dpoulopoulos

prompt = """
    Input: Print the current directory
    Output: pwd

    Input: List files
    Output: ls -l

    Input: Change directory to /tmp
    Output: cd /tmp

dpoulopoulos

plt.figure(figsize=(10,6))
sns.kdeplot(probs_lgr, label='Logistic regression')
sns.kdeplot(preds_svc, label='SVM')
plt.title("Probability Density Plot for 2 Classifiers")
plt.show()

dpoulopoulos

strategy = tf.distribute.MirroredStrategy()

BATCH_SIZE = 64
GLOBAL_BATCH_SIZE = BATCH_SIZE * strategy.num_replicas_in_sync

train_data = tf.data.Dataset(...).batch(GLOBAL_BATCH_SIZE)

with strategy.scope():
  model = tf.keras.Sequential(...)
  model.compile(...)

dpoulopoulos

BATCH_SIZE = 64

train_data = tf.data.Dataset(...).batch(BATCH_SIZE)

model = tf.keras.Sequential(...)
model.compile(...)

model.fit(train_data, epochs=4)

dpoulopoulos

class MyModel(keras.Model):
  def train_step(self, data):
    # Get the data batch
    inputs, targets = data
    # Get the model's weights
    trainable_vars = self.trainable_variables
    # Forward pass
    with tf.GradientTape() as tape:
      # Get the predictions
      preds = self(inputs, training=True)

dpoulopoulos

import torch
import torchvision.models as models
import torchvision.transforms as transforms

from PIL import Image


img = Image.open("test/assets/encode_jpeg/grace_hopper_517x606.jpg")

# Step 1: Load a pre-trained model.

dpoulopoulos

from PIL import Image
from torchvision.prototype import models as pm


img = Image.open("test/assets/encode_jpeg/grace_hopper_517x606.jpg")

# Step 1: Load a pre-trained model.
# In this step we will load a ResNet architecture.
weights = pm.ResNet50_Weights.ImageNet1K_V1
model = pm.resnet50(weights=weights)

dpoulopoulos

FROM <base.Dockerfile:tag>

# Install Tensorflow
RUN pip3 install tensorflow
# Install PyTorch
RUN pip3 install torch==1.5.1 torchvision==0.6.1

# Create and configure NB_USER user with UID=1000 and in the 'users' group
# but allow for non-initial launches of the notebook to have
# $HOME provided by the contents of a PV

dpoulopoulos

ARG CUDA=10.1
ARG UBUNTU_VERSION=18.04

FROM nvidia/cuda:${CUDA}-base-ubuntu${UBUNTU_VERSION} as base

# ARCH and CUDA are specified again because the FROM directive resets ARGs
# (but their default value is retained if set previously)
ARG CUDA
ARG CUDNN=7.6.4.38-1
ARG CUDNN_MAJOR_VERSION=7

dpoulopoulos

import ctypes
import pathlib

if __name__ == "__main__":
    # load the lib
    libname = pathlib.Path().absolute() / "libcadd.so"
    c_lib = ctypes.CDLL(libname)
    
    x, y = 6, 2.3