itsuncheng

MODEL:
  TYPE: generalized_rcnn
  CONV_BODY: FPN.add_fpn_ResNet50_conv5_body
  NUM_CLASSES: 4
  FASTER_RCNN: True
NUM_GPUS: 1
SOLVER:
  WEIGHT_DECAY: 0.0001
  LR_POLICY: steps_with_decay
  BASE_LR: 0.0025

itsuncheng

#!/usr/bin/env python
# --*-- coding: utf-8 --*--
import numpy as np
import json
import matplotlib.pyplot as plt
import cv2
from random import shuffle
import os

categories_dict ={1: 'upper', 2: 'upper', 3: 'upper', 4: 'upper', 5: 'upper',

itsuncheng

friendship
beauty
beautiful
engage
engaged
engagement
love
lover
romantic
romance

itsuncheng

# Evaluation Function

def evaluate(model, test_loader, version='title', threshold=0.5):
    y_pred = []
    y_true = []

    model.eval()
    with torch.no_grad():
        for (labels, (title, title_len), (text, text_len), (titletext, titletext_len)), _ in test_loader:           
            labels = labels.to(device)

itsuncheng

train_loss_list, valid_loss_list, global_steps_list = load_metrics(destination_folder + '/metrics.pt')
plt.plot(global_steps_list, train_loss_list, label='Train')
plt.plot(global_steps_list, valid_loss_list, label='Valid')
plt.xlabel('Global Steps')
plt.ylabel('Loss')
plt.legend()
plt.show() 

itsuncheng

# Training Function

def train(model,
          optimizer,
          criterion = nn.BCELoss(),
          train_loader = train_iter,
          valid_loader = valid_iter,
          num_epochs = 5,
          eval_every = len(train_iter) // 2,
          file_path = destination_folder,

itsuncheng

# Save and Load Functions

def save_checkpoint(save_path, model, optimizer, valid_loss):

    if save_path == None:
        return
    
    state_dict = {'model_state_dict': model.state_dict(),
                  'optimizer_state_dict': optimizer.state_dict(),
                  'valid_loss': valid_loss}

itsuncheng

class LSTM(nn.Module):

    def __init__(self, dimension=128):
        super(LSTM, self).__init__()

        self.embedding = nn.Embedding(len(text_field.vocab), 300)
        self.dimension = dimension
        self.lstm = nn.LSTM(input_size=300,
                            hidden_size=dimension,
                            num_layers=1,

itsuncheng

# Fields

label_field = Field(sequential=False, use_vocab=False, batch_first=True, dtype=torch.float)
text_field = Field(tokenize='spacy', lower=True, include_lengths=True, batch_first=True)
fields = [('label', label_field), ('title', text_field), ('text', text_field), ('titletext', text_field)]

# TabularDataset

train, valid, test = TabularDataset.splits(path=source_folder, train='train.csv', validation='valid.csv', test='test.csv',
                                           format='CSV', fields=fields, skip_header=True)

itsuncheng

# Libraries

import matplotlib.pyplot as plt
import pandas as pd
import torch

# Preliminaries

from torchtext.data import Field, TabularDataset, BucketIterator