【程序】yolo_v1 train

# -*- coding: utf-8 -*-
"""
@Time          : 2020/08/12 18:30
@Author        : Bryce
@File          : train.py
@Noice         :
@Modificattion :
    @Author    :
    @Time      :
    @Detail    :
"""
import warnings
import os
import numpy as np

import torch
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
from torchvision import models

from models.vgg_yolo import vgg16_bn
from models.resnet_yolo import resnet50
from models.yoloLoss import yoloLoss
from utils.dataset import yoloDataset

warnings.filterwarnings('ignore')
# 设置GPU ID
os.environ["CUDA_VISIBLE_DEVICES"] = "0"

# 判断GPU是否可用
use_gpu = torch.cuda.is_available()

# 数据文件
file_root = 'datasets'

# 超参数
learning_rate = 0.001
num_epochs = 100
# batch_size = 24
batch_size=4

# checkpoints
resume = False

# ---------------------数据读取---------------------
train_dataset = yoloDataset(root=file_root, list_file='images.txt', train=True,
                            transform=[transforms.ToTensor()])
# train_dataset = yoloDataset(root=file_root, list_file=['voc12_trainval.txt','voc07_trainval.txt'],
#                           train=True,transform = [transforms.ToTensor()] )
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4)

test_dataset = yoloDataset(root=file_root, list_file='voc2007test.txt', train=False,
                           transform=[transforms.ToTensor()])
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=4)
print('the train dataset has %d images' % (len(train_dataset)))
print('the test dataset has %d images' % (len(test_dataset)))
print('the batch_size is %d' % batch_size)


# ---------------------网络选择---------------------
use_resnet = True
if use_resnet:
    net = resnet50()
else:
    net = vgg16_bn()

if resume:
    print("loading weight from checkpoints/best.pth")
    net.load_state_dict(torch.load('checkpoints/best.pth'))
else:
    print('loading pre-trined model ......')
    if use_resnet:
        resnet = models.resnet50(pretrained=True)
        new_state_dict = resnet.state_dict()
        print(type(new_state_dict["conv1.weight"]),new_state_dict["conv1.weight"].dtype,(new_state_dict["conv1.weight"]).shape)
        input()
        dd = net.state_dict()
        print(dd.keys())
        for k in new_state_dict.keys():
            # print(len(k))
            # input()
            if k in dd.keys() and not k.startswith('fc'):
                # print(k)
                # print('yes')
                dd[k] = new_state_dict[k]
        print(dd.keys())
        net.load_state_dict(dd)
    else:
        vgg = models.vgg16_bn(pretrained=True)
        new_state_dict = vgg.state_dict()
        dd = net.state_dict()
        for k in new_state_dict.keys():
            print(k)
            if k in dd.keys() and k.startswith('features'):
                print('yes')
                dd[k] = new_state_dict[k]
        net.load_state_dict(dd)

if use_gpu:
    print('this computer has gpu %d and current is %s' % (torch.cuda.device_count(),
          torch.cuda.current_device()))
    net.cuda()


# ---------------------损失函数---------------------
criterion = yoloLoss(7, 2, 5, 0.5)

# ---------------------优化器----------------------

# different learning rate
params = []
params_dict = dict(net.named_parameters())
for key, value in params_dict.items():
    if key.startswith('features'):
        params += [{'params': [value], 'lr':learning_rate*1}]
    else:
        params += [{'params': [value], 'lr':learning_rate}]
optimizer = torch.optim.SGD(params, lr=learning_rate, momentum=0.9, weight_decay=5e-4)
# optimizer = torch.optim.Adam(net.parameters(),lr=learning_rate,weight_decay=1e-4)


# ---------------------训练---------------------
logfile = open('checkpoints/log.txt', 'w')
num_iter = 0
best_test_loss = np.inf

for epoch in range(num_epochs):
    # train
    net.train()
    if epoch == 30:
        learning_rate = 0.0001
    if epoch == 40:
        learning_rate = 0.00001
    for param_group in optimizer.param_groups:
        param_group['lr'] = learning_rate

    print('\n\nStarting epoch %d / %d' % (epoch + 1, num_epochs))
    print('Learning Rate for this epoch: {}'.format(learning_rate))

    total_loss = 0.

    for i, (images, target) in enumerate(train_loader):
        if use_gpu:
            images, target = images.cuda(), target.cuda()

        pred = net(images)
        loss = criterion(pred, target)
        total_loss += loss.data.item()

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        if (i+1) % 5 == 0:
            print('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f, average_loss: %.4f'
                        % (epoch+1, num_epochs, i+1, len(train_loader), loss.item(), total_loss / (i+1)))
            num_iter += 1

