iicd/xautodl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update tests for torch/cuda

Browse Source
This commit is contained in:
D-X-Y
2021-03-30 12:05:52 +00:00
parent c2270fd153
commit e5ec43e04a
12 changed files with 386 additions and 248 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.github/workflows/basic_test.yml vendored
View File

@@ -37,6 +37,7 @@ jobs:
python -m black ./lib/trade_models -l 88 --check --diff --verbose
python -m black ./lib/procedures -l 88 --check --diff --verbose
python -m black ./lib/config_utils -l 88 --check --diff --verbose
python -m black ./lib/log_utils -l 88 --check --diff --verbose
- name: Test Search Space
run: |

2
.latent-data/qlib

Submodule .latent-data/qlib updated: 968930e85f...70c84cbc77

26
exps/trading/baselines.py
View File

@@ -141,26 +141,25 @@ def retrieve_configs():
return alg2configs
def main(xargs, config):
def main(alg_name, market, config, times, save_dir, gpu):
pprint("Run {:}".format(xargs.alg))
config = update_market(config, xargs.market)
config = update_gpu(config, xargs.gpu)
pprint("Run {:}".format(alg_name))
config = update_market(config, market)
config = update_gpu(config, gpu)
qlib.init(**config.get("qlib_init"))
dataset_config = config.get("task").get("dataset")
dataset = init_instance_by_config(dataset_config)
pprint("args: {:}".format(xargs))
pprint(dataset_config)
pprint(dataset)
for irun in range(xargs.times):
for irun in range(times):
run_exp(
config.get("task"),
dataset,
xargs.alg,
"recorder-{:02d}-{:02d}".format(irun, xargs.times),
"{:}-{:}".format(xargs.save_dir, xargs.market),
alg_name,
"recorder-{:02d}-{:02d}".format(irun, times),
"{:}-{:}".format(save_dir, market),
)
@@ -203,6 +202,13 @@ if __name__ == "__main__":
args = parser.parse_args()
if len(args.alg) == 1:
main(args, alg2configs[args.alg[0]])
main(
args.alg[0],
args.market,
alg2configs[args.alg[0]],
args.times,
args.save_dir,
args.gpu,
)
else:
print("-")

1
lib/config_utils/__init__.py
View File

@@ -3,6 +3,7 @@
##################################################
# general config related functions
from .config_utils import load_config, dict2config, configure2str
# the args setting for different experiments
from .basic_args import obtain_basic_args
from .attention_args import obtain_attention_args

14
lib/log_utils/__init__.py
View File

@@ -3,6 +3,14 @@
##################################################
# every package does not rely on pytorch or tensorflow
# I tried to list all dependency here: os, sys, time, numpy, (possibly) matplotlib
from .logger import Logger, PrintLogger
from .meter import AverageMeter
from .time_utils import time_for_file, time_string, time_string_short, time_print, convert_secs2time
##################################################
from .logger import Logger, PrintLogger
from .meter import AverageMeter
from .time_utils import (
time_for_file,
time_string,
time_string_short,
time_print,
convert_secs2time,
)
from .pickle_wrap import pickle_save, pickle_load

