File size: 22,043 Bytes
8a9be66 6282b8b 8a9be66 6282b8b 8a9be66 6282b8b 8a9be66 6282b8b 8a9be66 6282b8b 8fe0c4a 6282b8b 6e158d7 8fe0c4a f001673 8270859 8fe0c4a 6282b8b 8fe0c4a 6282b8b 8fe0c4a 6282b8b 8fe0c4a 6282b8b 8fe0c4a 6282b8b 8fe0c4a 6282b8b 8fe0c4a 6282b8b 8fe0c4a 6282b8b 8fe0c4a 6282b8b b722033 ad31de9 be7b4da 4a865a4 be7b4da 6c4f924 be7b4da 4a865a4 8270859 ad31de9 6e158d7 ad31de9 4a865a4 ad31de9 f001673 ad31de9 be7b4da ad31de9 b722033 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 |
# # %%writefile app.py
# import streamlit as st
# import matplotlib.pyplot as plt
# import torch
# from transformers import AutoTokenizer, DataCollatorWithPadding, AutoModelForSequenceClassification, AdamW
# from datasets import load_dataset, Dataset
# from evaluate import load as load_metric
# from torch.utils.data import DataLoader
# import pandas as pd
# import random
# from collections import OrderedDict
# import flwr as fl
# DEVICE = torch.device("cpu")
# def load_data(dataset_name, train_size=20, test_size=20, num_clients=2):
# raw_datasets = load_dataset(dataset_name)
# raw_datasets = raw_datasets.shuffle(seed=42)
# del raw_datasets["unsupervised"]
# tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
# def tokenize_function(examples):
# return tokenizer(examples["text"], truncation=True)
# tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)
# tokenized_datasets = tokenized_datasets.remove_columns("text")
# tokenized_datasets = tokenized_datasets.rename_column("label", "labels")
# train_datasets = []
# test_datasets = []
# for _ in range(num_clients):
# train_dataset = tokenized_datasets["train"].select(random.sample(range(len(tokenized_datasets["train"])), train_size))
# test_dataset = tokenized_datasets["test"].select(random.sample(range(len(tokenized_datasets["test"])), test_size))
# train_datasets.append(train_dataset)
# test_datasets.append(test_dataset)
# data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
# return train_datasets, test_datasets, data_collator
# def read_log_file():
# with open("./log.txt", "r") as file:
# return file.read()
# def train(net, trainloader, epochs):
# optimizer = AdamW(net.parameters(), lr=5e-5)
# net.train()
# for _ in range(epochs):
# for batch in trainloader:
# batch = {k: v.to(DEVICE) for k, v in batch.items()}
# outputs = net(**batch)
# loss = outputs.loss
# loss.backward()
# optimizer.step()
# optimizer.zero_grad()
# def test(net, testloader):
# metric = load_metric("accuracy")
# net.eval()
# loss = 0
# for batch in testloader:
# batch = {k: v.to(DEVICE) for k, v in batch.items()}
# with torch.no_grad():
# outputs = net(**batch)
# logits = outputs.logits
# loss += outputs.loss.item()
# predictions = torch.argmax(logits, dim=-1)
# metric.add_batch(predictions=predictions, references=batch["labels"])
# loss /= len(testloader)
# accuracy = metric.compute()["accuracy"]
# return loss, accuracy
# class CustomClient(fl.client.NumPyClient):
# def __init__(self, net, trainloader, testloader, client_id):
# self.net = net
# self.trainloader = trainloader
# self.testloader = testloader
# self.client_id = client_id
# self.losses = []
# self.accuracies = []
# def get_parameters(self, config):
# return [val.cpu().numpy() for _, val in self.net.state_dict().items()]
# def set_parameters(self, parameters):
# params_dict = zip(self.net.state_dict().keys(), parameters)
# state_dict = OrderedDict({k: torch.Tensor(v) for k, v in params_dict})
# self.net.load_state_dict(state_dict, strict=True)
# def fit(self, parameters, config):
# self.set_parameters(parameters)
# train(self.net, self.trainloader, epochs=1)
# loss, accuracy = test(self.net, self.testloader)
# self.losses.append(loss)
# self.accuracies.append(accuracy)
# return self.get_parameters(config={}), len(self.trainloader.dataset), {}
