wac81

wac81

wac81

# WARNING: These steps seem to not work anymore!

#!/bin/bash

# Purge existign CUDA first
sudo apt --purge remove "cublas*" "cuda*"
sudo apt --purge remove "nvidia*"

# Install CUDA Toolkit 10
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-repo-ubuntu1804_10.0.130-1_amd64.deb

wac81

This gist contains instructions about cuda v11.1 and cudnn 8.0.4 installation in Ubuntu 18.04 for Tensorflow 2.4.1

• If you have previous installation remove it first.

!/bin/bash
sudo apt-get purge *nvidia*
sudo apt remove --autoremove nvidia-*
sudo rm /etc/apt/sources.list.d/cuda*
sudo apt remove --autoremove nvidia-cuda-toolkit
sudo apt-get autoremove && sudo apt-get autoclean

wac81

# ----------------------------
# Inference
# ----------------------------
def inference (model, val_dl):
  correct_prediction = 0
  total_prediction = 0

  # Disable gradient updates
  with torch.no_grad():
    for data in val_dl:

wac81

This is how I managed to build TensorFlow 2.0 on Ubuntu 18.04 (x86_64) with Bazelisk:

$ sudo apt update
$ sudo apt full-upgrade
$ sudo apt install curl

# Install Bazelisk.
$ sudo curl -Lo /usr/local/bin/bazel https://github.com/bazelbuild/bazelisk/releases/download/v1.1.0/bazelisk-linux-amd64
$ sudo chmod +x /usr/local/bin/bazel

wac81

1. Install osxfuse:

brew cask install osxfuse

2. Reboot your Mac.

3. Install ntfs-3g:

wac81

from keras.callbacks import Callback
import keras.backend as K
import numpy as np

class SGDRScheduler(Callback):
    '''Cosine annealing learning rate scheduler with periodic restarts.

    # Usage
        ```python
            schedule = SGDRScheduler(min_lr=1e-5,

wac81

import keras.backend as K
from keras.layers import Dense, Activation, Multiply, Add, Lambda
import keras.initializers

def highway_layers(value, n_layers, activation="tanh", gate_bias=-3):
    dim = K.int_shape(value)[-1]
    gate_bias_initializer = keras.initializers.Constant(gate_bias)
    for i in range(n_layers):     
        gate = Dense(units=dim, bias_initializer=gate_bias_initializer)(value)
        gate = Activation("sigmoid")(gate)

wac81

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.optim import Optimizer

KD_loss = nn.KLDivLoss(reduction='batchmean')

def kd_step(teacher: nn.Module,
            student: nn.Module,
            temperature: float,