I had fine tuned a bert model in pytorch and saved its checkpoints via torch.save(model.state_dict(), 'model.pt')
Now When I want to reload the model, I have to explain whole network again and reload the weights and then push to the device.
Can anyone tell me how can I save the bert model directly and load directly to use in production/deployment?
Following is the training code and you can try running there in colab itself! After training completion, you will notice in file system we have a checkpoint file. But I want to save the model itself.
LINK TO COLAB NOTEBOOK FOR SAMPLE TRAINING
Following is the current inferencing code I written.
import torch
import torch.nn as nn
from transformers import AutoModel, BertTokenizerFast
import numpy as np
import json
tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased')
device = torch.device("cpu")
class BERT_Arch(nn.Module):
def __init__(self, bert):
super(BERT_Arch, self).__init__()
self.bert = bert
# dropout layer
self.dropout = nn.Dropout(0.1)
# relu activation function
self.relu = nn.ReLU()
# dense layer 1
self.fc1 = nn.Linear(768, 512)
# dense layer 2 (Output layer)
self.fc2 = nn.Linear(512, 2)
# softmax activation function
self.softmax = nn.LogSoftmax(dim=1)
# define the forward pass
def forward(self, sent_id, mask):
# pass the inputs to the model
_, cls_hs = self.bert(sent_id, attention_mask=mask, return_dict=False)
x = self.fc1(cls_hs)
x = self.relu(x)
x = self.dropout(x)
# output layer
x = self.fc2(x)
# apply softmax activation
x = self.softmax(x)
return x
bert = AutoModel.from_pretrained('bert-base-uncased')
model = BERT_Arch(bert)
path = './models/saved_weights_new_data.pt'
model.load_state_dict(torch.load(path, map_location=device))
model.to(device)
def inference(comment):
tokens_test = tokenizer.batch_encode_plus(
list([comment]),
max_length=75,
pad_to_max_length=True,
truncation=True,
return_token_type_ids=False
)
test_seq = torch.tensor(tokens_test['input_ids'])
test_mask = torch.tensor(tokens_test['attention_mask'])
predictions = model(test_seq.to(device), test_mask.to(device))
predictions = predictions.detach().cpu().numpy()
predictions = np.argmax(predictions, axis=1)
return predictions
I simply want to save a model from this notebook in a way such that I can use it for inferencing anywhere.
Just save your model using model.save_pretrained, here is an example:
model.save_pretrained("<path_to_dummy_folder>")
You can download the model from colab, save it on your gdrive or at any other location of your choice. While doing inference, you can just give path to this model (you may have to upload it) and start with inference.
To load the model
model = AutoModel.from_pretrained("<path_to_saved_pretrained_model>")
#Note: Instead of AutoModel class, you may use the task specific class as well.
I am trying to understand deep-learning with pytorch. I read the pytorch tutorial: https://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html, and its written:
''torch.nn only supports mini-batches. The entire torch.nn package only supports inputs that are a mini-batch of samples, and not a single sample.
For example, nn.Conv2d will take in a 4D Tensor of nSamples x nChannels x Height x Width.
If you have a single sample, just use input.unsqueeze(0) to add a fake batch dimension.''
I am not sure to understand what it means.
Indeed, I have made a simple feed-forward neural network (cf below code), on which I used a really small dataset (the idea is to learn how it works without mini-batches first, not really to have anything useful), and hence don't need to use mini-batches. Hence, I introduce directly all the sample at each epochs. If I understand it correctly, I should add 'train_data = train_data.unsqueeze(0) '. But I am not sure where, as it seems to change the data size to 1. Also, it works without adding this line so why should I really use it?
Any help would be highly appreciated!
import torch
import torchvision
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import pandas as pd
import os
import numpy as np
# Download data
#...