# def evaluate(self, parameters, config):
# self.set_parameters(parameters)
# loss, accuracy = test(self.net, self.testloader)
# return float(loss), len(self.testloader.dataset), {"accuracy": float(accuracy)}
# def plot_metrics(self, round_num, plot_placeholder):
# if self.losses and self.accuracies:
# plot_placeholder.write(f"#### Client {self.client_id} Metrics for Round {round_num}")
# plot_placeholder.write(f"Loss: {self.losses[-1]:.4f}")
# plot_placeholder.write(f"Accuracy: {self.accuracies[-1]:.4f}")
# fig, ax1 = plt.subplots()
# color = 'tab:red'
# ax1.set_xlabel('Round')
# ax1.set_ylabel('Loss', color=color)
# ax1.plot(range(1, len(self.losses) + 1), self.losses, color=color)
# ax1.tick_params(axis='y', labelcolor=color)
# ax2 = ax1.twinx() # instantiate a second axes that shares the same x-axis
# color = 'tab:blue'
# ax2.set_ylabel('Accuracy', color=color)
# ax2.plot(range(1, len(self.accuracies) + 1), self.accuracies, color=color)
# ax2.tick_params(axis='y', labelcolor=color)
# fig.tight_layout()
# plot_placeholder.pyplot(fig)
# def main():
# st.write("## Federated Learning with Dynamic Models and Datasets for Mobile Devices")
# dataset_name = st.selectbox("Dataset", ["imdb", "amazon_polarity", "ag_news"])
# model_name = st.selectbox("Model", ["bert-base-uncased","facebook/hubert-base-ls960", "distilbert-base-uncased"])
# NUM_CLIENTS = st.slider("Number of Clients", min_value=1, max_value=10, value=2)
# NUM_ROUNDS = st.slider("Number of Rounds", min_value=1, max_value=10, value=3)
# train_datasets, test_datasets, data_collator = load_data(dataset_name, num_clients=NUM_CLIENTS)
# trainloaders = []
# testloaders = []
# clients = []
# for i in range(NUM_CLIENTS):
# st.write(f"### Client {i+1} Datasets")
# train_df = pd.DataFrame(train_datasets[i])
# test_df = pd.DataFrame(test_datasets[i])
# st.write("#### Train Dataset")
# edited_train_df = st.data_editor(train_df, key=f"train_{i}")
# st.write("#### Test Dataset")
# edited_test_df = st.data_editor(test_df, key=f"test_{i}")
# edited_train_dataset = Dataset.from_pandas(edited_train_df)
# edited_test_dataset = Dataset.from_pandas(edited_test_df)
# trainloader = DataLoader(edited_train_dataset, shuffle=True, batch_size=32, collate_fn=data_collator)
# testloader = DataLoader(edited_test_dataset, batch_size=32, collate_fn=data_collator)
# trainloaders.append(trainloader)
# testloaders.append(testloader)
# net = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
# client = CustomClient(net, trainloader, testloader, client_id=i+1)
# clients.append(client)
# if st.button("Start Training"):
# def client_fn(cid):
# return clients[int(cid)]
# def weighted_average(metrics):
# accuracies = [num_examples * m["accuracy"] for num_examples, m in metrics]
# losses = [num_examples * m["loss"] for num_examples, m in metrics]
# examples = [num_examples for num_examples, _ in metrics]
# return {"accuracy": sum(accuracies) / sum(examples), "loss": sum(losses) / sum(examples)}
# strategy = fl.server.strategy.FedAvg(
# fraction_fit=1.0,
# fraction_evaluate=1.0,
# evaluate_metrics_aggregation_fn=weighted_average,
# )
# for round_num in range(NUM_ROUNDS):
# st.write(f"### Round {round_num + 1}")
# plot_placeholders = [st.empty() for _ in range(NUM_CLIENTS)]
# fl.common.logger.configure(identifier="myFlowerExperiment", filename="./log.txt")
# fl.simulation.start_simulation(
# client_fn=client_fn,
# num_clients=NUM_CLIENTS,
# config=fl.server.ServerConfig(num_rounds=1),
# strategy=strategy,
# client_resources={"num_cpus": 1, "num_gpus": 0},
# ray_init_args={"log_to_driver": False, "num_cpus": 1, "num_gpus": 0}
# )
# for i, client in enumerate(clients):
# st.markdown("LOGS : "+ read_log_file())
# client.plot_metrics(round_num + 1, plot_placeholders[i])
# st.write(" ")
# st.success("Training completed successfully!")
# # Display final metrics
# st.write("## Final Client Metrics")
# for client in clients:
# st.write(f"### Client {client.client_id}")
# st.write(f"Final Loss: {client.losses[-1]:.4f}")
# st.write(f"Final Accuracy: {client.accuracies[-1]:.4f}")
# client.plot_metrics(NUM_ROUNDS, st.empty())
# st.write(" ")
# else:
# st.write("Click the 'Start Training' button to start the training process.")
# if __name__ == "__main__":
# main()
# %%writefile app.py
import streamlit as st