    # validation
    validation_loss = 0.0
    net.eval()
    for i, (images, target) in enumerate(test_loader):
        if use_gpu:
            images, target = images.cuda(), target.cuda()

        pred = net(images)
        loss = criterion(pred, target)
        validation_loss += loss.item()
    validation_loss /= len(test_loader)

    if best_test_loss > validation_loss:
        best_test_loss = validation_loss
        print('get best test loss %.5f' % best_test_loss)
        torch.save(net.state_dict(), 'checkpoints/best.pth')
    logfile.writelines(str(epoch) + '\t' + str(validation_loss) + '\n')
    logfile.flush()

eg1:

resume=Flase

use_resnet = True
if use_resnet:
    net = resnet50()
else:
    net = vgg16_bn()


if resume:
    print("loading weight from checkpoints/best.pth")
    net.load_state_dict(torch.load('checkpoints/best.pth'))
else:
    print('loading pre-trined model ......')
    if use_resnet:
        resnet = models.resnet50(pretrained=True)
        new_state_dict = resnet.state_dict()
        print(type(new_state_dict["conv1.weight"]),new_state_dict["conv1.weight"].dtype,(new_state_dict["conv1.weight"]).shape)
        input()
        dd = net.state_dict()
        # print(dd.keys())
        for k in new_state_dict.keys():
            print(k)
            print(len(k))
            # input()
            if k in dd.keys() and not k.startswith('fc'):
                # print(k)
                # print('yes')
                dd[k] = new_state_dict[k]
        # print(dd.keys())
        net.load_state_dict(dd)
    else:
        vgg = models.vgg16_bn(pretrained=True)
        new_state_dict = vgg.state_dict()
        dd = net.state_dict()
        for k in new_state_dict.keys():
            print(k)
            if k in dd.keys() and k.startswith('features'):
                print('yes')
                dd[k] = new_state_dict[k]
        net.load_state_dict(dd)

the train dataset has 22129 images
the test dataset has 4951 images
the batch_size is 4
loading pre-trined model ......
<class 'torch.Tensor'> torch.float32 torch.Size([64, 3, 7, 7])

conv1.weight
12
bn1.weight
10
bn1.bias
8
bn1.running_mean
16
bn1.running_var
15
bn1.num_batches_tracked
23
layer1.0.conv1.weight
21
layer1.0.bn1.weight
19
layer1.0.bn1.bias
17
layer1.0.bn1.running_mean
25
...

eg2:

resume=False
use_resnet = True
if use_resnet:
    net = resnet50()
else:
    net = vgg16_bn()

if resume:
    print("loading weight from checkpoints/best.pth")
    net.load_state_dict(torch.load('checkpoints/best.pth'))
else:
    print('loading pre-trined model ......')
    if use_resnet:
        resnet = models.resnet50(pretrained=True)
        new_state_dict = resnet.state_dict()
        print(type(new_state_dict["conv1.weight"]),new_state_dict["conv1.weight"].dtype,(new_state_dict["conv1.weight"]).shape)
        input()
        dd = net.state_dict()
        print(dd.keys())
        for k in new_state_dict.keys():
            # print(len(k))
            # input()
            if k in dd.keys() and not k.startswith('fc'):
                # print(k)
                # print('yes')
                dd[k] = new_state_dict[k]
        print(dd.keys())
        net.load_state_dict(dd)
    else:
        vgg = models.vgg16_bn(pretrained=True)
        new_state_dict = vgg.state_dict()
        dd = net.state_dict()
        for k in new_state_dict.keys():
            print(k)
            if k in dd.keys() and k.startswith('features'):
                print('yes')
                dd[k] = new_state_dict[k]
        net.load_state_dict(dd)

the train dataset has 22129 images
the test dataset has 4951 images
the batch_size is 4
loading pre-trined model ......
<class 'torch.Tensor'> torch.float32 torch.Size([64, 3, 7, 7])