# Construct network
len_input = len(data[0])
len_output = nbr_class
print('There is %d classes used for classification'%nbr_class)
#defining a new class: Net, that extended nn.Module
#setup the “skeleton” of our network architecture
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
#creation of fully connected. A fully connected neural network layer is represented by the nn.Linear object,
#with the first argument in the definition being the number of nodes in layer l and the next argument being
#the number of nodes in layer l+1
self.fc1 = nn.Linear(len_input, 200)
self.fc2 = nn.Linear(200, 200)
self.fc3 = nn.Linear(200, len_output)
def forward(self, x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return F.log_softmax(x)
# Create initial network
epochs = 3000
model = Net()
criterion = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
# Train & test network
def train(data, target, epoch):
model.train() # set the model in "training mode"
# run the main training loop
#no need batch size as small number of sample! like this the process is more exact
#zero our gradients before calling .backward() which is necessary for new sum of gradients
optimizer.zero_grad()
target_pred = model(data)
loss = criterion(target_pred, target)
#Propagate the gradients back through the network
loss.backward()
#update the weights
#tell our optimizer to “step”, meaning that the weights will be updated using the calculated gradients
#according to our rule. perform model parameter update (update weights)
optimizer.step()
# for graphing puposes
loss_array.append(loss.data[0])
if epoch in list(range(0,20000,100)):
print('Train Epoch: {} \tLoss: {:.6f}'.format(epoch, loss.data[0]))
def test(epoch, test_data, test_target):
#eval mode to turn Dropout and BatchNorm off
model.eval()
test_loss = 0
correct = 0
test_target_pred = model(test_data)
criterion = nn.NLLLoss()
# sum up batch loss
test_loss += criterion(test_target_pred, test_target).data[0]
pred = test_target_pred.data.max(1)[1] # get the index of the max log-probability
correct += pred.eq(test_target.data).sum()
if epoch in list(range(0,20000,100)):
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_target), 100. * correct / len(test_target)))
if __name__ == '__main__':
for epoch in range(epochs):
train(data = train_data, target=train_target, epoch=epoch)
test(epoch, test_data, test_target)
I’m trying to train a captcha recognition model. Model details are resnet pretrained CNN layers + Bidirectional LSTM + Fully Connected. It reached 90% sequence accuracy on captcha generated by python library captcha. The problem is that these generated captcha seems to have similary location of each character. When I randomly add spaces between characters, the model does not work any more. So I wonder is LSTM learning segmentation during learning? Then I try to use CTC loss. At first, loss goes down pretty quick. But it stays at about 16 without significant drop later. I tried different layers of LSTM, different number of units. 2 Layers of LSTM reach lower loss, but still not converging. 3 layers are just like 2 layers. The loss curve:
#encoding:utf8
import os
import sys
import torch
import warpctc_pytorch
import traceback
import torchvision
from torch import nn, autograd, FloatTensor, optim
from torch.nn import functional as F
from torch.utils.data import DataLoader
from torch.optim.lr_scheduler import MultiStepLR
from tensorboard import SummaryWriter
from pprint import pprint
from net.utils import decoder
from logging import getLogger, StreamHandler
logger = getLogger(__name__)
handler = StreamHandler(sys.stdout)
logger.addHandler(handler)
from dataset_util.utils import id_to_character
from dataset_util.transform import rescale, normalizer
from config.config import MAX_CAPTCHA_LENGTH, TENSORBOARD_LOG_PATH, MODEL_PATH
class CNN_RNN(nn.Module):
def __init__(self, lstm_bidirectional=True, use_ctc=True, *args, **kwargs):
super(CNN_RNN, self).__init__(*args, **kwargs)
model_conv = torchvision.models.resnet18(pretrained=True)
for param in model_conv.parameters():
param.requires_grad = False
modules = list(model_conv.children())[:-1] # delete the last fc layer.