import matplotlib.pyplot as plt
import torch
from transformers import AutoTokenizer, DataCollatorWithPadding, AutoModelForSequenceClassification, AdamW
from datasets import load_dataset, Dataset
from evaluate import load as load_metric
from torch.utils.data import DataLoader
import pandas as pd
import random
from collections import OrderedDict
import flwr as fl
from logging import INFO, DEBUG
from flwr.common.logger import log
import logging
import streamlit
# If you're curious of all the loggers
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
fl.common.logger.configure(identifier="myFlowerExperiment", filename="./log.txt")
def load_data(dataset_name, train_size=20, test_size=20, num_clients=2):
raw_datasets = load_dataset(dataset_name)
raw_datasets = raw_datasets.shuffle(seed=42)
del raw_datasets["unsupervised"]
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
def tokenize_function(examples):
return tokenizer(examples["text"], truncation=True)
tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)
tokenized_datasets = tokenized_datasets.remove_columns("text")
tokenized_datasets = tokenized_datasets.rename_column("label", "labels")
train_datasets = []
test_datasets = []
for _ in range(num_clients):
train_dataset = tokenized_datasets["train"].select(random.sample(range(len(tokenized_datasets["train"])), train_size))
test_dataset = tokenized_datasets["test"].select(random.sample(range(len(tokenized_datasets["test"])), test_size))
train_datasets.append(train_dataset)
test_datasets.append(test_dataset)
data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
return train_datasets, test_datasets, data_collator, raw_datasets
def train(net, trainloader, epochs):
optimizer = AdamW(net.parameters(), lr=5e-5)
net.train()
for _ in range(epochs):
for batch in trainloader:
batch = {k: v.to(DEVICE) for k, v in batch.items()}
outputs = net(**batch)
loss = outputs.loss
loss.backward()
optimizer.step()
optimizer.zero_grad()
def test(net, testloader):
metric = load_metric("accuracy")
net.eval()
loss = 0
for batch in testloader:
batch = {k: v.to(DEVICE) for k, v in batch.items()}
with torch.no_grad():
outputs = net(**batch)
logits = outputs.logits
loss += outputs.loss.item()
predictions = torch.argmax(logits, dim=-1)
metric.add_batch(predictions=predictions, references=batch["labels"])
loss /= len(testloader)
accuracy = metric.compute()["accuracy"]
return loss, accuracy
class CustomClient(fl.client.NumPyClient):
def __init__(self, net, trainloader, testloader, client_id):
self.net = net
self.trainloader = trainloader
self.testloader = testloader
self.client_id = client_id
self.losses = []
self.accuracies = []
def get_parameters(self, config):
return [val.cpu().numpy() for _, val in self.net.state_dict().items()]
def set_parameters(self, parameters):
params_dict = zip(self.net.state_dict().keys(), parameters)
state_dict = OrderedDict({k: torch.Tensor(v) for k, v in params_dict})
self.net.load_state_dict(state_dict, strict=True)
def fit(self, parameters, config):
log(INFO, f"Client {self.client_id} is starting fit()")
self.set_parameters(parameters)
train(self.net, self.trainloader, epochs=1)
loss, accuracy = test(self.net, self.testloader)
self.losses.append(loss)
self.accuracies.append(accuracy)
