Deep Learning questions and answers
Neural network architectures, training dynamics and GPU execution. Page 5 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 241-300
- Do keras loss have to output one scalar per batch or one scalar for the whole batch ?
- Does applying a Dropout Layer after the Embedding Layer have the same effect as applying the dropout through the LSTM dropout parameter?
- Does batch normalisation work with a small batch size?
- Does bias in the convolutional layer really make a difference to the test accuracy?
- Does config.gpu_options.allow_growthTrue reduce performance in the long run?
- Does cudaFree after asynchronous call work?
- Does dropout layer go before or after dense layer in TensorFlow?
- Does EarlyStopping in Keras save the best model?
- Does model.compile initialize all the weights and biases in Keras tensorflow backend?
- Does TensorFlow by default use all available GPUs in the machine?
- Does TensorFlow have cross validation implemented?
- Does tensorflow map_fn support taking more than one tensor?
- Does TensorFlow plan to support OpenCL?
- Does Tensorflow simplify a computational graph?
- Does the TensorFlow backend of Keras rely on the eager execution?
- Doing pairwise distance computation with TensorFlow
- downloading ResNet50 in Keras generates SSL CERTIFICATE_VERIFY_FAILED
- Drop a dimension of a tensor in Tensorflow
- Dropout behavior in Keras with rate1 dropping all input units not as expected
- Dropout layer before or after LSTM. What is the difference?
- Dropout rate guidance for hidden layers in a convolution neural network
- duplicate a tensorflow graph
- Dynamic quantization in Pytorch starts random training after quantization
- Dynamically tile a tensor depending on the batch size
- Eager Execution - InternalError Could not find valid device for node name Sqrt
- EarlyStopping is ignoring my custom metrics defined. Keras model
- Effects of randomizing the order of inputs to a neural network
- Efficient element-wise multiplication of a matrix and a vector in TensorFlow
- Efficiently grab gradients from TensorFlow?
- ERROR Cannot uninstall 'wrapt'. when installing tensorflow-gpu1.14
- Error OOM when allocating tensor with shape
- Error Out Of Memory, tensorflow cnn
- Error Propagation in Keras DNN and/or CNN Regression
- Error running basic tensorflow example
- Error Trying to Convert TensorFlow Saved Model to TensorFlow.js Model
- Error using Tensorflow with GPU
- Error when checking model input expected convolution2d_input_1 to have shape None, 3, 32, 32 but got array with shape 50000, 32, 32, 3
- Error when checking target expected to have shape 256, 256, 1 but got array with shape 256, 256, 3
- Error when profiling keras models
- Estimating the number of neurons and number of layers of an artificial neural network
- Evaluate a function in a sliding window with Keras
- Evaluate all pair combinations of rows of two tensors in tensorflow
- Exact model converging on keras-tf but not on keras
- Exception CallbackOnCollectedDelegate when creating tensorflow graph
- Expected parameters of Conv2d
- Explain with example how embedding layers in keras works
- Extract encoder and decoder from trained autoencoder
- Extract features using pre-trained Tensorflow CNN
- Extract features using pre-trained Tensorflow CNN
- Extract random slice from tensor in Tensorflow
- extrapolation with recurrent neural network
- facenet triplet loss with keras
- Fail to run word embedding example in tensorflow tutorial with GPUs
- Failed to create CUBLAS handle. Tensorflow interaction with OpenCV
- Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
- Faster-RCNN, why don''t we just use only RPN for detection?
- Faster RCNN for TensorFlow
- Feature-wise scaling and shifting FiLM layer in Keras
- Feeding image data in tensorflow for transfer learning
- Filter shape in tensorflow.nn.conv2d with NCHW format
.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