odict_keys(['conv1.weight', 'bn1.weight', 'bn1.bias', 'bn1.running_mean', 'bn1.running_var', 'bn1.num_batches_tracked', 'layer1.0.conv1.weight', 'layer1.0.bn1.weight', 'layer1.0.bn1.bias', 'layer1.0.bn1.running_mean', 'layer1.0.bn1.running_var', 'layer1.0.bn1.num_batches_tracked', 'layer1.0.conv2.weight', 'layer1.0.bn2.weight', 'layer1.0.bn2.bias', 'layer1.0.bn2.running_mean', 'layer1.0.bn2.running_var', 'layer1.0.bn2.num_batches_tracked', 'layer1.0.conv3.weight', 'layer1.0.bn3.weight', 'layer1.0.bn3.bias', 'layer1.0.bn3.running_mean', 'layer1.0.bn3.running_var', 'layer1.0.bn3.num_batches_tracked', 'layer1.0.downsample.0.weight', 'layer1.0.downsample.1.weight', 'layer1.0.downsample.1.bias', 'layer1.0.downsample.1.running_mean', 'layer1.0.downsample.1.running_var', 'layer1.0.downsample.1.num_batches_tracked', 'layer1.1.conv1.weight', 'layer1.1.bn1.weight', 'layer1.1.bn1.bias', 'layer1.1.bn1.running_mean', 'layer1.1.bn1.running_var', 'layer1.1.bn1.num_batches_tracked', 'layer1.1.conv2.weight', 'layer1.1.bn2.weight', 'layer1.1.bn2.bias', 'layer1.1.bn2.running_mean', 'layer1.1.bn2.running_var', 'layer1.1.bn2.num_batches_tracked', 'layer1.1.conv3.weight', 'layer1.1.bn3.weight', 'layer1.1.bn3.bias', 'layer1.1.bn3.running_mean', 'layer1.1.bn3.running_var', 'layer1.1.bn3.num_batches_tracked', 'layer1.2.conv1.weight', 'layer1.2.bn1.weight', 'layer1.2.bn1.bias', 'layer1.2.bn1.running_mean', 'layer1.2.bn1.running_var', 'layer1.2.bn1.num_batches_tracked', 'layer1.2.conv2.weight', 'layer1.2.bn2.weight', 'layer1.2.bn2.bias', 'layer1.2.bn2.running_mean', 'layer1.2.bn2.running_var', 'layer1.2.bn2.num_batches_tracked', 'layer1.2.conv3.weight', 'layer1.2.bn3.weight', 'layer1.2.bn3.bias', 'layer1.2.bn3.running_mean', 'layer1.2.bn3.running_var', 'layer1.2.bn3.num_batches_tracked', 'layer2.0.conv1.weight', 'layer2.0.bn1.weight', 'layer2.0.bn1.bias', 'layer2.0.bn1.running_mean', 'layer2.0.bn1.running_var', 'layer2.0.bn1.num_batches_tracked', 'layer2.0.conv2.weight', 'layer2.0.bn2.weight', 'layer2.0.bn2.bias', 'layer2.0.bn2.running_mean', 'layer2.0.bn2.running_var', 'layer2.0.bn2.num_batches_tracked', 'layer2.0.conv3.weight', 'layer2.0.bn3.weight', 'layer2.0.bn3.bias', 'layer2.0.bn3.running_mean', 'layer2.0.bn3.running_var', 'layer2.0.bn3.num_batches_tracked', 'layer2.0.downsample.0.weight', 'layer2.0.downsample.1.weight', 'layer2.0.downsample.1.bias', 'layer2.0.downsample.1.running_mean', 'layer2.0.downsample.1.running_var', 'layer2.0.downsample.1.num_batches_tracked', 'layer2.1.conv1.weight', 'layer2.1.bn1.weight', 'layer2.1.bn1.bias', 'layer2.1.bn1.running_mean', 'layer2.1.bn1.running_var', 'layer2.1.bn1.num_batches_tracked', 'layer2.1.conv2.weight', 'layer2.1.bn2.weight', 'layer2.1.bn2.bias', 'layer2.1.bn2.running_mean', 'layer2.1.bn2.running_var', 'layer2.1.bn2.num_batches_tracked', 'layer2.1.conv3.weight', 'layer2.1.bn3.weight', 'layer2.1.bn3.bias', 'layer2.1.bn3.running_mean', 'layer2.1.bn3.running_var', 'layer2.1.bn3.num_batches_tracked', 'layer2.2.conv1.weight', 'layer2.2.bn1.weight', 'layer2.2.bn1.bias', 'layer2.2.bn1.running_mean', 'layer2.2.bn1.running_var', 'layer2.2.bn1.num_batches_tracked', 'layer2.2.conv2.weight', 'layer2.2.bn2.weight', 'layer2.2.bn2.bias', 'layer2.2.bn2.running_mean', 'layer2.2.bn2.running_var', 'layer2.2.bn2.num_batches_tracked', 'layer2.2.conv3.weight', 'layer2.2.bn3.weight', 'layer2.2.bn3.bias', 'layer2.2.bn3.running_mean', 'layer2.2.bn3.running_var', 'layer2.2.bn3.num_batches_tracked', 'layer2.3.conv1.weight', 'layer2.3.bn1.weight', 'layer2.3.bn1.bias', 'layer2.3.bn1.running_mean', 'layer2.3.bn1.running_var', 