log(INFO, f"Client {self.client_id} finished fit() with loss: {loss:.4f} and accuracy: {accuracy:.4f}")
return self.get_parameters(config={}), len(self.trainloader.dataset), {"loss": loss, "accuracy": accuracy}
def evaluate(self, parameters, config):
log(INFO, f"Client {self.client_id} is starting evaluate()")
self.set_parameters(parameters)
loss, accuracy = test(self.net, self.testloader)
log(INFO, f"Client {self.client_id} finished evaluate() with loss: {loss:.4f} and accuracy: {accuracy:.4f}")
return float(loss), len(self.testloader.dataset), {"accuracy": float(accuracy), "loss": float(loss)}
def plot_metrics(self, round_num, plot_placeholder):
if self.losses and self.accuracies:
plot_placeholder.write(f"#### Client {self.client_id} Metrics for Round {round_num}")
plot_placeholder.write(f"Loss: {self.losses[-1]:.4f}")
plot_placeholder.write(f"Accuracy: {self.accuracies[-1]:.4f}")
fig, ax1 = plt.subplots()
color = 'tab:red'
ax1.set_xlabel('Round')
ax1.set_ylabel('Loss', color=color)
ax1.plot(range(1, len(self.losses) + 1), self.losses, color=color)
ax1.tick_params(axis='y', labelcolor=color)
ax2 = ax1.twinx() # instantiate a second axes that shares the same x-axis
color = 'tab:blue'
ax2.set_ylabel('Accuracy', color=color)
ax2.plot(range(1, len(self.accuracies) + 1), self.accuracies, color=color)
ax2.tick_params(axis='y', labelcolor=color)
fig.tight_layout()
plot_placeholder.pyplot(fig)
import matplotlib.pyplot as plt
import re
def read_log_file(log_path='./log.txt'):
with open(log_path, 'r') as file:
log_lines = file.readlines()
return log_lines
def parse_log(log_lines):
rounds = []
clients = {}
memory_usage = []
round_pattern = re.compile(r'ROUND(\d+)ROUND (\d+)')
client_pattern = re.compile(r'Client (\d+) \| (INFO|DEBUG) \| (.*)')
memory_pattern = re.compile(r'memory used=(\d+\.\d+)GB')
current_round = None
for line in log_lines:
round_match = round_pattern.search(line)
client_match = client_pattern.search(line)
memory_match = memory_pattern.search(line)
if round_match:
current_round = int(round_match.group(1))
rounds.append(current_round)
elif client_match:
client_id = int(client_match.group(1))
log_level = client_match.group(2)
message = client_match.group(3)
if client_id not in clients:
clients[client_id] = {'rounds': [], 'messages': []}
clients[client_id]['rounds'].append(current_round)
clients[client_id]['messages'].append((log_level, message))
elif memory_match:
memory_usage.append(float(memory_match.group(1)))
return rounds, clients, memory_usage
def plot_metrics(rounds, clients, memory_usage):
st.write("## Metrics Overview")
st.write("### Memory Usage")
plt.figure()
plt.plot(range(len(memory_usage)), memory_usage, label='Memory Usage (GB)')
plt.xlabel('Step')
plt.ylabel('Memory Usage (GB)')
plt.legend()
st.pyplot(plt)
for client_id, data in clients.items():
st.write(f"### Client {client_id} Metrics")
info_messages = [msg for level, msg in data['messages'] if level == 'INFO']
debug_messages = [msg for level, msg in data['messages'] if level == 'DEBUG']
st.write("#### INFO Messages")
for msg in info_messages:
st.write(msg)
st.write("#### DEBUG Messages")
for msg in debug_messages:
st.write(msg)
# Placeholder for actual loss and accuracy values, assuming they're included in the messages
losses = [float(re.search(r'loss=([\d\.]+)', msg).group(1)) for msg in debug_messages if 'loss=' in msg]
accuracies = [float(re.search(r'accuracy=([\d\.]+)', msg).group(1)) for msg in debug_messages if 'accuracy=' in msg]
if losses:
plt.figure()
plt.plot(data['rounds'], losses, label='Loss')
plt.xlabel('Round')
plt.ylabel('Loss')
plt.legend()
st.pyplot(plt)
if accuracies:
plt.figure()
plt.plot(data['rounds'], accuracies, label='Accuracy')
plt.xlabel('Round')
plt.ylabel('Accuracy')
plt.legend()
st.pyplot(plt)
