pythonlessons

dataset, vocab, max_len = [], set(), 0

# Preprocess the dataset by the specific IAM_Words dataset file structure
words = open(os.path.join(dataset_path, "words.txt"), "r").readlines()
for line in tqdm(words):
    if line.startswith("#"):
        continue

    line_split = line.split(" ")
    if line_split[1] == "err":

pythonlessons

def download_and_unzip(url, extract_to='Datasets', chunk_size=1024*1024):
    http_response = urlopen(url)

    data = b''
    iterations = http_response.length // chunk_size + 1
    for _ in tqdm(range(iterations)):
        data += http_response.read(chunk_size)

    zipfile = ZipFile(BytesIO(data))
    zipfile.extractall(path=extract_to)

pythonlessons

import os
import tarfile
from tqdm import tqdm
from io import BytesIO
from zipfile import ZipFile
from urllib.request import urlopen

import torch
import torch.optim as optim
from torchsummaryX import summary

pythonlessons

# loop over test images
for test_image, test_target in zip(test_data, test_targets):

    # normalize image and convert to tensor
    inference_image = torch.from_numpy(test_image).float() / 255.0
    inference_image = inference_image.unsqueeze(0).unsqueeze(0)

    # predict
    output = network(inference_image)
    pred = output.argmax(dim=1, keepdim=True)

pythonlessons

import os
import cv2
import numpy as np
import requests, gzip, os, hashlib

from model import Net

path='Datasets/mnist' # Path where to save the downloaded mnist dataset
def fetch(url):
    if os.path.exists(path) is False:

pythonlessons

import torch
from model import Net

# output path
model_path = 'Model/07_pytorch_wrapper'

# construct network and load weights
network = Net()
network.load_state_dict(torch.load("Models/07_pytorch_wrapper/model.pt"))
network.eval() # set to evaluation mode

pythonlessons

Epoch 1 - loss: 0.6189 - accuracy: 0.8059: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████| 938/938 [00:12<00:00, 74.08it/s]
          val_loss: 0.1308 - val_accuracy: 0.9584: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 157/157 [00:00<00:00, 239.33it/s]
2023-03-08 21:31:31,494 INFO ModelCheckpoint: Epoch 1: val_accuracy improved from -inf to 0.95840, saving model to Models/07_pytorch_wrapper/model.pt
Epoch 2 - loss: 0.2956 - accuracy: 0.9151: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 938/938 [00:06<00:00, 138.14it/s]
          val_loss: 0.0915 - val_accuracy: 0.9720: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 157/157 [00:00<00:00, 225.51it/s]
2023-03-08 21:31:38,996 INFO ModelCheckpoint: Epoch 2: val_accuracy improved from 0.95840 to 0.97200, saving model to Models/07_pytorch_wrapper/m

pythonlessons

model.fit(
    train_dataProvider, 
    test_dataProvider, 
    epochs=100, 
    callbacks=[earlyStopping, modelCheckpoint]
    )

pythonlessons

# create model object that will handle training and testing of the network
model = Model(network, optimizer, loss, metrics=[Accuracy()])

pythonlessons

# create callbacks
earlyStopping = EarlyStopping(
    monitor='val_accuracy', 
    patience=3, 
    mode="max", 
    verbose=1
    )
modelCheckpoint = ModelCheckpoint(
    'Models/07_pytorch_wrapper/model.pt', 
    monitor='val_accuracy',