for param in modules[8].parameters():
param.requires_grad = True
self.resnet = nn.Sequential(*modules) # CNN with fixed parameters from resnet as feature extractor
self.lstm_input_size = 512 * 2 * 2
self.lstm_hidden_state_size = 512
self.lstm_num_layers = 2
self.chracter_space_length = 64
self._lstm_bidirectional = lstm_bidirectional
self._use_ctc = use_ctc
if use_ctc:
self._max_captcha_length = int(MAX_CAPTCHA_LENGTH * 2)
else:
self._max_captcha_length = MAX_CAPTCHA_LENGTH
if lstm_bidirectional:
self.lstm_hidden_state_size = self.lstm_hidden_state_size * 2 # so that hidden size for one direction in bidirection lstm is the same as vanilla lstm
self.lstm = self.lstm = nn.LSTM(self.lstm_input_size, self.lstm_hidden_state_size // 2, dropout=0.5, bidirectional=True, num_layers=self.lstm_num_layers)
else:
self.lstm = nn.LSTM(self.lstm_input_size, self.lstm_hidden_state_size, dropout=0.5, bidirectional=False, num_layers=self.lstm_num_layers) # dropout doen't work for one layer lstm
self.ouput_to_tag = nn.Linear(self.lstm_hidden_state_size, self.chracter_space_length)
self.tensorboard_writer = SummaryWriter(TENSORBOARD_LOG_PATH)
# self.dropout_lstm = nn.Dropout()
def init_hidden_status(self, batch_size):
if self._lstm_bidirectional:
self.hidden = (autograd.Variable(torch.zeros((self.lstm_num_layers * 2, batch_size, self.lstm_hidden_state_size // 2))),
autograd.Variable(torch.zeros((self.lstm_num_layers * 2, batch_size, self.lstm_hidden_state_size // 2)))) # number of layers, batch size, hidden dimention
else:
self.hidden = (autograd.Variable(torch.zeros((self.lstm_num_layers, batch_size, self.lstm_hidden_state_size))),
autograd.Variable(torch.zeros((self.lstm_num_layers, batch_size, self.lstm_hidden_state_size)))) # number of layers, batch size, hidden dimention
def forward(self, image):
'''
:param image: # batch_size, CHANNEL, HEIGHT, WIDTH
:return:
'''
features = self.resnet(image) # [batch_size, 512, 2, 2]
batch_size = image.shape[0]
features = [features.view(batch_size, -1) for i in range(self._max_captcha_length)]
features = torch.stack(features)
self.init_hidden_status(batch_size)
output, hidden = self.lstm(features, self.hidden)
# output = self.dropout_lstm(output)
tag_space = self.ouput_to_tag(output.view(-1, output.size(2))) # [MAX_CAPTCHA_LENGTH * BATCH_SIZE, CHARACTER_SPACE_LENGTH]
tag_space = tag_space.view(self._max_captcha_length, batch_size, -1)
if not self._use_ctc:
tag_score = F.log_softmax(tag_space, dim=2) # [MAX_CAPTCHA_LENGTH, BATCH_SIZE, CHARACTER_SPACE_LENGTH]
else:
tag_score = tag_space
return tag_score
def train_net(self, data_loader, eval_data_loader=None, learning_rate=0.008, epoch_num=400):
try:
if self._use_ctc:
loss_function = warpctc_pytorch.warp_ctc.CTCLoss()
else:
loss_function = nn.NLLLoss()
# optimizer = optim.SGD(filter(lambda p: p.requires_grad, self.parameters()), momentum=0.9, lr=learning_rate)
# optimizer = MultiStepLR(optimizer, milestones=[10,15], gamma=0.5)
# optimizer = optim.Adadelta(filter(lambda p: p.requires_grad, self.parameters()))
optimizer = optim.Adam(filter(lambda p: p.requires_grad, self.parameters()))
self.tensorboard_writer.add_scalar("learning_rate", learning_rate)
tensorbard_global_step=0
if os.path.exists(os.path.join(TENSORBOARD_LOG_PATH, "resume_step")):
with open(os.path.join(TENSORBOARD_LOG_PATH, "resume_step"), "r") as file_handler:
tensorbard_global_step = int(file_handler.read()) + 1
for epoch_index, epoch in enumerate(range(epoch_num)):
for index, sample in enumerate(data_loader):
optimizer.zero_grad()
input_image = autograd.Variable(sample["image"]) # batch_size, 3, 255, 255
tag_score = self.forward(input_image)
if self._use_ctc:
tag_score, target, tag_score_sizes, target_sizes = self._loss_preprocess_ctc(tag_score, sample)
loss = loss_function(tag_score, target, tag_score_sizes, target_sizes)
loss = loss / tag_score.size(1)