def read_log_file2():
with open("./log.txt", "r") as file:
return file.read()
def main():
st.markdown(print(streamlit.logger._loggers))
st.write("## Federated Learning with Dynamic Models and Datasets for Mobile Devices")
dataset_name = st.selectbox("Dataset", ["imdb", "amazon_polarity", "ag_news"])
model_name = st.selectbox("Model", ["bert-base-uncased", "facebook/hubert-base-ls960", "distilbert-base-uncased"])
NUM_CLIENTS = st.slider("Number of Clients", min_value=1, max_value=10, value=2)
NUM_ROUNDS = st.slider("Number of Rounds", min_value=1, max_value=10, value=3)
train_datasets, test_datasets, data_collator, raw_datasets = load_data(dataset_name, num_clients=NUM_CLIENTS)
trainloaders = []
testloaders = []
clients = []
for i in range(NUM_CLIENTS):
st.write(f"### Client {i+1} Datasets")
train_df = pd.DataFrame(train_datasets[i])
test_df = pd.DataFrame(test_datasets[i])
st.write("#### Train Dataset (Words)")
st.dataframe(raw_datasets["train"].select(random.sample(range(len(raw_datasets["train"])), 20)))
st.write("#### Train Dataset (Tokens)")
edited_train_df = st.data_editor(train_df, key=f"train_{i}")
st.write("#### Test Dataset (Words)")
st.dataframe(raw_datasets["test"].select(random.sample(range(len(raw_datasets["test"])), 20)))
st.write("#### Test Dataset (Tokens)")
edited_test_df = st.data_editor(test_df, key=f"test_{i}")
edited_train_dataset = Dataset.from_pandas(edited_train_df)
edited_test_dataset = Dataset.from_pandas(edited_test_df)
trainloader = DataLoader(edited_train_dataset, shuffle=True, batch_size=32, collate_fn=data_collator)
testloader = DataLoader(edited_test_dataset, batch_size=32, collate_fn=data_collator)
trainloaders.append(trainloader)
testloaders.append(testloader)
net = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
client = CustomClient(net, trainloader, testloader, client_id=i+1)
clients.append(client)
if st.button("Start Training"):
def client_fn(cid):
return clients[int(cid)]
def weighted_average(metrics):
accuracies = [num_examples * m["accuracy"] for num_examples, m in metrics]
losses = [num_examples * m["loss"] for num_examples, m in metrics]
examples = [num_examples for num_examples, _ in metrics]
return {"accuracy": sum(accuracies) / sum(examples), "loss": sum(losses) / sum(examples)}
strategy = fl.server.strategy.FedAvg(
fraction_fit=1.0,
fraction_evaluate=1.0,
evaluate_metrics_aggregation_fn=weighted_average,
)
for round_num in range(NUM_ROUNDS):
st.write(f"### Round {round_num + 1}")
st.markdown(read_log_file2())
plot_placeholders = [st.empty() for _ in range(NUM_CLIENTS)]
fl.simulation.start_simulation(
client_fn=client_fn,
num_clients=NUM_CLIENTS,
config=fl.server.ServerConfig(num_rounds=1),
strategy=strategy,
client_resources={"num_cpus": 1, "num_gpus": (1 if torch.cuda.is_available() else 0)},
ray_init_args={"log_to_driver": True, "num_cpus": 1, "num_gpus": (1 if torch.cuda.is_available() else 0)}
)
for i, client in enumerate(clients):
client.plot_metrics(round_num + 1, plot_placeholders[i])
st.write(" ")
st.success("Training completed successfully!")
# Display final metrics
st.write("## Final Client Metrics")
for client in clients:
st.write(f"### Client {client.client_id}")
if client.losses and client.accuracies:
st.write(f"Final Loss: {client.losses[-1]:.4f}")
st.write(f"Final Accuracy: {client.accuracies[-1]:.4f}")
client.plot_metrics(NUM_ROUNDS, st.empty())
else:
st.write("No metrics available.")
st.write(" ")
# Display log.txt content
st.write("## Training Log")
# st.text(read_log_file())
st.write("## Training Log Analysis")
log_lines = read_log_file()
rounds, clients, memory_usage = parse_log(log_lines)
plot_metrics(rounds, clients, memory_usage)
else:
st.write("Click the 'Start Training' button to start the training process.")
if __name__ == "__main__":
main()
|