Learn Python Tutorials

We are using TrainResNet_CIFAR10.py as an example to learn cntk. We have created two methods, eva… Read more Eval And Test_minibatch In Cntk

For example, I got a tensor: tensor = torch.rand(12, 512, 768) And I got an index list, say it is:… Read more How To Dynamically Index The Tensor In Pytorch?

I have Unet model from Retina Unet, However I have augmented the images as well as the masks. Now?… Read more Keras Valueerror: Output Of Generator Should Be A Tuple (x, Y, Sample_weight) Or (x, Y). Found: None

I have a keras 3D/2D model. In this model a 3D layer has a shape of [None, None, 4, 32]. I want to … Read more How To Use Reshape Keras Layer With Two None Dimension?

I was wondering if it's possible to predict a 1-by-n feature associated to an input image using… Read more How To Predict Float Vector Labels With Caffe?

I have the following keras model that is working fine: model = tf.keras.Sequential( [ #fir… Read more Non-identical Results From String Identifier And Actual Class Names For Activations, Loss Functions, And Metrics

I want to fine-tune BERT on texts that are related to a specific domain (in my case related to engi… Read more Fine-tune Bert For Specific Domain (unsupervised)

I am using transfer learning with MobileNet and then sending the extracted features to a LSTM for v… Read more Valueerror: Input 0 Of Layer Sequential_16 Is Incompatible With The Layer: Expected Ndim=5, Found Ndim=4. Full Shape Received: [none, 224, 224, 3]

The Keras website has this article about exporting Keras models to core Tensorflow. However the ste… Read more Why Is Valueerror Thrown By Keras.models.model_from_config() In The Keras-to-tensorflow Exporting Example?

I am beginner with keras and today I bumped into this sort of issue I don't know how to handle.… Read more Why Is History Storing Auc And Val_auc With Incrementing Integers (auc_2, Auc_4, ...)?

i have a directory of png files . there is a train folder and test folder . In the train folder i h… Read more How Can I Load A Directory Of Png In Tensorflow?

I haven't used Keras and I'm thinking whether to use it or not. I want to save a trained la… Read more Is It Possible To Save A Trained Layer To Use Layer On Keras?

In TensorFlow, I can get the count of each element in an array with tf.bincount: x = tf.placeholder… Read more Tensorflow: Bincount With Axis Option

I've written a simple tensorflow program here that reads in a feature list and tries to predict… Read more Loss Function Is Returning Nan Tensorflow

I have 1000 resume in png format and I am implementing MaskRcnn for object detection. What data aug… Read more What Are Some Good Data Augmentation Techniques For Document Images?

In Neural Networks and Deep Learning, there's an object called network3 (which is a PY file, wr… Read more Error (theano.gof.opt): Optimization Failure Due To: Constant_folding

I'm trying to detect fraud using autoencoder and Keras. I've written the following code as … Read more Keras - Autoencoder Accuracy Stuck On Zero

Problem statement I have 3 classes (A, B, and C). I have 6 features: train_x = [[ 6.442 6.338 7.0… Read more How Can I Implement This Model?

Do RNNs learn different dependency patterns when the input is batch-major as opposed to time-major?… Read more Batch-major Vs Time-major Lstm

I'm trying to use UINT8 quantization while converting tensorflow model to tflite model: If use … Read more Understanding Tf.contrib.lite.tfliteconverter Quantization Parameters