else:
target = sample["padded_label_idx"]
tag_score, target = self._loss_preprocess(tag_score, target)
loss = loss_function(tag_score, target)
print("Training loss: {}".format(float(loss)))
self.tensorboard_writer.add_scalar("training_loss", float(loss), tensorbard_global_step)
loss.backward()
optimizer.step()
if index % 250 == 0:
print(u"Processing batch: {} of {}, epoch: {}".format(index, len(data_loader), epoch_index))
self.evaluate(eval_data_loader, loss_function, tensorbard_global_step)
tensorbard_global_step += 1
self.save_model(MODEL_PATH + "_epoch_{}".format(epoch_index))
except KeyboardInterrupt:
print("Exit for KeyboardInterrupt, save model")
self.save_model(MODEL_PATH)
with open(os.path.join(TENSORBOARD_LOG_PATH, "resume_step"), "w") as file_handler:
file_handler.write(str(tensorbard_global_step))
except Exception as excp:
logger.error(str(excp))
logger.error(traceback.format_exc())
def predict(self, image):
# TODO ctc version
'''
:param image: [batch_size, channel, height, width]
:return:
'''
tag_score = self.forward(image)
# TODO ctc
# if self._use_ctc:
# tag_score = F.softmax(tag_score, dim=-1)
# decoder.decode(tag_score)
confidence_log_probability, indexes = tag_score.max(2)
predicted_labels = []
for batch_index in range(indexes.size(1)):
label = ""
for character_index in range(self._max_captcha_length):
if int(indexes[character_index, batch_index]) != 1:
label += id_to_character[int(indexes[character_index, batch_index])]
predicted_labels.append(label)
return predicted_labels, tag_score
def predict_pil_image(self, pil_image):
try:
self.eval()
processed_image = normalizer(rescale({"image": pil_image}))["image"].view(1, 3, 255, 255)
result, tag_score = self.predict(processed_image)
self.train()
except Exception as excp:
logger.error(str(excp))
logger.error(traceback.format_exc())
return [""], None
return result, tag_score
def evaluate(self, eval_dataloader, loss_function, step=0):
total = 0
sequence_correct = 0
character_correct = 0
character_total = 0
loss_total = 0
batch_size = eval_data_loader.batch_size
true_predicted = {}
self.eval()
for sample in eval_dataloader:
total += batch_size
input_images = sample["image"]
predicted_labels, tag_score = self.predict(input_images)
for predicted, true_label in zip(predicted_labels, sample["label"]):
if predicted == true_label: # dataloader is making label a list, use batch_size=1
sequence_correct += 1
for index, true_character in enumerate(true_label):
character_total += 1
if index < len(predicted) and predicted[index] == true_character:
character_correct += 1
true_predicted[true_label] = predicted
if self._use_ctc:
tag_score, target, tag_score_sizes, target_sizes = self._loss_preprocess_ctc(tag_score, sample)
loss_total += float(loss_function(tag_score, target, tag_score_sizes, target_sizes) / batch_size)
else:
tag_score, target = self._loss_preprocess(tag_score, sample["padded_label_idx"])
loss_total += float(loss_function(tag_score, target)) # averaged over batch index
print("True captcha to predicted captcha: ")
pprint(true_predicted)
self.tensorboard_writer.add_text("eval_ture_to_predicted", str(true_predicted), global_step=step)
accuracy = float(sequence_correct) / total
avg_loss = float(loss_total) / (total / batch_size)
character_accuracy = float(character_correct) / character_total
self.tensorboard_writer.add_scalar("eval_sequence_accuracy", accuracy, global_step=step)
self.tensorboard_writer.add_scalar("eval_character_accuracy", character_accuracy, global_step=step)
self.tensorboard_writer.add_scalar("eval_loss", avg_loss, global_step=step)
self.zero_grad()
self.train()
def _loss_preprocess(self, tag_score, target):
'''
:param tag_score: value return by self.forward
:param target: sample["padded_label_idx"]
:return: (processed_tag_score, processed_target) ready for NLLoss function
'''
target = target.transpose(0, 1)