'layer2.3.bn1.num_batches_tracked', 'layer2.3.conv2.weight', 'layer2.3.bn2.weight', 'layer2.3.bn2.bias', 'layer2.3.bn2.running_mean', 'layer2.3.bn2.running_var', 'layer2.3.bn2.num_batches_tracked', 'layer2.3.conv3.weight', 'layer2.3.bn3.weight', 'layer2.3.bn3.bias', 'layer2.3.bn3.running_mean', 'layer2.3.bn3.running_var', 'layer2.3.bn3.num_batches_tracked', 'layer3.0.conv1.weight', 'layer3.0.bn1.weight', 'layer3.0.bn1.bias', 'layer3.0.bn1.running_mean', 'layer3.0.bn1.running_var', 'layer3.0.bn1.num_batches_tracked', 'layer3.0.conv2.weight', 'layer3.0.bn2.weight', 'layer3.0.bn2.bias', 'layer3.0.bn2.running_mean', 'layer3.0.bn2.running_var', 'layer3.0.bn2.num_batches_tracked', 'layer3.0.conv3.weight', 'layer3.0.bn3.weight', 'layer3.0.bn3.bias', 'layer3.0.bn3.running_mean', 'layer3.0.bn3.running_var', 'layer3.0.bn3.num_batches_tracked', 'layer3.0.downsample.0.weight', 'layer3.0.downsample.1.weight', 'layer3.0.downsample.1.bias', 'layer3.0.downsample.1.running_mean', 'layer3.0.downsample.1.running_var', 'layer3.0.downsample.1.num_batches_tracked', 'layer3.1.conv1.weight', 'layer3.1.bn1.weight', 'layer3.1.bn1.bias', 'layer3.1.bn1.running_mean', 'layer3.1.bn1.running_var', 'layer3.1.bn1.num_batches_tracked', 'layer3.1.conv2.weight', 'layer3.1.bn2.weight', 'layer3.1.bn2.bias', 'layer3.1.bn2.running_mean', 'layer3.1.bn2.running_var', 'layer3.1.bn2.num_batches_tracked', 'layer3.1.conv3.weight', 'layer3.1.bn3.weight', 'layer3.1.bn3.bias', 'layer3.1.bn3.running_mean', 'layer3.1.bn3.running_var', 'layer3.1.bn3.num_batches_tracked', 'layer3.2.conv1.weight', 'layer3.2.bn1.weight', 'layer3.2.bn1.bias', 'layer3.2.bn1.running_mean', 'layer3.2.bn1.running_var', 'layer3.2.bn1.num_batches_tracked', 'layer3.2.conv2.weight', 'layer3.2.bn2.weight', 'layer3.2.bn2.bias', 'layer3.2.bn2.running_mean', 'layer3.2.bn2.running_var', 'layer3.2.bn2.num_batches_tracked', 'layer3.2.conv3.weight', 'layer3.2.bn3.weight', 'layer3.2.bn3.bias', 'layer3.2.bn3.running_mean', 'layer3.2.bn3.running_var', 'layer3.2.bn3.num_batches_tracked', 'layer3.3.conv1.weight', 'layer3.3.bn1.weight', 'layer3.3.bn1.bias', 'layer3.3.bn1.running_mean', 'layer3.3.bn1.running_var', 'layer3.3.bn1.num_batches_tracked', 'layer3.3.conv2.weight', 'layer3.3.bn2.weight', 'layer3.3.bn2.bias', 'layer3.3.bn2.running_mean', 'layer3.3.bn2.running_var', 'layer3.3.bn2.num_batches_tracked', 'layer3.3.conv3.weight', 'layer3.3.bn3.weight', 'layer3.3.bn3.bias', 'layer3.3.bn3.running_mean', 'layer3.3.bn3.running_var', 'layer3.3.bn3.num_batches_tracked', 'layer3.4.conv1.weight', 'layer3.4.bn1.weight', 'layer3.4.bn1.bias', 'layer3.4.bn1.running_mean', 'layer3.4.bn1.running_var', 'layer3.4.bn1.num_batches_tracked', 'layer3.4.conv2.weight', 'layer3.4.bn2.weight', 'layer3.4.bn2.bias', 'layer3.4.bn2.running_mean', 'layer3.4.bn2.running_var', 'layer3.4.bn2.num_batches_tracked', 'layer3.4.conv3.weight', 'layer3.4.bn3.weight', 'layer3.4.bn3.bias', 'layer3.4.bn3.running_mean', 'layer3.4.bn3.running_var', 'layer3.4.bn3.num_batches_tracked', 'layer3.5.conv1.weight', 'layer3.5.bn1.weight', 'layer3.5.bn1.bias', 'layer3.5.bn1.running_mean', 'layer3.5.bn1.running_var', 'layer3.5.bn1.num_batches_tracked', 'layer3.5.conv2.weight', 'layer3.5.bn2.weight', 'layer3.5.bn2.bias', 'layer3.5.bn2.running_mean', 'layer3.5.bn2.running_var', 'layer3.5.bn2.num_batches_tracked', 'layer3.5.conv3.weight', 'layer3.5.bn3.weight', 'layer3.5.bn3.bias', 'layer3.5.bn3.running_mean', 'layer3.5.bn3.running_var', 'layer3.5.bn3.num_batches_tracked', 'layer4.0.conv1.weight', 'layer4.0.bn1.weight', 'layer4.0.bn1.bias', 'layer4.0.bn1.running_mean', 