Here's my full code, just in case. The relevant part is under the comment "Setting Model Parameters With Skorch"
import numpy as np
import pandas as pd
import cv2
from PIL import Image
import os
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, models
import torchvision.transforms.functional as tf
from torch.utils.data import random_split, ConcatDataset,DataLoader
from skorch import NeuralNetClassifier
from skorch.callbacks import LRScheduler, Checkpoint, EpochScoring, EarlyStopping
from skorch.dataset import Dataset
from skorch.helper import predefined_split
import warnings
warnings.filterwarnings('ignore')
os.chdir("/cluster/qtim/users/riya/race_ukbb")
class PretrainedModel(nn.Module):
def __init__(self, output_features):
super().__init__()
model = models.resnet18(pretrained=True)
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, output_features)
self.model = model
def forward(self, x):
return self.model(x)
def train(data_dir, experiment_name,
num_classes=2, batch_size=64, num_epochs=50, lr=0.001, image_size = (224, 224)):
# USING GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
if device == 'cuda:0':
torch.cuda.empty_cache()
# TRANSFORMING TRAIN/TEST DATA
def train_loader(path):
# transforms
return tensor
def test_loader(path):
# transforms
return tensor
# APPENDING DATA TO DATA FOLDERS.
train_folder = os.path.join(data_dir, 'train')
test_folder = os.path.join(data_dir, 'test')
train_dataset = datasets.ImageFolder(train_folder, loader = train_loader)
test_dataset = datasets.ImageFolder(test_folder, loader = test_loader)
# DEFINING VALIDATION SPLIT FOR 5-FOLD CROSS VALIDATION
tl = np.round(len(train_dataset)/5) # manually done 5 fold
print(len(train_dataset))
print(tl)
generator1 = torch.Generator().manual_seed(86)
subset_arr = random_split(train_dataset, np.array([tl, tl, tl, tl+1, tl+1]).astype(int), generator1)
for i in range(len(subset_arr)):
idxs = set(np.arange(0, len(train_dataset)))
val_subset = subset_arr[i]
train_idxs = []
train_arr = subset_arr[:i] + subset_arr[i+1:] # indexing lolzzz
for j in train_arr:
train_idxs.append(j.indices) # neat
train_idxs = np.concatenate(train_idxs) # idxs preserved from train_dataset
train_subset = torch.utils.data.Subset(train_dataset, train_idxs)
f_params = f'./outputs/checkpoints/{experiment_name}/model_fold{i+1}.pt'
f_history = f'./outputs/histories/{experiment_name}/model_fold{i+1}.json'
csv_name = f'./outputs/probabilities/{experiment_name}/model_fold{i+1}.csv'
print(len(train_subset), len(val_subset))
print("Train/Test/Val datasets have been created.")
# WEIGHTED SAMPLING
val_indxs = val_subset.indices
for k in val_indxs:
idxs.discard(k) # this is now train_idxs
print(f"indxs:{len(idxs)}")
train_label_indxs = list(idxs)
train_labels = np.array(train_dataset.samples)[:,1][train_label_indxs]
labels = train_labels.astype(int)
black_weight = 1 / len(labels[labels == 0])
white_weight = 1 / len(labels[labels == 1])
sample_weights = np.array([black_weight, white_weight])
weights = sample_weights[labels]
sampler = torch.utils.data.WeightedRandomSampler(weights, len(train_subset), replacement=True)
# SETTING MODEL PARAMETERS WITH SKORCH
checkpoint = Checkpoint(monitor='valid_loss_best',
f_params=f_params,
f_history=f_history)
train_acc = EpochScoring(scoring='accuracy',
on_train=True,
name='train_acc',
lower_is_better=False)
val_roc = EpochScoring(scoring='roc_auc',
on_train=False,
name='valid-auc',
lower_is_better=False)
val_pr = EpochScoring(scoring='precision',
on_train=False,
name='valid-precision',
lower_is_better=False)
val_re = EpochScoring(scoring='recall',
on_train=False,
name='valid-recall',
lower_is_better=False)
early_stopping = EarlyStopping()
callbacks = [checkpoint, train_acc, early_stopping, val_roc, val_pr, val_re]
net = NeuralNetClassifier(PretrainedModel,
criterion=nn.CrossEntropyLoss,
lr=lr,
batch_size=batch_size,
max_epochs=num_epochs,
module__output_features=num_classes,
optimizer=optim.SGD,
optimizer__momentum=0.9,
iterator_train__num_workers=1,
iterator_train__sampler=sampler,
iterator_valid__shuffle=False,
iterator_valid__num_workers=1,
train_split=predefined_split(val_subset),
callbacks=callbacks,
device=device)
# SKORCH MODEL FITTING
print ("Model is fitting. Thank you for your patience.")
net.fit(train_subset, y=None)
print ("Model is performing inference. Results saved in probabilities folder.")
# SAVING RESULTS
img_locs = [loc for loc, _ in test_dataset.samples]
test_probs = net.predict_proba(test_dataset)
test_probs = [prob[0] for prob in test_probs]
data = {'img_loc' : img_locs, 'probability' : test_probs}
pd.DataFrame(data=data).to_csv(csv_name, index=False)
print (f"Model {i+1} is done and saved.")
print ("The code is done.") ```
I run into this error when using the auc_roc skorch callback instead of accuracy although auc_roc should be implemented (it's an available score on the sklearn scoring page). When I try other scoring callbacks, specifically precision or recall, I receive the following error message:
AttributeError: 'NeuralNetClassifier' object has no attribute 'classes_inferred_'Here's my full code, just in case. The relevant part is under the comment "Setting Model Parameters With Skorch"