def main():
# Load net
cnn = CNN()
loss_func = nn.MultiLabelSoftMarginLoss()
optimizer = optim.Adam(cnn.parameters(), lr=learning_rate)
if torch.cuda.is_available():
cnn.cuda()
loss_func.cuda()
# Load data
train_dataloader = dataset.get_train_data_loader()
test_dataloader = dataset.get_test_data_loader()
# Train model
for epoch in range(num_epochs):
cnn.train()
for i, (images, labels) in enumerate(train_dataloader):
images = Variable(images)
labels = Variable(labels.long())
if torch.cuda.is_available():
images = images.cuda()
labels = labels.cuda()
predict_labels = cnn(images)
loss = loss_func(predict_labels, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i + 1) % 100 == 0:
print("epoch:", epoch, "step:", i, "loss:", loss.item())
# Save and test model
if (epoch + 1) % 10 == 0:
filename = "model" + str(epoch + 1) + ".pkl"
torch.save(cnn.state_dict(), filename)
cnn.eval()
correct = 0
total = 0
for (image, label) in test_dataloader:
vimage = Variable(image)
if torch.cuda.is_available():
vimage = vimage.cuda()
output = cnn(vimage)
predict_label = ""
for k in range(4):
predict_label += config.CHAR_SET[np.argmax(
output[0, k * config.CHAR_SET_LEN:(k + 1) *
config.CHAR_SET_LEN].data.cpu().numpy())]
true_label = one_hot.vec2text(label.numpy()[0])
total += label.size(0)
if predict_label == true_label:
correct += 1
if total % 200 == 0:
print(
'Test Accuracy of the model on the %d test images: %f %%'
% (total, 100 * correct / total))
print('Test Accuracy of the model on the %d test images: %f %%' %
(total, 100 * correct / total))
print("save and test model...")
torch.save(cnn.state_dict(), "./model.pkl") # current is model.pkl
print("save last model")
def run_predict_one_fold(fold: int):
test_data_loader = get_test_data_loader()
model = load_trained_model(f"checkpoint-f{fold}.pt")
results = []
for images, image_ids in test_data_loader:
images = list(image.to(config.DEVICE) for image in images)
outputs = model(images)
for i, image in enumerate(images):
boxes = outputs[i]['boxes'].cpu().detach().numpy()
scores = outputs[i]['scores'].cpu().detach().numpy()
boxes = boxes[scores > config.SCORE_THRESHOLD]
scores = scores[scores > config.SCORE_THRESHOLD]
image_id = image_ids[i]
result = {
'image_id': image_id,
'PredictionString': format_prediction_string(boxes, scores)
}
results.append(result)
save_labeled_image(image, boxes, image_id)
test_df = pd.DataFrame(results, columns=['image_id', 'PredictionString'])
test_df.to_csv('submission.csv', index=False)
def test(model_name='model.pkl'):
cnn = CNN()
cnn.eval()
cnn.load_state_dict(torch.load(model_name))
print('load cnn net.')
test_dataloader = dataset.get_test_data_loader()
correct = 0
total = 0
for i, (images, labels) in enumerate(test_dataloader):
image = images
vimage = Variable(image)
predict_label = cnn(vimage)
chars = ''
for i in range(setting.MAX_CAPTCHA):
chars += setting.ALL_CHAR_SET[np.argmax(
predict_label[0, i * setting.ALL_CHAR_SET_LEN:(i + 1) *
setting.ALL_CHAR_SET_LEN].data.numpy())]
predict_label = chars
true_label = one_hot.decode(labels.numpy()[0])
total += labels.size(0)
if (predict_label == true_label):
correct += 1
else:
print('Predict:' + predict_label)
print('Real :' + true_label)
if (total % 200 == 0):
print('Test Accuracy of the model on the %d test images: %f %%' %
(total, 100 * correct / total))
print('Test Accuracy of the model on the %d test images: %f %%' %
(total, 100 * correct / total))
def run_predict():
test_data_loader = get_test_data_loader()
for fold in range(0, config.NUM_FOLDS):
models.append(load_trained_model(f"checkpoint-f{fold}.pt"))
results = []
for images, image_ids in test_data_loader:
predictions = make_ensemble_predictions(images, models)
for i, image in enumerate(images):
boxes, scores, labels = run_wbf(predictions, image_index=i)
boxes = boxes.astype(np.int32)
image_id = image_ids[i]
result = {
'image_id': image_id,
'PredictionString': format_prediction_string(boxes, scores)
}
results.append(result)
save_labeled_image(image, boxes, image_id)
test_df = pd.DataFrame(results, columns=['image_id', 'PredictionString'])
test_df.to_csv('submission.csv', index=False)
def main():
cnn = CNN()
cnn.eval()
cnn.load_state_dict(torch.load('model.pkl'))
print("load cnn net.")
test_dataloader = dataset.get_test_data_loader()
correct = 0
total = 0
for i, (images, labels) in enumerate(test_dataloader):
image = images
vimage = Variable(image)
predict_label = cnn(vimage)
c0 = setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 0:setting.ALL_CHAR_SET_LEN].data.numpy())]
c1 = setting.ALL_CHAR_SET[np.argmax(
predict_label[0, setting.ALL_CHAR_SET_LEN:2 *
setting.ALL_CHAR_SET_LEN].data.numpy())]
c2 = setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 2 * setting.ALL_CHAR_SET_LEN:3 *
setting.ALL_CHAR_SET_LEN].data.numpy())]
c3 = setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 3 * setting.ALL_CHAR_SET_LEN:4 *
setting.ALL_CHAR_SET_LEN].data.numpy())]
predict_label = '%s%s%s%s' % (c0, c1, c2, c3)
true_label = one_hot_encoding.decode(labels.numpy()[0])
total += labels.size(0)
if (predict_label == true_label):
correct += 1
if (total % 200 == 0):
print('Test Accuracy of the model on the %d test images: %f %%' %
(total, 100 * correct / total))
print('Test Accuracy of the model on the %d test images: %f %%' %
(total, 100 * correct / total))
return correct / total