'layer4.0.bn1.running_var', 'layer4.0.bn1.num_batches_tracked', 'layer4.0.conv2.weight', 'layer4.0.bn2.weight', 'layer4.0.bn2.bias', 'layer4.0.bn2.running_mean', 'layer4.0.bn2.running_var', 'layer4.0.bn2.num_batches_tracked', 'layer4.0.conv3.weight', 'layer4.0.bn3.weight', 'layer4.0.bn3.bias', 'layer4.0.bn3.running_mean', 'layer4.0.bn3.running_var', 'layer4.0.bn3.num_batches_tracked', 'layer4.0.downsample.0.weight', 'layer4.0.downsample.1.weight', 'layer4.0.downsample.1.bias', 'layer4.0.downsample.1.running_mean', 'layer4.0.downsample.1.running_var', 'layer4.0.downsample.1.num_batches_tracked', 'layer4.1.conv1.weight', 'layer4.1.bn1.weight', 'layer4.1.bn1.bias', 'layer4.1.bn1.running_mean', 'layer4.1.bn1.running_var', 'layer4.1.bn1.num_batches_tracked', 'layer4.1.conv2.weight', 'layer4.1.bn2.weight', 'layer4.1.bn2.bias', 'layer4.1.bn2.running_mean', 'layer4.1.bn2.running_var', 'layer4.1.bn2.num_batches_tracked', 'layer4.1.conv3.weight', 'layer4.1.bn3.weight', 'layer4.1.bn3.bias', 'layer4.1.bn3.running_mean', 'layer4.1.bn3.running_var', 'layer4.1.bn3.num_batches_tracked', 'layer4.2.conv1.weight', 'layer4.2.bn1.weight', 'layer4.2.bn1.bias', 'layer4.2.bn1.running_mean', 'layer4.2.bn1.running_var', 'layer4.2.bn1.num_batches_tracked', 'layer4.2.conv2.weight', 'layer4.2.bn2.weight', 'layer4.2.bn2.bias', 'layer4.2.bn2.running_mean', 'layer4.2.bn2.running_var', 'layer4.2.bn2.num_batches_tracked', 'layer4.2.conv3.weight', 'layer4.2.bn3.weight', 'layer4.2.bn3.bias', 'layer4.2.bn3.running_mean', 'layer4.2.bn3.running_var', 'layer4.2.bn3.num_batches_tracked', 'layer5.0.conv1.weight', 'layer5.0.bn1.weight', 'layer5.0.bn1.bias', 'layer5.0.bn1.running_mean', 'layer5.0.bn1.running_var', 'layer5.0.bn1.num_batches_tracked', 'layer5.0.conv2.weight', 'layer5.0.bn2.weight', 'layer5.0.bn2.bias', 'layer5.0.bn2.running_mean', 'layer5.0.bn2.running_var', 'layer5.0.bn2.num_batches_tracked', 'layer5.0.conv3.weight', 'layer5.0.bn3.weight', 'layer5.0.bn3.bias', 'layer5.0.bn3.running_mean', 'layer5.0.bn3.running_var', 'layer5.0.bn3.num_batches_tracked', 'layer5.0.downsample.0.weight', 'layer5.0.downsample.1.weight', 'layer5.0.downsample.1.bias', 'layer5.0.downsample.1.running_mean', 'layer5.0.downsample.1.running_var', 'layer5.0.downsample.1.num_batches_tracked', 'layer5.1.conv1.weight', 'layer5.1.bn1.weight', 'layer5.1.bn1.bias', 'layer5.1.bn1.running_mean', 'layer5.1.bn1.running_var', 'layer5.1.bn1.num_batches_tracked', 'layer5.1.conv2.weight', 'layer5.1.bn2.weight', 'layer5.1.bn2.bias', 'layer5.1.bn2.running_mean', 'layer5.1.bn2.running_var', 'layer5.1.bn2.num_batches_tracked', 'layer5.1.conv3.weight', 'layer5.1.bn3.weight', 'layer5.1.bn3.bias', 'layer5.1.bn3.running_mean', 'layer5.1.bn3.running_var', 'layer5.1.bn3.num_batches_tracked', 'layer5.2.conv1.weight', 'layer5.2.bn1.weight', 'layer5.2.bn1.bias', 'layer5.2.bn1.running_mean', 'layer5.2.bn1.running_var', 'layer5.2.bn1.num_batches_tracked', 'layer5.2.conv2.weight', 'layer5.2.bn2.weight', 'layer5.2.bn2.bias', 'layer5.2.bn2.running_mean', 'layer5.2.bn2.running_var', 'layer5.2.bn2.num_batches_tracked', 'layer5.2.conv3.weight', 'layer5.2.bn3.weight', 'layer5.2.bn3.bias', 'layer5.2.bn3.running_mean', 'layer5.2.bn3.running_var', 'layer5.2.bn3.num_batches_tracked', 'conv_end.weight', 'bn_end.weight', 'bn_end.bias', 'bn_end.running_mean', 'bn_end.running_var', 'bn_end.num_batches_tracked'])
