Q&A
>1と0が大量に表示されます
だけではわからないので、実際の結果をコピペして掲載してください。
#エラー内容
物体検出プログラムの学習時、1と0が大量に表示されます。エラーは出ません。参考サイトのプログラムでは動作したため、データセットの中身がおかしい？とも考えられますが、データセット作成時中身を見ても学習できたため完全に行き詰っています。。まったくわからないため教えていただきたいです。よろしくお願いします。
#エラーコード（エラーではない）
0
0
0
0
1
1
0
0
・・・
#エラーの出たプログラム
import chainer import cupy import chainercv import matplotlib import os import xml.etree.ElementTree as ET import numpy as np from chainercv.datasets import VOCBboxDataset bccd_labels = ('rock', 'mountain') class BCCDDataset(VOCBboxDataset): def _get_annotations(self, i): id_ = self.ids[i] anno = ET.parse( os.path.join(self.data_dir, 'Annotations', id_ + '.xml')) bbox = [] label = [] difficult = [] for obj in anno.findall('object'): bndbox_anno = obj.find('bndbox') bbox.append([ int(bndbox_anno.find(tag).text) - 1 for tag in ('ymin', 'xmin', 'ymax', 'xmax')]) name = obj.find('name').text.lower().strip() label.append(bccd_labels.index(name)) print(bccd_labels.index(obj.find('name').text.lower().strip())) bbox = np.stack(bbox).astype(np.float32) label = np.stack(label).astype(np.int32) difficult = np.array(difficult, dtype=np.bool) return bbox, label, difficult train_dataset = BCCDDataset('rock_detect_dataset/BCCD', 'train') valid_dataset = BCCDDataset('rock_detect_dataset/BCCD', 'val') test_dataset = BCCDDataset('rock_detect_dataset/BCCD', 'test') import chainer from chainercv.links import SSD300 from chainercv.links.model.ssd import multibox_loss class MultiboxTrainChain(chainer.Chain): def __init__(self, model, alpha=1, k=3): super(MultiboxTrainChain, self).__init__() with self.init_scope(): self.model = model self.alpha = alpha self.k = k def forward(self, imgs, gt_mb_locs, gt_mb_labels): mb_locs, mb_confs = self.model(imgs) loc_loss, conf_loss = multibox_loss( mb_locs, mb_confs, gt_mb_locs, gt_mb_labels, self.k) loss = loc_loss * self.alpha + conf_loss chainer.reporter.report( {'loss': loss, 'loss/loc': loc_loss, 'loss/conf': conf_loss}, self) return loss model = SSD300(n_fg_class=len(bccd_labels), pretrained_model='imagenet') train_chain = MultiboxTrainChain(model) import copy import numpy as np from chainercv import transforms from chainercv.links.model.ssd import random_crop_with_bbox_constraints from chainercv.links.model.ssd import random_distort from chainercv.links.model.ssd import resize_with_random_interpolation class Transform(object): def __init__(self, coder, size, mean): self.coder = copy.copy(coder) self.coder.to_cpu() self.size = size self.mean = mean def __call__(self, in_data): img, bbox, label = in_data img = random_distort(img) if np.random.randint(2): img, param = transforms.random_expand( img, fill=self.mean, return_param=True) bbox = transforms.translate_bbox( bbox, y_offset=param['y_offset'], x_offset=param['x_offset']) img, param = random_crop_with_bbox_constraints( img, bbox, return_param=True) bbox, param = transforms.crop_bbox( bbox, y_slice=param['y_slice'], x_slice=param['x_slice'], allow_outside_center=False, return_param=True) label = label[param['index']] _, H, W = img.shape img = resize_with_random_interpolation(img, (self.size, self.size)) bbox = transforms.resize_bbox(bbox, (H, W), (self.size, self.size)) img, params = transforms.random_flip( img, x_random=True, return_param=True) bbox = transforms.flip_bbox( bbox, (self.size, self.size), x_flip=params['x_flip']) img -= self.mean mb_loc, mb_label = self.coder.encode(bbox, label) return img, mb_loc, mb_label from chainer.datasets import TransformDataset from chainer.optimizer_hooks import WeightDecay from chainer import serializers from chainer import training from chainer.training import extensions from chainer.training import triggers from chainercv.extensions import DetectionVOCEvaluator from chainercv.links.model.ssd import GradientScaling chainer.cuda.set_max_workspace_size(1024 * 1024 * 1024) chainer.config.autotune = True batchsize = 32 gpu_id = 0 out = 'results' initial_lr = 0.001 training_epoch = 300 log_interval = 10, 'epoch' lr_decay_rate = 0.1 lr_decay_timing = [200, 250] transformed_train_dataset = TransformDataset(train_dataset, Transform(model.coder, model.insize, model.mean)) train_iter = chainer.iterators.MultiprocessIterator(transformed_train_dataset, batchsize) valid_iter = chainer.iterators.SerialIterator(valid_dataset, batchsize, repeat=False, shuffle=False) optimizer = chainer.optimizers.MomentumSGD() optimizer.setup(train_chain) for param in train_chain.params(): if param.name == 'b': param.update_rule.add_hook(GradientScaling(2)) else: param.update_rule.add_hook(WeightDecay(0.0005)) updater = training.updaters.StandardUpdater( train_iter, optimizer, device=gpu_id) trainer = training.Trainer( updater, (training_epoch, 'epoch'), out) trainer.extend( extensions.ExponentialShift('lr', lr_decay_rate, init=initial_lr), trigger=triggers.ManualScheduleTrigger(lr_decay_timing, 'epoch')) trainer.extend( DetectionVOCEvaluator( valid_iter, model, use_07_metric=False, label_names=bccd_labels), trigger=(1, 'epoch')) trainer.extend(extensions.LogReport(trigger=log_interval)) trainer.extend(extensions.observe_lr(), trigger=log_interval) trainer.extend(extensions.PrintReport( ['epoch', 'iteration', 'lr', 'main/loss', 'main/loss/loc', 'main/loss/conf', 'validation/main/map', 'elapsed_time']), trigger=log_interval) if extensions.PlotReport.available(): trainer.extend( extensions.PlotReport( ['main/loss', 'main/loss/loc', 'main/loss/conf'], 'epoch', file_name='loss.png')) trainer.extend( extensions.PlotReport( ['validation/main/map'], 'epoch', file_name='accuracy.png')) trainer.extend(extensions.snapshot( filename='snapshot_epoch_{.updater.epoch}.npz'), trigger=(10, 'epoch')) trainer.run()
#参考サイト学習画面
学習がきれいに進んでいます
jupyter
1epoch iteration lr main/loss main/loss/loc main/loss/conf validation/main/map elapsed_time 210 65 0.001 7.70718 2.17807 5.52911 0.114415 51.3745 320 129 0.001 4.29963 1.64196 2.65768 0.110095 96.4896 430 193 0.001 3.86515 1.45706 2.40808
回答1件
0
36行目のprint文を削除
投稿2019/11/27 05:29
総合スコア995
あなたの回答
tips
プレビュー
