File size: 7,040 Bytes
5209465 |
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 |
# ------------------------------------------------------------------------------
# Copyright (c) Microsoft
# Licensed under the MIT License.
# Written by Bin Xiao (Bin.Xiao@microsoft.com)
# ------------------------------------------------------------------------------
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import logging
import time
from collections import namedtuple
from pathlib import Path
import torch
import torch.optim as optim
import torch.nn as nn
def create_logger(cfg, cfg_name, phase='train'):
root_output_dir = Path(cfg.OUTPUT_DIR)
# set up logger
if not root_output_dir.exists():
print('=> creating {}'.format(root_output_dir))
root_output_dir.mkdir()
dataset = cfg.DATASET.DATASET + '_' + cfg.DATASET.HYBRID_JOINTS_TYPE \
if cfg.DATASET.HYBRID_JOINTS_TYPE else cfg.DATASET.DATASET
dataset = dataset.replace(':', '_')
model = cfg.MODEL.NAME
cfg_name = os.path.basename(cfg_name).split('.')[0]
final_output_dir = root_output_dir / dataset / model / cfg_name
print('=> creating {}'.format(final_output_dir))
final_output_dir.mkdir(parents=True, exist_ok=True)
time_str = time.strftime('%Y-%m-%d-%H-%M')
log_file = '{}_{}_{}.log'.format(cfg_name, time_str, phase)
final_log_file = final_output_dir / log_file
head = '%(asctime)-15s %(message)s'
logging.basicConfig(filename=str(final_log_file),
format=head)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console = logging.StreamHandler()
logging.getLogger('').addHandler(console)
tensorboard_log_dir = Path(cfg.LOG_DIR) / dataset / model / \
(cfg_name + '_' + time_str)
print('=> creating {}'.format(tensorboard_log_dir))
tensorboard_log_dir.mkdir(parents=True, exist_ok=True)
return logger, str(final_output_dir), str(tensorboard_log_dir)
def get_optimizer(cfg, model):
optimizer = None
if cfg.TRAIN.OPTIMIZER == 'sgd':
optimizer = optim.SGD(
model.parameters(),
lr=cfg.TRAIN.LR,
momentum=cfg.TRAIN.MOMENTUM,
weight_decay=cfg.TRAIN.WD,
nesterov=cfg.TRAIN.NESTEROV
)
elif cfg.TRAIN.OPTIMIZER == 'adam':
optimizer = optim.Adam(
model.parameters(),
lr=cfg.TRAIN.LR
)
return optimizer
def save_checkpoint(states, is_best, output_dir,
filename='checkpoint.pth'):
torch.save(states, os.path.join(output_dir, filename))
if is_best and 'state_dict' in states:
torch.save(states['best_state_dict'],
os.path.join(output_dir, 'model_best.pth'))
def get_model_summary(model, *input_tensors, item_length=26, verbose=False):
"""
:param model:
:param input_tensors:
:param item_length:
:return:
"""
summary = []
ModuleDetails = namedtuple(
"Layer", ["name", "input_size", "output_size", "num_parameters", "multiply_adds"])
hooks = []
layer_instances = {}
def add_hooks(module):
def hook(module, input, output):
class_name = str(module.__class__.__name__)
instance_index = 1
if class_name not in layer_instances:
layer_instances[class_name] = instance_index
else:
instance_index = layer_instances[class_name] + 1
layer_instances[class_name] = instance_index
layer_name = class_name + "_" + str(instance_index)
params = 0
if class_name.find("Conv") != -1 or class_name.find("BatchNorm") != -1 or \
class_name.find("Linear") != -1:
for param_ in module.parameters():
params += param_.view(-1).size(0)
flops = "Not Available"
if class_name.find("Conv") != -1 and hasattr(module, "weight"):
flops = (
torch.prod(
torch.LongTensor(list(module.weight.data.size()))) *
torch.prod(
torch.LongTensor(list(output.size())[2:]))).item()
elif isinstance(module, nn.Linear):
flops = (torch.prod(torch.LongTensor(list(output.size()))) \
* input[0].size(1)).item()
if isinstance(input[0], list):
input = input[0]
if isinstance(output, list):
output = output[0]
summary.append(
ModuleDetails(
name=layer_name,
input_size=list(input[0].size()),
output_size=list(output.size()),
num_parameters=params,
multiply_adds=flops)
)
if not isinstance(module, nn.ModuleList) \
and not isinstance(module, nn.Sequential) \
and module != model:
hooks.append(module.register_forward_hook(hook))
model.eval()
model.apply(add_hooks)
space_len = item_length
model(*input_tensors)
for hook in hooks:
hook.remove()
details = ''
if verbose:
details = "Model Summary" + \
os.linesep + \
"Name{}Input Size{}Output Size{}Parameters{}Multiply Adds (Flops){}".format(
' ' * (space_len - len("Name")),
' ' * (space_len - len("Input Size")),
' ' * (space_len - len("Output Size")),
' ' * (space_len - len("Parameters")),
' ' * (space_len - len("Multiply Adds (Flops)"))) \
+ os.linesep + '-' * space_len * 5 + os.linesep
params_sum = 0
flops_sum = 0
for layer in summary:
params_sum += layer.num_parameters
if layer.multiply_adds != "Not Available":
flops_sum += layer.multiply_adds
if verbose:
details += "{}{}{}{}{}{}{}{}{}{}".format(
layer.name,
' ' * (space_len - len(layer.name)),
layer.input_size,
' ' * (space_len - len(str(layer.input_size))),
layer.output_size,
' ' * (space_len - len(str(layer.output_size))),
layer.num_parameters,
' ' * (space_len - len(str(layer.num_parameters))),
layer.multiply_adds,
' ' * (space_len - len(str(layer.multiply_adds)))) \
+ os.linesep + '-' * space_len * 5 + os.linesep
details += os.linesep \
+ "Total Parameters: {:,}".format(params_sum) \
+ os.linesep + '-' * space_len * 5 + os.linesep
details += "Total Multiply Adds (For Convolution and Linear Layers only): {:,} GFLOPs".format(flops_sum/(1024**3)) \
+ os.linesep + '-' * space_len * 5 + os.linesep
details += "Number of Layers" + os.linesep
for layer in layer_instances:
details += "{} : {} layers ".format(layer, layer_instances[layer])
return details
|