Deep Learning questions and answers
Neural network architectures, training dynamics and GPU execution. Page 4 of 20.
ML System Design practice on Codemia
Design recommenders, ranking systems and training pipelines the way ML interviews actually ask for them, with worked solutions.
Answers 181-240
- cuda install error on Ubuntu 17.04
- CUDA stream compaction algorithm
- CUDA streams, texture binding and async memcpy
- cudaGetDevice failed. Status CUDA driver version is insufficient for CUDA runtime version
- CuDNN library compatibility error after loading model weights
- CUDNN_STATUS_BAD_PARAM when trying to perform inference on a LSTM Seq2Seq with masked inputs
- CUDNN_STATUS_NOT_INITIALIZED when trying to run TensorFlow
- CuDNNLSTM Failed to call ThenRnnForward
- Custom loss function for U-net in keras using class weights class_weight not supported for 3 dimensional targets
- Custom loss function in Keras
- Custom loss function in Keras to penalize false negatives
- Custom loss function with weights in Keras
- Custom median pooling in tensorflow
- Custom padding for convolutions in TensorFlow
- Custom transformer for sklearn Pipeline that alters both X and y
- Custom weighted loss function in Keras for weighing each element
- ''CXXABI_1.3.8'' not found in tensorflow-gpu - install from source
- Darknet YOLO image size
- Data Augmentation in PyTorch
- Dataset gets re-copied to GPU causing out of memory when calling to eval twice
- Dead simple example of synaptic js lstm rnn algorithm
- Debugging a Neural Network
- Decoder's weights of Autoencoder with tied weights in Keras
- Deep-Learning Nan loss reasons
- Deep-Learning Nan loss reasons
- Deep Belief Networks vs Convolutional Neural Networks
- Deep learning for image classification
- Deep Learning model with Different data types in Keras
- Deep learning Udacity course Prob 2 assignment 1 notMNIST
- Deep neural network skip connection implemented as summation vs concatenation?
- deeplearning4j - using an RNN/LSTM for audio signal processing
- Default Adam optimizer doesn't work in tf.keras but string adam does
- Deleting all but a few nodes in TensorFlow graph
- Deploy Semantic Segmentation Network U-Net with TensorRT no upsampling support
- Derivative of activation function and use in backpropagation
- Design patterns for tensorflow models
- Determinism in tensorflow gradient updates?
- Difference between bidirectional_dynamic_rnn and stack_bidirectional_dynamic_rnn in Tensorflow
- Difference between Conv2D and Convolution2D in Keras
- Difference between Conv3d vs Conv2d
- Difference between Dense2 and Dense1 as the final layer of a binary classification CNN?
- Difference between feature_column.embedding_column and keras.layers.Embedding in TensorFlow
- Difference between installation libraries of Tensorflow GPU vs CPU
- Difference between Keras' BatchNormalization and PyTorch's BatchNorm2d?
- Difference between Keras model.save and model.save_weights?
- Difference between keras.metrics.Accuracy and accuracy
- Difference between modelx and model.predictx in Keras?
- Difference between NumPy and TensorFlow?
- difference between Tensorflow's Graph and GraphDef
- Difference between tf.clip_by_value and tf.clip_by_global_norm for RNN's and how to decide max value to clip on?
- Difference between tfjs_layers_model and tfjs_graph_model
- Difference between tf.layers.conv2d and tf.contrib.slim.conv2d
- Difference between tf.saved_model.savemodel, path_to_dir and tf.keras.model.save
- Difference on Keras 1.2.2 and Keras 2.2 Predictions
- Different approaches for applying SVM in Keras
- Differentiable round function in Tensorflow?
- Digit Recognition on CNN
- Dimension of shape in conv1D
- Display image of graph in TensorFlow?
- Distributed Tensorflow who applies the parameter update?
.png&w=3840&q=75)
Free course
Beginner
7 lessons
2 hours
Tackling System Design Interview Problems
A short course that equips you with the skills to approach system design interviews methodically.
Start the free course