odict_keys(['conv1.weight', 'bn1.weight', 'bn1.bias', 'bn1.running_mean', 'bn1.running_var', 'bn1.num_batches_tracked', 'layer1.0.conv1.weight', 'layer1.0.bn1.weight', 'layer1.0.bn1.bias', 'layer1.0.bn1.running_mean', 'layer1.0.bn1.running_var', 'layer1.0.bn1.num_batches_tracked', 'layer1.0.conv2.weight', 'layer1.0.bn2.weight', 'layer1.0.bn2.bias', 'layer1.0.bn2.running_mean', 'layer1.0.bn2.running_var', 'layer1.0.bn2.num_batches_tracked', 'layer1.0.conv3.weight', 'layer1.0.bn3.weight', 'layer1.0.bn3.bias', 'layer1.0.bn3.running_mean', 'layer1.0.bn3.running_var', 'layer1.0.bn3.num_batches_tracked', 'layer1.0.downsample.0.weight', 'layer1.0.downsample.1.weight', 'layer1.0.downsample.1.bias', 'layer1.0.downsample.1.running_mean', 'layer1.0.downsample.1.running_var', 'layer1.0.downsample.1.num_batches_tracked', 'layer1.1.conv1.weight', 'layer1.1.bn1.weight', 'layer1.1.bn1.bias', 'layer1.1.bn1.running_mean', 'layer1.1.bn1.running_var', 'layer1.1.bn1.num_batches_tracked', 'layer1.1.conv2.weight', 'layer1.1.bn2.weight', 'layer1.1.bn2.bias', 'layer1.1.bn2.running_mean', 'layer1.1.bn2.running_var', 'layer1.1.bn2.num_batches_tracked', 'layer1.1.conv3.weight', 'layer1.1.bn3.weight', 'layer1.1.bn3.bias', 'layer1.1.bn3.running_mean', 'layer1.1.bn3.running_var', 'layer1.1.bn3.num_batches_tracked', 'layer1.2.conv1.weight', 'layer1.2.bn1.weight', 'layer1.2.bn1.bias', 'layer1.2.bn1.running_mean', 'layer1.2.bn1.running_var', 'layer1.2.bn1.num_batches_tracked', 'layer1.2.conv2.weight', 'layer1.2.bn2.weight', 'layer1.2.bn2.bias', 'layer1.2.bn2.running_mean', 'layer1.2.bn2.running_var', 'layer1.2.bn2.num_batches_tracked', 'layer1.2.conv3.weight', 'layer1.2.bn3.weight', 'layer1.2.bn3.bias', 'layer1.2.bn3.running_mean', 'layer1.2.bn3.running_var', 'layer1.2.bn3.num_batches_tracked', 'layer2.0.conv1.weight', 'layer2.0.bn1.weight', 'layer2.0.bn1.bias', 'layer2.0.bn1.running_mean', 'layer2.0.bn1.running_var', 'layer2.0.bn1.num_batches_tracked', 'layer2.0.conv2.weight', 'layer2.0.bn2.weight', 'layer2.0.bn2.bias', 'layer2.0.bn2.running_mean', 'layer2.0.bn2.running_var', 'layer2.0.bn2.num_batches_tracked', 'layer2.0.conv3.weight', 'layer2.0.bn3.weight', 'layer2.0.bn3.bias', 'layer2.0.bn3.running_mean', 'layer2.0.bn3.running_var', 'layer2.0.bn3.num_batches_tracked', 'layer2.0.downsample.0.weight', 'layer2.0.downsample.1.weight', 'layer2.0.downsample.1.bias', 'layer2.0.downsample.1.running_mean', 'layer2.0.downsample.1.running_var', 'layer2.0.downsample.1.num_batches_tracked', 'layer2.1.conv1.weight', 'layer2.1.bn1.weight', 'layer2.1.bn1.bias', 'layer2.1.bn1.running_mean', 'layer2.1.bn1.running_var', 'layer2.1.bn1.num_batches_tracked', 'layer2.1.conv2.weight', 'layer2.1.bn2.weight', 'layer2.1.bn2.bias', 'layer2.1.bn2.running_mean', 'layer2.1.bn2.running_var', 'layer2.1.bn2.num_batches_tracked', 'layer2.1.conv3.weight', 'layer2.1.bn3.weight', 'layer2.1.bn3.bias', 'layer2.1.bn3.running_mean', 'layer2.1.bn3.running_var', 'layer2.1.bn3.num_batches_tracked', 'layer2.2.conv1.weight', 'layer2.2.bn1.weight', 'layer2.2.bn1.bias', 'layer2.2.bn1.running_mean', 'layer2.2.bn1.running_var', 'layer2.2.bn1.num_batches_tracked', 'layer2.2.conv2.weight', 'layer2.2.bn2.weight', 'layer2.2.bn2.bias', 'layer2.2.bn2.running_mean', 'layer2.2.bn2.running_var', 'layer2.2.bn2.num_batches_tracked', 'layer2.2.conv3.weight', 'layer2.2.bn3.weight', 'layer2.2.bn3.bias', 'layer2.2.bn3.running_mean', 'layer2.2.bn3.running_var', 'layer2.2.bn3.num_batches_tracked', 'layer2.3.conv1.weight', 'layer2.3.bn1.weight', 'layer2.3.bn1.bias', 'layer2.3.bn1.running_mean', 'layer2.3.bn1.running_var', 'layer2.3.bn1.num_batches_tracked', 'layer2.3.conv2.weight', 'layer2.3.bn2.weight', 'layer2.3.bn2.bias', 'layer2.3.bn2.running_mean', 'layer2.3.bn2.running_var', 'layer2.3.bn2.num_batches_tracked', 