Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 6 months ago.
Improve this question
I am struggling with training a CNN model to identify dogbreeds. I intend to train the Stanford Dogs Dataset using ResNet architecture. I downloaded the dataset from http://vision.stanford.edu/aditya86/ImageNetDogs/ into google-colab notebook and have extracted the images in the dataset. I get a folder structure like this: folder_structure. I know I need the folder structure which has subfolders train and test and then further subfolders with images of dogs with corresponding species. How do I go along doing that?
You don't need to strictly create separate folders for train and test. You can use the method tf.keras.utils.image_dataset_from_directory from tensorflow. It lets you load your all-in-one-folder dataset taking the right split while loading. This is how:
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
"/images/", # path to your data folder
validation_split=0.2, # percentage reserved for test
subset="training", # this dataset is for training
seed=1024 # must be the same for both train and test: ensures that you take the images consistently
)
test_ds = tf.keras.preprocessing.image_dataset_from_directory(
"/images/",
validation_split=0.2,
subset="validation",
seed=1024
)
Both functions return a tf.data.Dataset object. The argument validation_split lets you specify the percentage of data to reserve for validation (test in your case). In the example above I chose 80% train and 20% validation.
The seed argument must be the same for both train_ds and test_ds, because it ensures that the images are taken in same order, so you don't end up with mixed images in your train and test split.
Related
Closed. This question needs debugging details. It is not currently accepting answers.
Edit the question to include desired behavior, a specific problem or error, and the shortest code necessary to reproduce the problem. This will help others answer the question.
Closed 2 years ago.
Improve this question
I have created a simple Keras model which fits to the points I've created as shown in below image. My problem is that when I run the code, I can't always get this red line (maybe in 1 run of 5 runs I get the desired result. In other 4 runs I get a straight line). What should I do to make my model fit always?
Is this related to randomness
model = models.Sequential()
model.add(layers.Dense(2,activation = 'linear'))
model.add(layers.Dense(2,activation = 'relu'))
model.add(layers.Dense(1,activation = 'linear'))
model.compile(loss='mse', optimizer=optimizers.Adam(lr=0.001))
history = model.fit(X,y, epochs=1500, verbose=False)
y_hat = model.predict(X)**strong text**
pyplot image
Yes, the initial weights of your network get randomly initialized. To get reproducable results, you must set a seed for the random numbers. The random initialization of the weights is based on this seed. Having the same seed will therefore always result in the same initialization.
Taken from https://machinelearningmastery.com/reproducible-results-neural-networks-keras/
that is:
from numpy.random import seed
seed(1)
from tensorflow import set_random_seed
set_random_seed(2)
The seed values can have any number of course, but must be fixed.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I followed a tutorial about detecting objects using deep learning here: https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html
At some point, after training up to 4082 steps, i stopped the training using CTRL+C.
Now i have bunch of files under my training directory, which looks like this:
list of files in the training directory
The question is, how do i proceed now? what to do next? the tutorial doesn't teach you how to use the training data, how to even test it if its recognizing correctly.
Thanks in advance.
The files you obtained are checkpoints. What you want to do now is to restore your model from the checkpoints. Indications from CV tricks:
with tf.Session() as sess:
model = tf.train.import_meta_graph('my_test_model-1000.meta')
model.restore(sess, tf.train.latest_checkpoint('./'))
After, you can evaluate your model on your test set:
test_accuracy = tfe.metrics.Accuracy()
for (x, y) in test_dataset:
logits = model(x)
prediction = tf.argmax(logits, axis=1, output_type=tf.int32)
test_accuracy(prediction, y)
print("Test set accuracy: {:.3%}".format(test_accuracy.result()))
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I am new to tensorflow and trying to look at different examples of tensorflow to understand it better.