257
lib/log_utils/logger.py
View File

@@ -4,147 +4,168 @@
from pathlib import Path
import importlib, warnings
import os, sys, time, numpy as np
if sys.version_info.major == 2: # Python 2.x
from StringIO import StringIO as BIO
else: # Python 3.x
from io import BytesIO as BIO
if importlib.util.find_spec('tensorflow'):
import tensorflow as tf
if sys.version_info.major == 2: # Python 2.x
from StringIO import StringIO as BIO
else: # Python 3.x
from io import BytesIO as BIO
if importlib.util.find_spec("tensorflow"):
import tensorflow as tf
class PrintLogger(object):
def __init__(self):
"""Create a summary writer logging to log_dir."""
self.name = "PrintLogger"
def __init__(self):
"""Create a summary writer logging to log_dir."""
self.name = 'PrintLogger'
def log(self, string):
print(string)
def log(self, string):
print (string)
def close(self):
print ('-'*30 + ' close printer ' + '-'*30)
def close(self):
print("-" * 30 + " close printer " + "-" * 30)
class Logger(object):
def __init__(self, log_dir, seed, create_model_dir=True, use_tf=False):
"""Create a summary writer logging to log_dir."""
self.seed = int(seed)
self.log_dir = Path(log_dir)
self.model_dir = Path(log_dir) / "checkpoint"
self.log_dir.mkdir(parents=True, exist_ok=True)
if create_model_dir:
self.model_dir.mkdir(parents=True, exist_ok=True)
# self.meta_dir.mkdir(mode=0o775, parents=True, exist_ok=True)
def __init__(self, log_dir, seed, create_model_dir=True, use_tf=False):
"""Create a summary writer logging to log_dir."""
self.seed = int(seed)
self.log_dir = Path(log_dir)
self.model_dir = Path(log_dir) / 'checkpoint'
self.log_dir.mkdir (parents=True, exist_ok=True)
if create_model_dir:
self.model_dir.mkdir(parents=True, exist_ok=True)
#self.meta_dir.mkdir(mode=0o775, parents=True, exist_ok=True)
self.use_tf = bool(use_tf)
self.tensorboard_dir = self.log_dir / (
"tensorboard-{:}".format(time.strftime("%d-%h", time.gmtime(time.time())))
)
# self.tensorboard_dir = self.log_dir / ('tensorboard-{:}'.format(time.strftime( '%d-%h-at-%H:%M:%S', time.gmtime(time.time()) )))
self.logger_path = self.log_dir / "seed-{:}-T-{:}.log".format(
self.seed, time.strftime("%d-%h-at-%H-%M-%S", time.gmtime(time.time()))
)
self.logger_file = open(self.logger_path, "w")
self.use_tf = bool(use_tf)
self.tensorboard_dir = self.log_dir / ('tensorboard-{:}'.format(time.strftime( '%d-%h', time.gmtime(time.time()) )))
#self.tensorboard_dir = self.log_dir / ('tensorboard-{:}'.format(time.strftime( '%d-%h-at-%H:%M:%S', time.gmtime(time.time()) )))
self.logger_path = self.log_dir / 'seed-{:}-T-{:}.log'.format(self.seed, time.strftime('%d-%h-at-%H-%M-%S', time.gmtime(time.time())))
self.logger_file = open(self.logger_path, 'w')
if self.use_tf:
self.tensorboard_dir.mkdir(mode=0o775, parents=True, exist_ok=True)
self.writer = tf.summary.FileWriter(str(self.tensorboard_dir))
else:
self.writer = None
if self.use_tf:
self.tensorboard_dir.mkdir(mode=0o775, parents=True, exist_ok=True)
self.writer = tf.summary.FileWriter(str(self.tensorboard_dir))
else:
self.writer = None
def __repr__(self):
return "{name}(dir={log_dir}, use-tf={use_tf}, writer={writer})".format(
name=self.__class__.__name__, **self.__dict__
)
def __repr__(self):
return ('{name}(dir={log_dir}, use-tf={use_tf}, writer={writer})'.format(name=self.__class__.__name__, **self.__dict__))
def path(self, mode):
valids = ("model", "best", "info", "log")
if mode == "model":
return self.model_dir / "seed-{:}-basic.pth".format(self.seed)
elif mode == "best":
return self.model_dir / "seed-{:}-best.pth".format(self.seed)
elif mode == "info":
return self.log_dir / "seed-{:}-last-info.pth".format(self.seed)
elif mode == "log":
return self.log_dir
else:
raise TypeError("Unknow mode = {:}, valid modes = {:}".format(mode, valids))
def path(self, mode):
valids = ('model', 'best', 'info', 'log')
if mode == 'model': return self.model_dir / 'seed-{:}-basic.pth'.format(self.seed)
elif mode == 'best' : return self.model_dir / 'seed-{:}-best.pth'.format(self.seed)
elif mode == 'info' : return self.log_dir / 'seed-{:}-last-info.pth'.format(self.seed)
elif mode == 'log' : return self.log_dir
else: raise TypeError('Unknow mode = {:}, valid modes = {:}'.format(mode, valids))
def extract_log(self):
return self.logger_file
def extract_log(self):
return self.logger_file
def close(self):
self.logger_file.close()
if self.writer is not None:
self.writer.close()
def close(self):
self.logger_file.close()
if self.writer is not None:
self.writer.close()
def log(self, string, save=True, stdout=False):