'layer2.3.conv3.weight', 'layer2.3.bn3.weight', 'layer2.3.bn3.bias', 'layer2.3.bn3.running_mean', 'layer2.3.bn3.running_var', 'layer2.3.bn3.num_batches_tracked', 'layer3.0.conv1.weight', 'layer3.0.bn1.weight', 'layer3.0.bn1.bias', 'layer3.0.bn1.running_mean', 'layer3.0.bn1.running_var', 'layer3.0.bn1.num_batches_tracked', 'layer3.0.conv2.weight', 'layer3.0.bn2.weight', 'layer3.0.bn2.bias', 'layer3.0.bn2.running_mean', 'layer3.0.bn2.running_var', 'layer3.0.bn2.num_batches_tracked', 'layer3.0.conv3.weight', 'layer3.0.bn3.weight', 'layer3.0.bn3.bias', 'layer3.0.bn3.running_mean', 'layer3.0.bn3.running_var', 'layer3.0.bn3.num_batches_tracked', 'layer3.0.downsample.0.weight', 'layer3.0.downsample.1.weight', 'layer3.0.downsample.1.bias', 'layer3.0.downsample.1.running_mean', 'layer3.0.downsample.1.running_var', 'layer3.0.downsample.1.num_batches_tracked', 'layer3.1.conv1.weight', 'layer3.1.bn1.weight', 'layer3.1.bn1.bias', 'layer3.1.bn1.running_mean', 'layer3.1.bn1.running_var', 'layer3.1.bn1.num_batches_tracked', 'layer3.1.conv2.weight', 'layer3.1.bn2.weight', 'layer3.1.bn2.bias', 'layer3.1.bn2.running_mean', 'layer3.1.bn2.running_var', 'layer3.1.bn2.num_batches_tracked', 'layer3.1.conv3.weight', 'layer3.1.bn3.weight', 'layer3.1.bn3.bias', 'layer3.1.bn3.running_mean', 'layer3.1.bn3.running_var', 'layer3.1.bn3.num_batches_tracked', 'layer3.2.conv1.weight', 'layer3.2.bn1.weight', 'layer3.2.bn1.bias', 'layer3.2.bn1.running_mean', 'layer3.2.bn1.running_var', 'layer3.2.bn1.num_batches_tracked', 'layer3.2.conv2.weight', 'layer3.2.bn2.weight', 'layer3.2.bn2.bias', 'layer3.2.bn2.running_mean', 'layer3.2.bn2.running_var', 'layer3.2.bn2.num_batches_tracked', 'layer3.2.conv3.weight', 'layer3.2.bn3.weight', 'layer3.2.bn3.bias', 'layer3.2.bn3.running_mean', 'layer3.2.bn3.running_var', 'layer3.2.bn3.num_batches_tracked', 'layer3.3.conv1.weight', 'layer3.3.bn1.weight', 'layer3.3.bn1.bias', 'layer3.3.bn1.running_mean', 'layer3.3.bn1.running_var', 'layer3.3.bn1.num_batches_tracked', 'layer3.3.conv2.weight', 'layer3.3.bn2.weight', 'layer3.3.bn2.bias', 'layer3.3.bn2.running_mean', 'layer3.3.bn2.running_var', 'layer3.3.bn2.num_batches_tracked', 'layer3.3.conv3.weight', 'layer3.3.bn3.weight', 'layer3.3.bn3.bias', 'layer3.3.bn3.running_mean', 'layer3.3.bn3.running_var', 'layer3.3.bn3.num_batches_tracked', 'layer3.4.conv1.weight', 'layer3.4.bn1.weight', 'layer3.4.bn1.bias', 'layer3.4.bn1.running_mean', 'layer3.4.bn1.running_var', 'layer3.4.bn1.num_batches_tracked', 'layer3.4.conv2.weight', 'layer3.4.bn2.weight', 'layer3.4.bn2.bias', 'layer3.4.bn2.running_mean', 'layer3.4.bn2.running_var', 'layer3.4.bn2.num_batches_tracked', 'layer3.4.conv3.weight', 'layer3.4.bn3.weight', 'layer3.4.bn3.bias', 'layer3.4.bn3.running_mean', 'layer3.4.bn3.running_var', 'layer3.4.bn3.num_batches_tracked', 'layer3.5.conv1.weight', 'layer3.5.bn1.weight', 'layer3.5.bn1.bias', 'layer3.5.bn1.running_mean', 'layer3.5.bn1.running_var', 'layer3.5.bn1.num_batches_tracked', 'layer3.5.conv2.weight', 'layer3.5.bn2.weight', 'layer3.5.bn2.bias', 'layer3.5.bn2.running_mean', 'layer3.5.bn2.running_var', 'layer3.5.bn2.num_batches_tracked', 'layer3.5.conv3.weight', 'layer3.5.bn3.weight', 'layer3.5.bn3.bias', 'layer3.5.bn3.running_mean', 'layer3.5.bn3.running_var', 'layer3.5.bn3.num_batches_tracked', 'layer4.0.conv1.weight', 'layer4.0.bn1.weight', 'layer4.0.bn1.bias', 'layer4.0.bn1.running_mean', 'layer4.0.bn1.running_var', 'layer4.0.bn1.num_batches_tracked', 'layer4.0.conv2.weight', 'layer4.0.bn2.weight', 'layer4.0.bn2.bias', 'layer4.0.bn2.running_mean', 'layer4.0.bn2.running_var', 