersk speaker "produces" 50000 MFCC vectors, you will get (50000, 13) training array. Corresponding label array would be 50000 with single constant value (id) that corresponds to the speaker (say, omersk is 0, lucas is 1 and so on). I'd consider taking longer windows (perhaps 200 ms, experiment!) to reduce the variance.
Don't forget to split your data for training, validation and test. You will have more than enough data. Also, for this exercise I'd watch for not feeding too much of data for any single speaker - ot taking steps to make sure algorithm is not biased.
Later, when you make prediction, you will again compute MFCCs for the speaker. With 10 sec recording, 200 ms window and 100 ms overlap, you'll get 99 MFCC vectors, shape (99, 13). The model should run on each of the 99 vectors, for each producing probability. When you sum it (and normalise, to make it nice) and take top value, you'll get the most likely speaker.
There's a dozen of other things that typically would be taken into account, but in this case (homework) I'd focus on getting the basics right.
EDIT: I decided to take a stab at creating the model with your idea at heart, but basics fixed. It's not exactly clean Python, all because it's adapted from Jupyter Notebook I was running.
import python_speech_features
import scipy.io.wavfile as wav
import numpy as np
import glob
import os
from collections import defaultdict
from sklearn.neural_network import MLPClassifier
from sklearn import preprocessing
from sklearn.model_selection import cross_validate
from sklearn.ensemble import RandomForestClassifier
audio_files_path = glob.glob('audio/*.wav')
win_len = 0.04 # in seconds
step = win_len / 2
nfft = 2048
mfccs_all_speakers = []
names = []
data = []
for path in audio_files_path:
fs, audio = wav.read(path)
if audio.size > 0:
mfcc = python_speech_features.mfcc(audio, samplerate=fs, winlen=win_len,
winstep=step, nfft=nfft, appendEnergy=False)
filename = os.path.splitext(os.path.basename(path))[0]
speaker = filename[:filename.find('_')]
data.append({'filename': filename,
'speaker': speaker,
'samples': mfcc.shape[0],
'mfcc': mfcc})
else:
print(f'Skipping {path} due to 0 file size')
speaker_sample_size = defaultdict(int)
for entry in data:
speaker_sample_size[entry['speaker']] += entry['samples']
person_with_fewest_samples = min(speaker_sample_size, key=speaker_sample_size.get)
print(person_with_fewest_samples)
max_accepted_samples = int(speaker_sample_size[person_with_fewest_samples] * 0.8)
print(max_accepted_samples)
training_idx = []
test_idx = []
accumulated_size = defaultdict(int)
for entry in data:
if entry['speaker'] not in accumulated_size:
training_idx.append(entry['filename'])
accumulated_size[entry['speaker']] += entry['samples']
elif accumulated_size[entry['speaker']] < max_accepted_samples:
accumulated_size[entry['speaker']] += entry['samples']
training_idx.append(entry['filename'])
X_train = []
label_train = []
X_test = []
label_test = []
for entry in data:
if entry['filename'] in training_idx:
X_train.append(entry['mfcc'])
label_train.extend([entry['speaker']] * entry['mfcc'].shape[0])
else:
X_test.append(entry['mfcc'])
label_test.extend([entry['speaker']] * entry['mfcc'].shape[0])
X_train = np.concatenate(X_train, axis=0)
X_test = np.concatenate(X_test, axis=0)
assert (X_train.shape[0] == len(label_train))
assert (X_test.shape[0] == len(label_test))
print(f'Training: {X_train.shape}')
print(f'Testing: {X_test.shape}')
le = preprocessing.LabelEncoder()
y_train = le.fit_transform(label_train)
y_test = le.transform(label_test)
clf = MLPClassifier(solver='lbfgs', alpha=1e-2, hidden_layer_sizes=(5, 3), random_state=42, max_iter=1000)
cv_results = cross_validate(clf, X_train, y_train, cv=4)
print(cv_results)
{'fit_time': array([3.33842635, 4.25872731, 4.73704267, 5.9454329 ]),
'score_time': array([0.00125694, 0.00073504, 0.00074005, 0.00078583]),
'test_score': array([0.40380048, 0.52969121, 0.48448687, 0.46043165])}
The test_score isn't stellar. There's a lot to improve (for starter, choice of algorithm), but the basics are there. Notice for starter how I get the training samples. It's not random, I only consider recordings as whole. You can't put samples from a given recording to both training and test, as test is supposed to be novel.
What was not working in your code? I'd say a lot. You were taking 200ms samples and yet very short fft. python_speech_features likely complained to you that the fft is should be longer than the frame you're processing.
I leave to you testing the model. It won't be good, but it's a starter.