if stdout:
sys.stdout.write(string)
sys.stdout.flush()
else:
print(string)
if save:
self.logger_file.write("{:}\n".format(string))
self.logger_file.flush()
def log(self, string, save=True, stdout=False):
if stdout:
sys.stdout.write(string); sys.stdout.flush()
else:
print (string)
if save:
self.logger_file.write('{:}\n'.format(string))
self.logger_file.flush()
def scalar_summary(self, tags, values, step):
"""Log a scalar variable."""
if not self.use_tf:
warnings.warn("Do set use-tensorflow installed but call scalar_summary")
else:
assert isinstance(tags, list) == isinstance(
values, list
), "Type : {:} vs {:}".format(type(tags), type(values))
if not isinstance(tags, list):
tags, values = [tags], [values]
for tag, value in zip(tags, values):
summary = tf.Summary(
value=[tf.Summary.Value(tag=tag, simple_value=value)]
)
self.writer.add_summary(summary, step)
self.writer.flush()
def scalar_summary(self, tags, values, step):
"""Log a scalar variable."""
if not self.use_tf:
warnings.warn('Do set use-tensorflow installed but call scalar_summary')
else:
assert isinstance(tags, list) == isinstance(values, list), 'Type : {:} vs {:}'.format(type(tags), type(values))
if not isinstance(tags, list):
tags, values = [tags], [values]
for tag, value in zip(tags, values):
summary = tf.Summary(value=[tf.Summary.Value(tag=tag, simple_value=value)])
def image_summary(self, tag, images, step):
"""Log a list of images."""
import scipy
if not self.use_tf:
warnings.warn("Do set use-tensorflow installed but call scalar_summary")
return
img_summaries = []
for i, img in enumerate(images):
# Write the image to a string
try:
s = StringIO()
except:
s = BytesIO()
scipy.misc.toimage(img).save(s, format="png")
# Create an Image object
img_sum = tf.Summary.Image(
encoded_image_string=s.getvalue(),
height=img.shape[0],
width=img.shape[1],
)
# Create a Summary value
img_summaries.append(
tf.Summary.Value(tag="{}/{}".format(tag, i), image=img_sum)
)
# Create and write Summary
summary = tf.Summary(value=img_summaries)
self.writer.add_summary(summary, step)
self.writer.flush()
def image_summary(self, tag, images, step):
"""Log a list of images."""
import scipy
if not self.use_tf:
warnings.warn('Do set use-tensorflow installed but call scalar_summary')
return
def histo_summary(self, tag, values, step, bins=1000):
"""Log a histogram of the tensor of values."""
if not self.use_tf:
raise ValueError("Do not have tensorflow")
import tensorflow as tf
img_summaries = []
for i, img in enumerate(images):
# Write the image to a string
try:
s = StringIO()
except:
s = BytesIO()
scipy.misc.toimage(img).save(s, format="png")
# Create a histogram using numpy
counts, bin_edges = np.histogram(values, bins=bins)
# Create an Image object
img_sum = tf.Summary.Image(encoded_image_string=s.getvalue(),
height=img.shape[0],
width=img.shape[1])
# Create a Summary value
img_summaries.append(tf.Summary.Value(tag='{}/{}'.format(tag, i), image=img_sum))
# Fill the fields of the histogram proto
hist = tf.HistogramProto()
hist.min = float(np.min(values))
hist.max = float(np.max(values))
hist.num = int(np.prod(values.shape))
hist.sum = float(np.sum(values))
hist.sum_squares = float(np.sum(values ** 2))
# Create and write Summary
summary = tf.Summary(value=img_summaries)
self.writer.add_summary(summary, step)
self.writer.flush()
# Drop the start of the first bin
bin_edges = bin_edges[1:]
def histo_summary(self, tag, values, step, bins=1000):
"""Log a histogram of the tensor of values."""
if not self.use_tf: raise ValueError('Do not have tensorflow')
import tensorflow as tf
# Add bin edges and counts
for edge in bin_edges:
hist.bucket_limit.append(edge)
for c in counts:
hist.bucket.append(c)
# Create a histogram using numpy
counts, bin_edges = np.histogram(values, bins=bins)
# Fill the fields of the histogram proto
hist = tf.HistogramProto()
hist.min = float(np.min(values))
hist.max = float(np.max(values))
hist.num = int(np.prod(values.shape))
hist.sum = float(np.sum(values))
hist.sum_squares = float(np.sum(values**2))
# Drop the start of the first bin
bin_edges = bin_edges[1:]
# Add bin edges and counts
for edge in bin_edges:
hist.bucket_limit.append(edge)
for c in counts:
hist.bucket.append(c)
# Create and write Summary
summary = tf.Summary(value=[tf.Summary.Value(tag=tag, histo=hist)])
self.writer.add_summary(summary, step)
self.writer.flush()
# Create and write Summary
summary = tf.Summary(value=[tf.Summary.Value(tag=tag, histo=hist)])
self.writer.add_summary(summary, step)
self.writer.flush()

