archydeberker

from typing import List
from uuid import UUID
from sqlalchemy import create_engine
from sqlalchemy.orm import Session, sessionmaker
from fastapi import FastAPI, Depends, HTTPException
from sqlalchemy.orm import Session
from pydantic import BaseModel

class User(BaseModel):
    # This is a DB model - in SQLModel you can return the ORM model directly bc it's Pydantic under the hood

archydeberker

n_searches = 20
n_epochs = 15
n_val = 500

for train_size in dataset_size:
    print('Training with subset %1.4f, which is %d images'%(train_size, train_size*total_train))
    
    test_acc[train_size] = []
    test_loss[train_size] = []
    val_acc[train_size] = []

archydeberker

def random_hyperparamters():
    """ Returns randomly drawn hyperparamters for our CNN"
    
    hyperparam_dict = {}
    
    hyperparam_dict['lr'] = 10 ** np.random.uniform(-6, -1)
    hyperparam_dict['weight_decay'] = 10 ** np.random.uniform(-6, -3)
    hyperparam_dict['momentum'] = 10 ** np.random.uniform(-1, 0)
    
    hyperparam_dict['conv1_size'] = int(np.random.uniform(10,100))

archydeberker

test_acc = {}
val_acc = {}
train_acc = {}
test_loss = {}
for train_size in dataset_size:
    print('Training with subset %1.4f, which is %d images'%(train_size, train_size*total_train))
    net = Net()
    
    # Train model with an early stopping criterion - terminates after 4 epochs of non-improving val loss
    net, loss_list, val_list = train_model(net, trainset_loaders[train_size], valloader, 1000, n_epochs=10)

archydeberker

def get_dataset_size(start=0.5, end=100, base=2):
    """ Returns exponentially distributed dataset size vector"""
    dataset_size=[start]
    while True:
        dataset_size.append(dataset_size[-1]*base)
        if dataset_size[-1] > end:
            dataset_size[-1] = end
            break
    
    return dataset_size

archydeberker

class Net(nn.Module):
  """ A simple 5 layer CNN, configurable by passing a hyperparameter dictionary at initialization.
      Based upon the one outlined in the Pytorch intro tutorial 
      (http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network)
  """
  
    def __init__(self, hyperparam_dict=None):
        super(Net, self).__init__()
        
        if not hyperparam_dict :