I'm trying to use the ResNet-50 model from the ONNX model zoo and load and train it in CNTK for an image classification task. The first thing that confuses me is, that the batch axis (not sure what's the official name for it, dynamic axis?) is set to 1 in this model:
Why is that? Couldn't it simply be [3x224x224]? In this model for example, the input looks like this:
To load the model and use my own Dense layer, I use the following code:
def create_model(num_classes, input_features, freeze=False):
base_model = load_model("restnet-50.onnx", format=ModelFormat.ONNX)
feature_node = find_by_name(base_model, "gpu_0/data_0")
last_node = find_by_uid(base_model, "Reshape2959")
substitutions = {
feature_node : placeholder(name='new_input')
}
cloned_layers = last_node.clone(CloneMethod.clone, substitutions)
cloned_out = cloned_layers(input_features)
z = Dense(num_classes, activation=softmax, name="prediction") (cloned_out)
return z
For training I use (shortened):
# datasets = list of classes
feature = input_variable(shape=(1, 3, 224, 224))
label = input_variable(shape=(1,3))
model = create_model(len(datasets), feature)
loss = cross_entropy_with_softmax(model, label)
# some definitions for learner, epochs, ProgressPrinters missing
for epoch in range(epochs):
loss.train((X_current,y_current), parameter_learners=[learner], callbacks=[progress_printer])
X_current is a single image and y_current the corresponding class label both encoded as numpy arrays with the followings shapes
X_current.shape
(1, 3, 224, 224)
y_current.shape
(1, 3)
When I try to train the model, I get
"ValueError: ToBatchAxis7504 ToBatchAxisNode operation can only operate on tensor without minibatch data (no layout)"
What's wrong here?
I used the plot_importance to show me the importance variables. But some variables are categorical, so I did some transformation. After I transformed the type of the variables, when i plot importance features, the plot does not show me feature names. I attached my code, and the plot.
dataset = data.values
X = dataset[1:100,0:-2]
predictors=dataset[1:100,-1]
X = X.astype(str)
encoded_x = None
for i in range(0, X.shape[1]):
label_encoder = LabelEncoder()
feature = label_encoder.fit_transform(X[:,i])
feature = feature.reshape(X.shape[0], 1)
onehot_encoder = OneHotEncoder(sparse=False)
feature = onehot_encoder.fit_transform(feature)
if encoded_x is None:
encoded_x = feature
else:
encoded_x = np.concatenate((encoded_x, feature), axis=1)
print("X shape: : ", encoded_x.shape)
response='Default'
#predictors=list(data.columns.values[:-1])
# Randomly split indexes
X_train, X_test, y_train, y_test = train_test_split(encoded_x,predictors,train_size=0.7, random_state=5)
model = XGBClassifier()
model.fit(X_train, y_train)
plot_importance(model)
plt.show()
[enter image description here][1]
[1]: https://i.stack.imgur.com/M9qgY.png
This is the expected behaviour- sklearn.OneHotEncoder.transform() returns a numpy 2d array instead of the input pd.DataFrame (i assume that's the type of your dataset). So it is not a bug, but a feature. It doesn't look like there is a way to pass feature names manually in the sklearn API (it is possible to set those in xgb.Dmatrix creation in the native training API).
However, your problem is easily solvable with pd.get_dummies() instead of the LabelEncoder + OneHotEncoder combination that you have implemented. I do not know why did you choose to use it instead (it can be useful, if you need to handle also a test set but then you need to play extra tricks), but i would advise in favour of pd.get_dummies()
In this post you can find a very good tutorial on how to apply SVM classifier to MNIST dataset. I was wondering if I could use logistic regression instead of SVM classifier. So I searhed for Logistic regression in openCV, And I found that the syntax for both classifiers are almost identical. So I guessed that I could just comment out these parts:
cv::Ptr<cv::ml::SVM> svm = cv::ml::SVM::create();
svm->setType(cv::ml::SVM::C_SVC);
svm->setKernel(cv::ml::SVM::POLY);//LINEAR, RBF, SIGMOID, POLY
svm->setTermCriteria(cv::TermCriteria(cv::TermCriteria::MAX_ITER, 100, 1e-6));
svm->setGamma(3);
svm->setDegree(3);
svm->train( trainingMat , cv::ml::ROW_SAMPLE , labelsMat );
and replace it with:
cv::Ptr<cv::ml::LogisticRegression> lr1 = cv::ml::LogisticRegression::create();
lr1->setLearningRate(0.001);
lr1->setIterations(10);
lr1->setRegularization(cv::ml::LogisticRegression::REG_L2);
lr1->setTrainMethod(cv::ml::LogisticRegression::BATCH);
lr1->setMiniBatchSize(1);
lr1->train( trainingMat, cv::ml::ROW_SAMPLE, labelsMat);
But first I got this error:
OpenCV Error: Bad argument(data and labels must be a floating point matrix)
Then I changed
cv::Mat labelsMat(labels.size(), 1, CV_32S, labelsArray);
to:
cv::Mat labelsMat(labels.size(), 1, CV_32F, labelsArray);
And now I get this error: OpenCV Error: bad argument(data should have atleast two classes)
I have 10 classes (0,1,...,9) but I don't know why I get this error. My codes are almost identical with the ones in the mentioned tutorial.