target = target.contiguous()
target = target.view(target.size(0) * target.size(1))
tag_score = tag_score.view(-1, self.chracter_space_length)
return tag_score, target
def _loss_preprocess_ctc(self, tag_score, sample):
target_2d = [
[int(ele) for ele in sample["padded_label_idx"][row, :] if int(ele) != 0 and int(ele) != 1]
for row in range(sample["padded_label_idx"].size(0))]
target = []
for ele in target_2d:
target.extend(ele)
target = autograd.Variable(torch.IntTensor(target))
# tag_score = F.softmax(F.sigmoid(tag_score), dim=-1)
tag_score_sizes = autograd.Variable(torch.IntTensor([self._max_captcha_length] * tag_score.size(1)))
target_sizes = autograd.Variable(sample["captcha_length"].int())
return tag_score, target, tag_score_sizes, target_sizes
# def visualize_graph(self, dataset):
# '''Since pytorch use dynamic graph, an input is required to visualize graph in tensorboard'''
# # warning: Do not run this, the graph is too large to visualize...
# sample = dataset[0]
# input_image = autograd.Variable(sample["image"].view(1, 3, 255, 255))
# tag_score = self.forward(input_image)
# self.tensorboard_writer.add_graph(self, tag_score)
def save_model(self, model_path):
self.tensorboard_writer.close()
self.tensorboard_writer = None # can't be pickled
torch.save(self, model_path)
self.tensorboard_writer = SummaryWriter(TENSORBOARD_LOG_PATH)
#classmethod
def load_model(cls, model_path=MODEL_PATH, *args, **kwargs):
net = cls(*args, **kwargs)
if os.path.exists(model_path):
model = torch.load(model_path)
if model:
model.tensorboard_writer = SummaryWriter(TENSORBOARD_LOG_PATH)
net = model
return net
def __del__(self):
if self.tensorboard_writer:
self.tensorboard_writer.close()
if __name__ == "__main__":
from dataset_util.dataset import dataset, eval_dataset
data_loader = DataLoader(dataset, batch_size=2, shuffle=True)
eval_data_loader = DataLoader(eval_dataset, batch_size=2, shuffle=True)
net = CNN_RNN.load_model()
net.train_net(data_loader, eval_data_loader=eval_data_loader)
# net.predict(dataset[0]["image"].view(1, 3, 255, 255))
# predict_pil_image test code
# from config.config import IMAGE_PATHS
# import glob
# from PIL import Image
#
# image_paths = glob.glob(os.path.join(IMAGE_PATHS.get("EVAL"), "*.png"))
# for image_path in image_paths:
# pil_image = Image.open(image_path)
# predicted, score = net.predict_pil_image(pil_image)
# print("True value: {}, predicted: {}".format(os.path.split(image_path)[1], predicted))
print("Done")
The above codes are main part. If you need other components that makes it running, leave a comment. Got stuck here for quite long. Any advice for training crnn + ctc is appreciated.
I've been training with ctc loss and encountered the same problem. I know this is a rather late answer but hopefully it'll help someone else who's researching on this. After trial and error and a lot of research there are a few things that's worth knowing when it comes to training with ctc (if your model is set up correctly):
The quickest way for the model to lower cost is to predict only blanks. This is noted in a few papers and blogs: see http://www.tbluche.com/ctc_and_blank.html
The model learns to predict only blanks first, then it starts picking up on the error signal in regards to the correct underlying labels. This is also explained in the above link. In practice, I noticed that my model starts to learn the real underlying labels/targets after a couple hundred epochs and the loss starts decreasing dramatically again. Similar to what is shown for the toy example here: https://thomasmesnard.github.io/files/CTC_Poster_Mesnard_Auvolat.pdf
These parameters have a great impact on whether your model converges or not - learning rate, batch size and epoch number.
You have a few questions, so I will try to answer them one by one.
First, why does adding spaces to the captcha break the model?