Now I have seen this line being used in many tensorflow examples without mentioning of any specific embedding algorithm being used for getting the words embeddings.
embeddings = tf.Variable(tf.random_uniform((vocab_size, embed_dim), -1, 1))
embed = tf.nn.embedding_lookup(embeddings, input_data)
Here are some examples:
https://github.com/Decalogue/dlnd_tv_script_generation/blob/master/dlnd_tv_script_generation.py
https://github.com/ajmaradiaga/cervantes-text-generation/blob/master/cervants_nn.py
I understand that the first line will initialize the embedding of the words by random distribution but will the embedding vectors further be trained in the model to give more accurate representation of the words (and change the initial random values to more accurate numbers) and if yes what is the actual method being used when there is no mention of any obvious embedding methods such as using word2vec and glove inside the code (or feeding the pre_tained vectors of these methods instead of random numbers in the beginning)?
Yes, those embeddings are trained further just like weights and biases otherwise representing words with some random values wouldn't make any sense. Those embeddings are updated while training like you would update a weight matrix, that is, by using optimization methods like Gradient Descent or Adam optimizer, etc.
When we use pre-trained embeddings like word2vec, they're already trained on very large datasets and are quite accurate representations of words already hence, they don't need any further training. If you are asking how those are trained, there are two main training algorithms that can be used to learn the embedding from the text; they are Continuous Bag of Words (CBOW) and Skip Grams. Explaining them completely is not possible here but I would suggest taking help from Google. This article might get you started.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I'm not exactly sure how to approach this question. The dataset has 8 attributes and one y-value. How would I train a linear regression model on 85% of the dataset?
You can also use train_test_split from sklearn as in sklearn example to split the data into training and testing sets e.g. if X is data with features and y is label then:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.15)
And for linear regression you can try using: linregress from scipy as in similar question:
Use ndf = df.sample(frac=0.85) to get a DataFrame with 85% of your total rows and then use this new DataFrame ndf to train your linear regression model.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I'm new to tensorflow and would like to know if there is any tutorial or example of a multilabel classification with multiple network outputs.
I'm asking this because I have a collection of images, in which, each image can belong to several classes and my output needs to have a score of each class.
I also do not know if the tensorflow follows some file pattern of the images and the classes, so if someone has some example it would facilitate a lot.
Thank you.
You can also try transforming your problem from a multi-label to multi-class classification using a Label Powerset approach. Label Powerset transformation treats every label combination attested in the training set as a different class and constructs one instance of a multi-class clasifier - and after prediction converts the assigned classes back to multi-label case. It is provided in scikit-multilearn and scikit-compatibility wrapper over the tensorflow Estimator or via an input_fn or use skflow. Then just plug it into an instance of LabelPowerset.
The code could go as follows:
from skmultilearn.problem_transform import LabelPowerset
import tensorflow.contrib.learn as skflow
# assume data is loaded using
# and is available in X_train/X_test, y_train/y_test
# initialize LabelPowerset multi-label classifier
# with tensor flow DNN base classifier
classifier = LabelPowerset(skflow.TensorFlowDNNClassifier(OPTIONS))
# train
classifier.fit(X_train, y_train)
# predict
predictions = classifier.predict(X_test)
The most naive (and reasonable) approach would be to train a classification network, and remove the softmax layer and replace it with a vector of sigmoids. This way you can have multiple units with an activation of 1.
You can see on TF-slim examples for classification networks. Under the path datasets you will find examples on how to prepare the TFExample "file pattern" for images and classes
Most solutions refer to sigmoid loss, and sigmoid do solve multi-label classification well in my case by tf.nn.sigmoid_cross_entropy_with_logits(labels,logits) in tensorflow.
However, when I handled class unbalance problem, where negative cases is much more than positive cases, I found my edited softsign loss worked much better than sigmoid. The adjust coefficient gamma is added to label to lower negative class's gradient by 3/4.
def unbalance_softsign_loss(labels, logits):
gamma = 1.25 *labels - 0.25
res = 1 - tf.log1p( gamma*logits/(1+ tf.abs(logits)) )
return res
where labels is multi-hot encoding vectors like [0, 1, 0, 1, 0], logits ~ (-inf, inf)