In Python you could do something like this:
import matplotlib.pyplot as plt
# Import datasets, classifiers and performance metrics
from sklearn import datasets, svm, metrics
from sklearn.linear_models import LogisticRegression
# The digits dataset
digits = datasets.load_digits()
# The data that we are interested in is made of 8x8 images of digits, let's
# have a look at the first 3 images, stored in the `images` attribute of the
# dataset. If we were working from image files, we could load them using
# pylab.imread. Note that each image must have the same size. For these
# images, we know which digit they represent: it is given in the 'target' of
# the dataset.
images_and_labels = list(zip(digits.images, digits.target))
for index, (image, label) in enumerate(images_and_labels[:4]):
plt.subplot(2, 4, index + 1)
plt.axis('off')
plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
plt.title('Training: %i' % label)
# To apply a classifier on this data, we need to flatten the image, to
# turn the data in a (samples, feature) matrix:
n_samples = len(digits.images)
data = digits.images.reshape((n_samples, -1))
Choose which one of the classifiers you like below
# Create a classifier: a support vector classifier
classifier = svm.SVC(gamma=0.001)
# create a Logistic Regression Classifier
classifier = LogisticRegression(C=1.0)
# We learn the digits on the first half of the digits
classifier.fit(data[:n_samples / 2], digits.target[:n_samples / 2])
# Now predict the value of the digit on the second half:
expected = digits.target[n_samples / 2:]
predicted = classifier.predict(data[n_samples / 2:])
print("Classification report for classifier %s:\n%s\n"
% (classifier, metrics.classification_report(expected, predicted)))
print("Confusion matrix:\n%s" % metrics.confusion_matrix(expected, predicted))
images_and_predictions = list(zip(digits.images[n_samples / 2:], predicted))
for index, (image, prediction) in enumerate(images_and_predictions[:4]):
plt.subplot(2, 4, index + 5)
plt.axis('off')
plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
plt.title('Prediction: %i' % prediction)
plt.show()
You can see the whole code here
I read this thread about the difference between SVC() and LinearSVC() in scikit-learn.
Now I have a data set of binary classification problem(For such a problem, the one-to-one/one-to-rest strategy difference between both functions could be ignore.)
I want to try under what parameters would these 2 functions give me the same result. First of all, of course, we should set kernel='linear' for SVC()
However, I just could not get the same result from both functions. I could not find the answer from the documents, could anybody help me to find the equivalent parameter set I am looking for?
Updated:
I modified the following code from an example of the scikit-learn website, and apparently they are not the same:
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets
# import some data to play with
iris = datasets.load_iris()
X = iris.data[:, :2] # we only take the first two features. We could
# avoid this ugly slicing by using a two-dim dataset
y = iris.target
for i in range(len(y)):
if (y[i]==2):
y[i] = 1
h = .02 # step size in the mesh
# we create an instance of SVM and fit out data. We do not scale our
# data since we want to plot the support vectors
C = 1.0 # SVM regularization parameter
svc = svm.SVC(kernel='linear', C=C).fit(X, y)
lin_svc = svm.LinearSVC(C=C, dual = True, loss = 'hinge').fit(X, y)
# create a mesh to plot in
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
# title for the plots
titles = ['SVC with linear kernel',
'LinearSVC (linear kernel)']
for i, clf in enumerate((svc, lin_svc)):
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, m_max]x[y_min, y_max].
plt.subplot(1, 2, i + 1)
plt.subplots_adjust(wspace=0.4, hspace=0.4)
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, cmap=plt.cm.Paired, alpha=0.8)
# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Paired)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.xticks(())
plt.yticks(())
plt.title(titles[i])
plt.show()
Result:
Output Figure from previous code
In mathematical sense you need to set:
SVC(kernel='linear', **kwargs) # by default it uses RBF kernel
and
LinearSVC(loss='hinge', **kwargs) # by default it uses squared hinge loss
Another element, which cannot be easily fixed is increasing intercept_scaling in LinearSVC, as in this implementation bias is regularized (which is not true in SVC nor should be true in SVM - thus this is not SVM) - consequently they will never be exactly equal (unless bias=0 for your problem), as they assume two different models
SVC : 1/2||w||^2 + C SUM xi_i
LinearSVC: 1/2||[w b]||^2 + C SUM xi_i
Personally I consider LinearSVC one of the mistakes of sklearn developers - this class is simply not a linear SVM.
After increasing intercept scaling (to 10.0)
However, if you scale it up too much - it will also fail, as now tolerance and number of iterations are crucial.
To sum up: LinearSVC is not linear SVM, do not use it if do not have to.