A neural network learns to deal with the data it is trained on. If you change the distribution of the data (by for example adding spaces between characters) there is no guarantee that the network will generalize. As you hint at in your question. It is possible that the captchas you train on always have the characters in the same positions, or at the same distance from one another, thus your model learns that and learns to exploit this by looking in those positions. If you want your network to generalize a specific scenario, you should explicitly train on that scenario. So in your case, you should add random spaces also during training.
Second, why does the loss not go below 16?
Clearly, from the fact that your training loss is also stalled at 16 (like your validation loss), the problem is that your model simply doesn't have the capacity to deal with the complexity of the problem. In other words, your model is underfitting. You had the correct reflex to try to increase the capacity of your network. You tried to increase the capacity of the LSTM and it didn't help. Thus, the next logical step is that the convolution part of your network is not powerful enough. So here are a few things that you might want to try, from most likely to succeed in my opinion to least likely:
Make convnet trainable: I notice that you are using a pretrained convnet and that you are not fine-tuning the weights of that convnet. That could be a problem. Whatever your convnet was trained on, it might not develop the required features to deal with captchas. You should try learning the weights of the convnet too, in order to develop useful features for captchas.
Use deeper convnet: This is the naive thing to do. Your convnet doesn't have good enough features, try a more powerful deeper one. (But you should definitely use this only after you've made the convnet trainable).
From my experience, training RNN model with CTC loss is not an EASY task. The model may not converge at all if the training is not carefully setup-ed. Here are my suggestions:
Check the CTC loss output along training. For a model would converge, the CTC loss at each batch fluctuates notably. If you observed that the CTC loss shrinks almost monotonically to a stable value, then the model is most likely stuck at a local minima
Use short samples to pretrain your model. Though we have advanced RNN strucures like LSTM and GRU, it's still hard to back-propagate the RNN for long steps.
Enlarge sample variety. You can even add artificial samples to help your model escape from local minima.
F.Y.I., we've just open-sourced a new deep learning framework Dandelion which has built-in CTC objective, and interface pretty much like pytorch. You can try your model with Dandelion and compare it with your current implementation.
I have been following the ants and bees transfer learning tutorial from the official PyTorch Docs (http://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html). I am trying to finetune a VGG19 model by changing the final layer to predict one of two classes. I am able to modify the last fc layer using the following code.
But I get an error when executing the train_model function. The error is “size mismatch at /opt/conda/conda-bld/pytorch_1513368888240/work/torch/lib/THC/generic/THCTensorMathBlas.cu:243”. Any idea what the issue is ?
model_conv = torchvision.models.vgg19(pretrained=True)
for param in model_conv.parameters():
param.requires_grad = False
model_conv = nn.Sequential(*list(model_conv.classifier.children())[:-1] +
[nn.Linear(in_features=4096, out_features=2)])
if use_gpu:
model_conv = model_conv.cuda()
criterion = nn.CrossEntropyLoss()
optimizer_conv = optim.SGD(model_conv._modules['6'].parameters(), lr=0.001, momentum=0.9)
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)
model_conv = train_model(model_conv, criterion, optimizer_conv, exp_lr_scheduler, num_epochs=25)
When you are defining your model you are just considering the classifier which consists on the fully connected part of the network only. Then, when feeding the 224*224*3 image to the model it tries to "go through" a linear layer with 25K features as the input. To solve it you just need to add the convolutional part before, to do so redefine the model like this:
class newModel(nn.Module):
def __init__(self, old_model):
super(newModel, self).__init__()
self.features = old_model.features
self.classifier = nn.Sequential(*list(old_model.classifier.children())[:-1] +
[nn.Linear(in_features=4096, out_features=2)])
def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), -1)
x = self.classifier(x)
return x
model_conv = newModel(model_conv)
Now you just also tell the parameters to optimize, if you just want to train the last layer (the one that is newly added) do :
optimizer_conv = optim.SGD(model_conv.classifier._modules['6'].parameters(), lr=0.001, momentum=0.9)
The rest of the code remains the same.
Hope it helps!