174
lib/log_utils/meter.py
View File

@@ -2,97 +2,119 @@ import numpy as np
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self):
self.reset()
"""Computes and stores the average and current value"""
def reset(self):
self.val = 0.0
self.avg = 0.0
self.sum = 0.0
self.count = 0.0
def __init__(self):
self.reset()
def update(self, val, n=1):
self.val = val
self.sum += val * n
self.count += n
self.avg = self.sum / self.count
def reset(self):
self.val = 0.0
self.avg = 0.0
self.sum = 0.0
self.count = 0.0
def __repr__(self):
return ('{name}(val={val}, avg={avg}, count={count})'.format(name=self.__class__.__name__, **self.__dict__))
def update(self, val, n=1):
self.val = val
self.sum += val * n
self.count += n
self.avg = self.sum / self.count
def __repr__(self):
return "{name}(val={val}, avg={avg}, count={count})".format(
name=self.__class__.__name__, **self.__dict__
)
class RecorderMeter(object):
"""Computes and stores the minimum loss value and its epoch index"""
def __init__(self, total_epoch):
self.reset(total_epoch)
"""Computes and stores the minimum loss value and its epoch index"""
def reset(self, total_epoch):
assert total_epoch > 0, 'total_epoch should be greater than 0 vs {:}'.format(total_epoch)
self.total_epoch = total_epoch
self.current_epoch = 0
self.epoch_losses = np.zeros((self.total_epoch, 2), dtype=np.float32) # [epoch, train/val]
self.epoch_losses = self.epoch_losses - 1
self.epoch_accuracy= np.zeros((self.total_epoch, 2), dtype=np.float32) # [epoch, train/val]
self.epoch_accuracy= self.epoch_accuracy
def __init__(self, total_epoch):
self.reset(total_epoch)
def update(self, idx, train_loss, train_acc, val_loss, val_acc):
assert idx >= 0 and idx < self.total_epoch, 'total_epoch : {} , but update with the {} index'.format(self.total_epoch, idx)
self.epoch_losses [idx, 0] = train_loss
self.epoch_losses [idx, 1] = val_loss
self.epoch_accuracy[idx, 0] = train_acc
self.epoch_accuracy[idx, 1] = val_acc
self.current_epoch = idx + 1
return self.max_accuracy(False) == self.epoch_accuracy[idx, 1]
def reset(self, total_epoch):
assert total_epoch > 0, "total_epoch should be greater than 0 vs {:}".format(
total_epoch
)
self.total_epoch = total_epoch
self.current_epoch = 0
self.epoch_losses = np.zeros(
(self.total_epoch, 2), dtype=np.float32
) # [epoch, train/val]
self.epoch_losses = self.epoch_losses - 1
self.epoch_accuracy = np.zeros(
(self.total_epoch, 2), dtype=np.float32
) # [epoch, train/val]
self.epoch_accuracy = self.epoch_accuracy
def max_accuracy(self, istrain):
if self.current_epoch <= 0: return 0
if istrain: return self.epoch_accuracy[:self.current_epoch, 0].max()
else: return self.epoch_accuracy[:self.current_epoch, 1].max()
def update(self, idx, train_loss, train_acc, val_loss, val_acc):
assert (
idx >= 0 and idx < self.total_epoch
), "total_epoch : {} , but update with the {} index".format(
self.total_epoch, idx
)
self.epoch_losses[idx, 0] = train_loss
self.epoch_losses[idx, 1] = val_loss
self.epoch_accuracy[idx, 0] = train_acc
self.epoch_accuracy[idx, 1] = val_acc
self.current_epoch = idx + 1
return self.max_accuracy(False) == self.epoch_accuracy[idx, 1]
def plot_curve(self, save_path):
import matplotlib
matplotlib.use('agg')