'layer4.0.bn2.num_batches_tracked', 'layer4.0.conv3.weight', 'layer4.0.bn3.weight', 'layer4.0.bn3.bias', 'layer4.0.bn3.running_mean', 'layer4.0.bn3.running_var', 'layer4.0.bn3.num_batches_tracked', 'layer4.0.downsample.0.weight', 'layer4.0.downsample.1.weight', 'layer4.0.downsample.1.bias', 'layer4.0.downsample.1.running_mean', 'layer4.0.downsample.1.running_var', 'layer4.0.downsample.1.num_batches_tracked', 'layer4.1.conv1.weight', 'layer4.1.bn1.weight', 'layer4.1.bn1.bias', 'layer4.1.bn1.running_mean', 'layer4.1.bn1.running_var', 'layer4.1.bn1.num_batches_tracked', 'layer4.1.conv2.weight', 'layer4.1.bn2.weight', 'layer4.1.bn2.bias', 'layer4.1.bn2.running_mean', 'layer4.1.bn2.running_var', 'layer4.1.bn2.num_batches_tracked', 'layer4.1.conv3.weight', 'layer4.1.bn3.weight', 'layer4.1.bn3.bias', 'layer4.1.bn3.running_mean', 'layer4.1.bn3.running_var', 'layer4.1.bn3.num_batches_tracked', 'layer4.2.conv1.weight', 'layer4.2.bn1.weight', 'layer4.2.bn1.bias', 'layer4.2.bn1.running_mean', 'layer4.2.bn1.running_var', 'layer4.2.bn1.num_batches_tracked', 'layer4.2.conv2.weight', 'layer4.2.bn2.weight', 'layer4.2.bn2.bias', 'layer4.2.bn2.running_mean', 'layer4.2.bn2.running_var', 'layer4.2.bn2.num_batches_tracked', 'layer4.2.conv3.weight', 'layer4.2.bn3.weight', 'layer4.2.bn3.bias', 'layer4.2.bn3.running_mean', 'layer4.2.bn3.running_var', 'layer4.2.bn3.num_batches_tracked', 'layer5.0.conv1.weight', 'layer5.0.bn1.weight', 'layer5.0.bn1.bias', 'layer5.0.bn1.running_mean', 'layer5.0.bn1.running_var', 'layer5.0.bn1.num_batches_tracked', 'layer5.0.conv2.weight', 'layer5.0.bn2.weight', 'layer5.0.bn2.bias', 'layer5.0.bn2.running_mean', 'layer5.0.bn2.running_var', 'layer5.0.bn2.num_batches_tracked', 'layer5.0.conv3.weight', 'layer5.0.bn3.weight', 'layer5.0.bn3.bias', 'layer5.0.bn3.running_mean', 'layer5.0.bn3.running_var', 'layer5.0.bn3.num_batches_tracked', 'layer5.0.downsample.0.weight', 'layer5.0.downsample.1.weight', 'layer5.0.downsample.1.bias', 'layer5.0.downsample.1.running_mean', 'layer5.0.downsample.1.running_var', 'layer5.0.downsample.1.num_batches_tracked', 'layer5.1.conv1.weight', 'layer5.1.bn1.weight', 'layer5.1.bn1.bias', 'layer5.1.bn1.running_mean', 'layer5.1.bn1.running_var', 'layer5.1.bn1.num_batches_tracked', 'layer5.1.conv2.weight', 'layer5.1.bn2.weight', 'layer5.1.bn2.bias', 'layer5.1.bn2.running_mean', 'layer5.1.bn2.running_var', 'layer5.1.bn2.num_batches_tracked', 'layer5.1.conv3.weight', 'layer5.1.bn3.weight', 'layer5.1.bn3.bias', 'layer5.1.bn3.running_mean', 'layer5.1.bn3.running_var', 'layer5.1.bn3.num_batches_tracked', 'layer5.2.conv1.weight', 'layer5.2.bn1.weight', 'layer5.2.bn1.bias', 'layer5.2.bn1.running_mean', 'layer5.2.bn1.running_var', 'layer5.2.bn1.num_batches_tracked', 'layer5.2.conv2.weight', 'layer5.2.bn2.weight', 'layer5.2.bn2.bias', 'layer5.2.bn2.running_mean', 'layer5.2.bn2.running_var', 'layer5.2.bn2.num_batches_tracked', 'layer5.2.conv3.weight', 'layer5.2.bn3.weight', 'layer5.2.bn3.bias', 'layer5.2.bn3.running_mean', 'layer5.2.bn3.running_var', 'layer5.2.bn3.num_batches_tracked', 'conv_end.weight', 'bn_end.weight', 'bn_end.bias', 'bn_end.running_mean', 'bn_end.running_var', 'bn_end.num_batches_tracked'])
this computer has gpu 1 and current is 0


Starting epoch 1 / 100
Learning Rate for this epoch: 0.001
Epoch [1/100], Iter [5/5533] Loss: 63.3935, average_loss: 72.0086
Epoch [1/100], Iter [10/5533] Loss: 48.9431, average_loss: 63.7175
Epoch [1/100], Iter [15/5533] Loss: 47.4720, average_loss: 54.4094
Epoch [1/100], Iter [20/5533] Loss: 21.6139, average_loss: 45.8016
Traceback (most recent call last):

eg3: