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 main():
cnn = CNN()
cnn.eval()
cnn.load_state_dict(torch.load('model/1500_model.pkl'))
print("load cnn net.")
predict_dataloader = my_dataset.get_predict_data_loader()
for i, (images, labels) in enumerate(predict_dataloader):
image = images
vimage = Variable(image)
predict_label = cnn(vimage)
c0 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 0:captcha_setting.ALL_CHAR_SET_LEN].data.numpy())]
c1 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, captcha_setting.ALL_CHAR_SET_LEN:2 *
captcha_setting.ALL_CHAR_SET_LEN].data.numpy())]
c2 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 2 * captcha_setting.ALL_CHAR_SET_LEN:3 *
captcha_setting.ALL_CHAR_SET_LEN].data.numpy())]
c3 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 3 * captcha_setting.ALL_CHAR_SET_LEN:4 *
captcha_setting.ALL_CHAR_SET_LEN].data.numpy())]
c = '%s%s%s%s' % (c0, c1, c2, c3)
return c
def main():
img = Image.open(IMAGEPATH)
transed_img = trans(img)
n_channels = 3
n_classes = 5
test_model = CNN(n_channels, n_classes)
model_dict = test_model.load_state_dict(torch.load(MODELPATH))
transed_img = transed_img.view(1, 3, DROPSIZE, DROPSIZE)
outputs = test_model(transed_img)
_, predicted = torch.max(outputs.data, 1)
# loss:
criterion = nn.CrossEntropyLoss()
loss = criterion(outputs, torch.from_numpy(np.array([2])))
# if loss >= 1:
# print("Unknown")
# return
if predicted == 0:
print("Dorm")
if predicted == 1:
print("Gym")
if predicted == 2:
print("Library")
if predicted == 3:
print("Market")
if predicted == 4:
print("Teaching Building 1")
def main():
cnn = CNN()
cnn.eval()
cnn.load_state_dict(torch.load('model/1500_model.pkl'))
print("load cnn net.")
test_dataloader = my_dataset.get_test_data_loader()
correct = 0
total = 0
error = []
true = []
for i, (images, labels) in enumerate(test_dataloader):
image = images
vimage = Variable(image)
predict_label = cnn(vimage)
c0 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 0:captcha_setting.ALL_CHAR_SET_LEN].data.numpy())]
c1 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, captcha_setting.ALL_CHAR_SET_LEN:2 *
captcha_setting.ALL_CHAR_SET_LEN].data.numpy())]
c2 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 2 * captcha_setting.ALL_CHAR_SET_LEN:3 *
captcha_setting.ALL_CHAR_SET_LEN].data.numpy())]
c3 = captcha_setting.ALL_CHAR_SET[np.argmax(
predict_label[0, 3 * captcha_setting.ALL_CHAR_SET_LEN:4 *
captcha_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])
print("true_label: ", true_label)
print("predict_lable: ", predict_label, "\n")
total += labels.size(0)
if (predict_label == true_label):
correct += 1
else:
error.append(predict_label)
true.append(true_label)
if (total % 200 == 0):
print('测试集数量：%d， 准确率 : %f %%' % (total, 100 * correct / total))
print('测试集数量：%d， 准确率 : %f %%' % (total, 100 * correct / total))
print('预测错误例子：\n')
print('正确字符：', true)
print('错误字符：', error)
def validate_model(args):
if torch.cuda.is_available():
device = torch.device("cuda")
else:
device = torch.device("cpu")
criterion = CrossEntropyLoss()
mode = args.mode
if mode in ['MC','LMC','MLMC']:
validation_loader = torch.utils.data.DataLoader(
UrbanSound8KDataset('UrbanSound8K_test.pkl', mode),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.worker_count,
pin_memory=True
)
model = CNN(height=85, width=41, channels=1, class_count=10, dropout=0.5, mode = mode)
checkpoint = torch.load(args.checkpoint, map_location = device)
model.load_state_dict(checkpoint['model'])
print(f"Validating {mode} model with parameters trained for {checkpoint['epoch']} epochs.")
loss, accuracy, class_accuracies = validate_single(model, validation_loader, criterion, device)
print(f"accuracy: {accuracy * 100:2.2f}")
print_class_accuracies(class_accuracies)
elif mode == 'TSCNN':
loader_LMC = torch.utils.data.DataLoader(
UrbanSound8KDataset('UrbanSound8K_test.pkl', 'LMC'),
batch_size=args.batch_size,
shuffle=False,
num_workers=args.worker_count,
pin_memory=True
)
loader_MC = torch.utils.data.DataLoader(
UrbanSound8KDataset('UrbanSound8K_test.pkl', 'MC'),
batch_size=args.batch_size,
shuffle=False,
num_workers=args.worker_count,
pin_memory=True
)
model1 = CNN(height=85, width=41, channels=1, class_count=10, dropout=0.5, mode = 'LMC')
model2 = CNN(height=85, width=41, channels=1, class_count=10, dropout=0.5, mode = 'MC')
checkpoint1 = torch.load(args.checkpoint, map_location = device)
model1.load_state_dict(checkpoint1['model'])
checkpoint2 = torch.load(args.checkpoint2, map_location = device)
model2.load_state_dict(checkpoint2['model'])
print(f"Validating {mode} model with parameters trained for {checkpoint1['epoch']} and {checkpoint2['epoch']} epochs.")
accuracy, class_accuracies = validate_double(model1, model2, loader_LMC, loader_MC, criterion, device)
print(f"accuracy: {accuracy * 100:2.2f}")
print_class_accuracies(class_accuracies)
else:
print('Please provide a valid argument.')
def recognize(model_name='model.pk'):
cnn = CNN()
cnn.eval()
cnn.load_state_dict(torch.load(model_name))
# print(load cnn net.)
# NUM_LEN = len(setting.NUMBER)
captcha_dataloader = dataset.get_captcha_data_loader()
code = ''
images = {}
for image, label in captcha_dataloader:
images[label] = image
images = [images[key] for key in sorted(images)]
for image in images:
vimage = Variable(image)
predict_label = cnn(vimage)
for i in range(setting.MAX_CAPTCHA):
code += setting.ALL_CHAR_SET[np.argmax(
predict_label[0, i * setting.ALL_CHAR_SET_LEN:(i + 1) *
setting.ALL_CHAR_SET_LEN].data.numpy())]
return code
to_train = True
cnn_model = CNN(vocab_size, embedding_size, n_filters, filter_sizes,
pool_size, hidden_size, num_classes, dropout_keep_prob)
# optimization algorithm
optimizer = torch.optim.Adam(cnn_model.parameters(), lr=lr)
# train and evaluation
if (to_train):
# train and evaluation
run_train(num_epochs, cnn_model, train_iterator, valid_iterator,
optimizer, loss_func, model_type)
# load weights
cnn_model.load_state_dict(
torch.load(os.path.join(path, "saved_weights_CNN.pt")))
# predict
test_loss, test_acc = evaluate(cnn_model, test_iterator, loss_func)
print(f'Test Loss: {test_loss:.3f} | Test Acc: {test_acc * 100:.2f}%')
if (model_type == "LSTM"):
num_hidden_nodes = 93
hidden_dim2 = 128
num_layers = 2 # LSTM layers
bi_directional = False
num_epochs = 7
to_train = True
pad_index = Text.vocab.stoi[Text.pad_token]
