編集履歴

質問編集履歴

コードの修正

2022/10/11 05:51

投稿

shinww

スコア4

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -24,137 +24,6 @@
 ### 該当のソースコード
-```ここに言語名を入力　python
-ソースコード
-```　train_imagenet.py
-from __future__ import print_function
-import argparse
-import datetime
-import json
-import multiprocessing
-import os
-import random
-import sys
-import threading
-import time
-import numpy as np
-from PIL import Image
-import six
-import six.moves.cPickle as pickle
-from six.moves import queue
-from chainer import computational_graph
-from chainer import cuda
-from chainer import optimizers
-from chainer import serializers
-parser = argparse.ArgumentParser(description='Learning convnet from ILSVRC2012 dataset')
-parser.add_argument('--train', help=r'D:\numadalab\2020\実験データ\20201114')
-parser.add_argument('--val', help=r'D:\numadalab\2020\実験データ\20201207_day')
-parser.add_argument('--mean', '-m', default='mean.npy',
-                    help='Path to the mean file (computed by compute_mean.py)')
-parser.add_argument('--arch', '-a', default='nin',
-                    help='Convnet architecture \
-                    (nin, alex, alexbn, googlenet, googlenetbn)')
-parser.add_argument('--batchsize', '-B', type=int, default=32,
-                    help='Learning minibatch size')
-parser.add_argument('--val_batchsize', '-b', type=int, default=250,
-                    help='Validation minibatch size')
-parser.add_argument('--epoch', '-E', default=50, type=int,
-                    help='Number of epochs to learn')
-parser.add_argument('--gpu', '-g', default=-1, type=int,
-                    help='GPU ID (negative value indicates CPU)')
-parser.add_argument('--loaderjob', '-j', default=20, type=int,
-                    help='Number of parallel data loading processes')
-parser.add_argument('--root', '-r', default='.',
-                    help='Root directory path of image files')
-parser.add_argument('--out', '-o', default='model',
-                    help='Path to save model on each validation')
-parser.add_argument('--outstate', '-s', default='state',
-                    help='Path to save optimizer state on each validation')
-parser.add_argument('--initmodel', default='',
-                    help='Initialize the model from given file')
-parser.add_argument('--resume', default='',
-                    help='Resume the optimization from snapshot')
-parser.add_argument('--test', dest='test', action='store_true')
-parser.set_defaults(test=False)
-#args = parser.parse_args(args=[])
-args = parser.parse_args()
-if args.gpu >= 0:
-    cuda.check_cuda_available()
-xp = cuda.cupy if args.gpu >= 0 else np
-assert 50000 % args.val_batchsize == 0
-if args.test:
-    denominator = 1
-else:
-    denominator = 100000
-def load_image_list(path, root):
-    tuples = []
-    for line in open(path):
-        pair = line.strip().split()
-        tuples.append((os.path.join(root, pair[0]), np.int32(pair[1])))
-    return tuples
-# Prepare dataset
-print(args.train)
-train_list = load_image_list(args.train, args.root)
-val_list = load_image_list(args.val, args.root)
-mean_image = np.load(args.mean,allow_pickle=True)
-**# Prepare model   **
-if args.arch == 'nin':
-    import nin
-    model = nin.NIN()
-elif args.arch == 'i2vvgg':
-    import i2vvgg
-    model = i2vvgg.i2vVGG()
-elif args.arch == 'alex':
-    import alex
-    model = alex.Alex()
-elif args.arch == 'alexbn':
-    import alexbn
-    model = alexbn.AlexBN()
-elif args.arch == 'googlenet':
-    import googlenet
-    model = googlenet.GoogLeNet()
-elif args.arch == 'googlenetbn':
-    import googlenetbn
-    model = googlenetbn.GoogLeNetBN()
-    else:
-    raise ValueError('Invalid architecture name')
-if args.gpu >= 0:
-    cuda.get_device(args.gpu).use()
-    model.to_gpu()
-# Setup optimizer
-optimizer = optimizers.MomentumSGD(lr=0.01, momentum=0.9)
-optimizer.setup(model)
-# Init/Resume
-if args.initmodel:
-    print('Load model from', args.initmodel)
-    serializers.load_npz(args.initmodel, model)
-if args.resume:
-    print('Load optimizer state from', args.resume)
-    serializers.load_npz(args.resume, optimizer)
 ```ここに言語を入力　python
 コード　nin.py
@@ -190,42 +59,4 @@
         self.loss = None
         self.accuracy = None
-    def __call__(self, x, t):
-        self.clear()
-        h = F.max_pooling_2d(F.relu(self.mlpconv1(x)), 3, stride=2)
-        h = F.max_pooling_2d(F.relu(self.mlpconv2(h)), 3, stride=2)
-        h = F.max_pooling_2d(F.relu(self.mlpconv3(h)), 3, stride=2)
-        h = self.mlpconv4(F.dropout(h, train=self.train))
-        h = F.reshape(F.average_pooling_2d(h, 6), (x.data.shape[0], 1000))
-        self.loss = F.softmax_cross_entropy(h, t)
-        self.accuracy = F.accuracy(h, t)
-        return self.loss
-    def predict(self, x_data, train=False):
-        x = chainer.Variable(x_data, volatile=True)
-        h = F.relu(self.conv1(x))
-        h = F.relu(self.conv1a(h))
-        h = F.relu(self.conv1b(h))
-        h = F.max_pooling_2d(h, 3, stride=2)
-        h = F.relu(self.conv2(h))
-        h = F.relu(self.conv2a(h))
-        h = F.relu(self.conv2b(h))
-        h = F.max_pooling_2d(h, 3, stride=2)
-        h = F.relu(self.conv3(h))
-        h = F.relu(self.conv3a(h))
-        h = F.relu(self.conv3b(h))
-        h = F.max_pooling_2d(h, 3, stride=2)
-        h = F.dropout(h, train=train)
-        h = F.relu(self.conv4(h))
-        h = F.relu(self.conv4a(h))
-        h = F.relu(self.conv4b(h))
-        h = F.reshape(F.average_pooling_2d(h, 6), (x_data.shape[0], 1000))
-        return F.softmax(h)
-### 補足情報（FW/ツールのバージョンなど）
-ここにより詳細な情報を記載してください。

Chainer 機械学習