import matplotlib.pyplot as plt
title = 'the accuracy/loss curve of train/val'
dpi = 100
width, height = 1600, 1000
legend_fontsize = 10
figsize = width / float(dpi), height / float(dpi)
def max_accuracy(self, istrain):
if self.current_epoch <= 0:
return 0
if istrain:
return self.epoch_accuracy[: self.current_epoch, 0].max()
else:
return self.epoch_accuracy[: self.current_epoch, 1].max()
fig = plt.figure(figsize=figsize)
x_axis = np.array([i for i in range(self.total_epoch)]) # epochs
y_axis = np.zeros(self.total_epoch)
def plot_curve(self, save_path):
import matplotlib
plt.xlim(0, self.total_epoch)
plt.ylim(0, 100)
interval_y = 5
interval_x = 5
plt.xticks(np.arange(0, self.total_epoch + interval_x, interval_x))
plt.yticks(np.arange(0, 100 + interval_y, interval_y))
plt.grid()
plt.title(title, fontsize=20)
plt.xlabel('the training epoch', fontsize=16)
plt.ylabel('accuracy', fontsize=16)
matplotlib.use("agg")
import matplotlib.pyplot as plt
y_axis[:] = self.epoch_accuracy[:, 0]
plt.plot(x_axis, y_axis, color='g', linestyle='-', label='train-accuracy', lw=2)
plt.legend(loc=4, fontsize=legend_fontsize)
title = "the accuracy/loss curve of train/val"
dpi = 100
width, height = 1600, 1000
legend_fontsize = 10
figsize = width / float(dpi), height / float(dpi)
y_axis[:] = self.epoch_accuracy[:, 1]
plt.plot(x_axis, y_axis, color='y', linestyle='-', label='valid-accuracy', lw=2)
plt.legend(loc=4, fontsize=legend_fontsize)
fig = plt.figure(figsize=figsize)
x_axis = np.array([i for i in range(self.total_epoch)]) # epochs
y_axis = np.zeros(self.total_epoch)
plt.xlim(0, self.total_epoch)
plt.ylim(0, 100)
interval_y = 5
interval_x = 5
plt.xticks(np.arange(0, self.total_epoch + interval_x, interval_x))
plt.yticks(np.arange(0, 100 + interval_y, interval_y))
plt.grid()
plt.title(title, fontsize=20)
plt.xlabel("the training epoch", fontsize=16)
plt.ylabel("accuracy", fontsize=16)
y_axis[:] = self.epoch_losses[:, 0]
plt.plot(x_axis, y_axis*50, color='g', linestyle=':', label='train-loss-x50', lw=2)
plt.legend(loc=4, fontsize=legend_fontsize)
y_axis[:] = self.epoch_accuracy[:, 0]
plt.plot(x_axis, y_axis, color="g", linestyle="-", label="train-accuracy", lw=2)
plt.legend(loc=4, fontsize=legend_fontsize)
y_axis[:] = self.epoch_losses[:, 1]
plt.plot(x_axis, y_axis*50, color='y', linestyle=':', label='valid-loss-x50', lw=2)
plt.legend(loc=4, fontsize=legend_fontsize)
y_axis[:] = self.epoch_accuracy[:, 1]
plt.plot(x_axis, y_axis, color="y", linestyle="-", label="valid-accuracy", lw=2)
plt.legend(loc=4, fontsize=legend_fontsize)
if save_path is not None:
fig.savefig(save_path, dpi=dpi, bbox_inches='tight')
print ('---- save figure {} into {}'.format(title, save_path))
plt.close(fig)
y_axis[:] = self.epoch_losses[:, 0]
plt.plot(
x_axis, y_axis * 50, color="g", linestyle=":", label="train-loss-x50", lw=2
)
plt.legend(loc=4, fontsize=legend_fontsize)
y_axis[:] = self.epoch_losses[:, 1]
plt.plot(
x_axis, y_axis * 50, color="y", linestyle=":", label="valid-loss-x50", lw=2
)
plt.legend(loc=4, fontsize=legend_fontsize)
if save_path is not None:
fig.savefig(save_path, dpi=dpi, bbox_inches="tight")
print("---- save figure {} into {}".format(title, save_path))
plt.close(fig)

21
lib/log_utils/pickle_wrap.py Normal file
View File

@@ -0,0 +1,21 @@
#####################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.01 #
#####################################################
import pickle
from pathlib import Path
def pickle_save(obj, path):
file_path = Path(path)
file_dir = file_path.parent
file_dir.mkdir(parents=True, exist_ok=True)
with file_path.open("wb") as f:
pickle.dump(obj, f)
def pickle_load(path):
if not Path(path).exists():
raise ValueError("{:} does not exists".format(path))
with Path(path).open("rb") as f:
data = pickle.load(f)
return data

57
lib/log_utils/time_utils.py
View File

@@ -4,39 +4,46 @@
import time, sys
import numpy as np
def time_for_file():
ISOTIMEFORMAT='%d-%h-at-%H-%M-%S'
return '{:}'.format(time.strftime( ISOTIMEFORMAT, time.gmtime(time.time()) ))
ISOTIMEFORMAT = "%d-%h-at-%H-%M-%S"
return "{:}".format(time.strftime(ISOTIMEFORMAT, time.gmtime(time.time())))
def time_string():
ISOTIMEFORMAT='%Y-%m-%d %X'
string = '[{:}]'.format(time.strftime( ISOTIMEFORMAT, time.gmtime(time.time()) ))
return string
ISOTIMEFORMAT = "%Y-%m-%d %X"
string = "[{:}]".format(time.strftime(ISOTIMEFORMAT, time.gmtime(time.time())))
return string
def time_string_short():
ISOTIMEFORMAT='%Y%m%d'
string = '{:}'.format(time.strftime( ISOTIMEFORMAT, time.gmtime(time.time()) ))
return string
ISOTIMEFORMAT = "%Y%m%d"
string = "{:}".format(time.strftime(ISOTIMEFORMAT, time.gmtime(time.time())))
return string
def time_print(string, is_print=True):
if (is_print):
print('{} : {}'.format(time_string(), string))
if is_print:
print("{} : {}".format(time_string(), string))
def convert_secs2time(epoch_time, return_str=False):
need_hour = int(epoch_time / 3600)
need_mins = int((epoch_time - 3600*need_hour) / 60)
need_secs = int(epoch_time - 3600*need_hour - 60*need_mins)
if return_str:
str = '[{:02d}:{:02d}:{:02d}]'.format(need_hour, need_mins, need_secs)
return str
else:
return need_hour, need_mins, need_secs
need_hour = int(epoch_time / 3600)
need_mins = int((epoch_time - 3600 * need_hour) / 60)
need_secs = int(epoch_time - 3600 * need_hour - 60 * need_mins)
if return_str:
str = "[{:02d}:{:02d}:{:02d}]".format(need_hour, need_mins, need_secs)
return str
else:
return need_hour, need_mins, need_secs
def print_log(print_string, log):
#if isinstance(log, Logger): log.log('{:}'.format(print_string))
if hasattr(log, 'log'): log.log('{:}'.format(print_string))
else:
print("{:}".format(print_string))
if log is not None:
log.write('{:}\n'.format(print_string))
log.flush()
# if isinstance(log, Logger): log.log('{:}'.format(print_string))
if hasattr(log, "log"):
log.log("{:}".format(print_string))
else:
print("{:}".format(print_string))
if log is not None:
log.write("{:}\n".format(print_string))
log.flush()

20
lib/utils/flop_benchmark.py
View File

@@ -9,15 +9,19 @@ def count_parameters_in_MB(model):
def count_parameters(model_or_parameters, unit="mb"):
if isinstance(model_or_parameters, nn.Module):
counts = np.sum(np.prod(v.size()) for v in model_or_parameters.parameters())
counts = sum(np.prod(v.size()) for v in model_or_parameters.parameters())
elif isinstance(models_or_parameters, nn.Parameter):
counts = models_or_parameters.numel()
elif isinstance(models_or_parameters, (list, tuple)):
counts = sum(count_parameters(x, None) for x in models_or_parameters)
else:
counts = np.sum(np.prod(v.size()) for v in model_or_parameters)
if unit.lower() == "mb":
counts /= 1e6
elif unit.lower() == "kb":
counts /= 1e3
elif unit.lower() == "gb":
counts /= 1e9
counts = sum(np.prod(v.size()) for v in model_or_parameters)
if unit.lower() == "kb" or unit.lower() == "k":
counts /= 2 ** 10 # changed from 1e3 to 2^10
elif unit.lower() == "mb" or unit.lower() == "m":
counts /= 2 ** 20 # changed from 1e6 to 2^20
elif unit.lower() == "gb" or unit.lower() == "g":
counts /= 2 ** 30 # changed from 1e9 to 2^30
elif unit is not None:
raise ValueError("Unknow unit: {:}".format(unit))
return counts

4
tests/test_torch.sh Normal file
View File

@@ -0,0 +1,4 @@
# bash ./tests/test_torch.sh
pytest ./tests/test_torch_gpu_bugs.py::test_create -s
CUDA_VISIBLE_DEVICES="" pytest ./tests/test_torch_gpu_bugs.py::test_load -s

43
tests/test_torch_gpu_bugs.py Normal file
View File

@@ -0,0 +1,43 @@
#####################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2021.03 #
#####################################################
# pytest ./tests/test_torch_gpu_bugs.py::test_create
#
# CUDA_VISIBLE_DEVICES="" pytest ./tests/test_torch_gpu_bugs.py::test_load
#####################################################
import os, sys, time, torch
import pickle
import tempfile
from pathlib import Path
lib_dir = (Path(__file__).parent / ".." / "lib").resolve()
print("library path: {:}".format(lib_dir))
if str(lib_dir) not in sys.path:
sys.path.insert(0, str(lib_dir))
from trade_models.quant_transformer import QuantTransformer
def test_create():
"""Test the basic quant-model."""
if not torch.cuda.is_available():
return
quant_model = QuantTransformer(GPU=0)
temp_dir = lib_dir / ".." / "tests" / ".pytest_cache"
temp_dir.mkdir(parents=True, exist_ok=True)
temp_file = temp_dir / "quant-model.pkl"
with temp_file.open("wb") as f:
# quant_model.to(None)
quant_model.to("cpu")
# del quant_model.model
# del quant_model.train_optimizer
pickle.dump(quant_model, f)
print("save into {:}".format(temp_file))
def test_load():
temp_file = lib_dir / ".." / "tests" / ".pytest_cache" / "quant-model.pkl"
with temp_file.open("rb") as f:
model = pickle.load(f)
print(model.model)
print(model.train_optimizer)