def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) # img, bbox, label, scale = dataset[0] # 返回的img是被scale后的图像,可能已经被随机翻转了 # 返回的 bbox 按照 ymin xmin ymax xmax 排列 # H, W = size(im) # 对于一张屏幕上显示的图片,a,b,c,d 代表 4 个顶点 # a ... b ymin # . . # c ... d ymax H高度 y的范围在 [0, H-1] 间 # xmin xmax # W宽度 x的范围在 [0, W-1] 间 print('load data') dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn) if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) for epoch in range(opt.epoch): for ii, (img, bbox_, label_, scale) in (enumerate(dataloader)): print('step: ', ii) scale = at.scalar(scale) img, bbox, label = img.float(), bbox_, label_ img, bbox, label = Variable(img), Variable(bbox), Variable(label) trainer.train_step(img, bbox, label, scale) if ((ii + 1) % opt.plot_every == 0) and (epoch > 50): # 运行多少步以后再predict一次,epoch跑的太少的话根本预测不准什么东西 # if os.path.exists(opt.debug_file): # ipdb.set_trace() # plot groud truth bboxes 画出原本的框 ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) # gt_img np类型 范围是 [0, 1] 间 3 x H x W # 这里要将 gt_img 这个带框,带标注的图像保存或者显示出来 # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0]))
def eval(dataloader, faster_rcnn, vis, test_num=10000): pred_bboxes, pred_labels, pred_scores = list(), list(), list() gt_bboxes, gt_labels, gt_difficults = list(), list(), list() for ii, (imgs, sizes, gt_bboxes_, gt_labels_, gt_difficults_) in tqdm(enumerate(dataloader)): # plot groud truth bboxes sizes = [sizes[0][0].item(), sizes[1][0].item()] pred_bboxes_, pred_labels_, pred_scores_ = faster_rcnn.predict( imgs, [sizes]) img = imgs.cuda().float() ori_img_ = inverse_normalize(at.tonumpy(img[0])) pred_img = visdom_bbox(ori_img_, at.tonumpy(pred_bboxes_[0]), at.tonumpy(pred_labels_[0]).reshape(-1), at.tonumpy(pred_scores_[0])) vis.img('test_pred_img', pred_img) gt_bboxes += list(gt_bboxes_.numpy()) gt_labels += list(gt_labels_.numpy()) gt_difficults += list(gt_difficults_.numpy()) pred_bboxes += pred_bboxes_ pred_labels += pred_labels_ pred_scores += pred_scores_ if ii == test_num: break result = eval_detection_voc(pred_bboxes, pred_labels, pred_scores, gt_bboxes, gt_labels, gt_difficults, use_07_metric=True) return result
def test(img): img = t.from_numpy(img)[None] opt.caffe_pretrain=False # this model was trained from caffe-pretrained model _bboxes, _labels, _scores = trainer.faster_rcnn.predict(img, visualize=True) #output the 坐标 bboxes = at.tonumpy(_bboxes[0]) print(bboxes) #输出框的坐标,array格式 test_img = visdom_bbox(at.tonumpy(img[0]), at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0]).reshape(-1)) trainer.vis.img('test_img', test_img)
def predict(load_path, **kwargs): """ """ """parse parameters""" opt.load_path = load_path opt.parse(kwargs) """get images to be predicted""" if not os.path.isdir(opt.predict_output_dir): os.mkdir(opt.predict_output_dir) img_files = os.listdir(opt.predict_input_dir) img_files.sort() img_paths = [ os.path.join(opt.predict_input_dir, name) for name in img_files ] """create model""" rfcn_md = RFCN_ResNet101() print('model construct completed') rfcn_trainer = RFCN_Trainer(rfcn_md).cuda() if opt.load_path: rfcn_trainer.load(opt.load_path, load_viz_idx=opt.load_viz_x) print('load pretrained model from %s' % opt.load_path) """predict""" for img_path in tqdm(img_paths): raw_img = read_image(img_path, color=True) # plot predict bboxes b_bboxes, b_labels, b_scores = rfcn_trainer.r_fcn.predict( [raw_img], visualize=True) pred_img = visdom_bbox(raw_img, tonumpy(b_bboxes[0]), tonumpy(b_labels[0]).reshape(-1), tonumpy(b_scores[0])) file_name, file_ext = os.path.splitext(os.path.basename(img_path)) result = np.hstack([ b_labels[0][:, np.newaxis], b_scores[0][:, np.newaxis], b_bboxes[0] ]) # output to file file_out_path = os.path.join(opt.predict_output_dir, 'res_' + file_name + '.txt') np.savetxt(file_out_path, result, fmt='%.2f', delimiter=',') img_out_path = os.path.join(opt.predict_output_dir, file_name + '_res.jpg') pred_img = np.flipud(pred_img).transpose((1, 2, 0)) * 255 cv2.imwrite(img_out_path, pred_img) print('Done!')
def test(**kwargs): opt._parse(kwargs) faster_rcnn = FasterRCNNVGG16() trainer = FasterRCNNTrainer(faster_rcnn).cuda() trainer.load( 'C:/Users/86188/Desktop/simple-faster-rcnn-pytorch-master/checkpoints/fasterrcnn_08042317_0.9090909090909093' ) print('load successs!') img = read_image('test_img/test.jpg') img = t.from_numpy(img)[None] opt.caffe_pretrain = False # this model was trained from caffe-pretrained model _bboxes, _labels, _scores = trainer.faster_rcnn.predict(img, visualize=True) test_img = visdom_bbox(at.tonumpy(img[0]), at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0]).reshape(-1)) trainer.vis.img('test_img', test_img)
def detec_test_pic(pth, pic_test): opt.load_path = opt.caffe_pretrain_path opt.env = 'detec-tset-pic' faster_rcnn = FasterRCNNVGG16() trainer = FasterRCNNTrainer(faster_rcnn).cuda() trainer.load(pth) opt.caffe_pretrain = True # this model was trained from caffe-pretrained model pic_index = 0 for pic in tqdm(os.listdir(pic_test)): time.sleep(1) img = read_image(os.path.join(pic_test, pic)) img = t.from_numpy(img)[None] _bboxes, _labels, _scores = trainer.faster_rcnn.predict(img, visualize=True) pred_img = visdom_bbox(at.tonumpy(img[0]), at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0]).reshape(-1)) trainer.vis.img('pred_img', pred_img) pic_index += 1 if pic_index > 1000: break
def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) print('load data') dataloader = data_.DataLoader(dataset, batch_size=1, shuffle=True, # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, pin_memory=True ) testset_all = TestDataset_all(opt, 'test2') test_all_dataloader = data_.DataLoader(testset_all, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, pin_memory=True ) tsf = Transform(opt.min_size, opt.max_size) faster_rcnn = FasterRCNNVGG16() trainer = FasterRCNNTrainer(faster_rcnn).cuda() print('model construct completed') # 加载训练过的模型,在config配置路径就可以了 if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) #提取蒸馏知识所需要的软标签 if opt.is_distillation == True: opt.predict_socre = 0.3 for ii, (imgs, sizes, gt_bboxes_, gt_labels_, scale, id_) in tqdm(enumerate(dataloader)): if len(gt_bboxes_) == 0: continue sizes = [sizes[0][0].item(), sizes[1][0].item()] pred_bboxes_, pred_labels_, pred_scores_, features_ = trainer.faster_rcnn.predict(imgs, [ sizes]) img_file = os.path.join( opt.voc_data_dir, 'JPEGImages', id_[0] + '.jpg') ori_img = read_image(img_file, color=True) img, pred_bboxes_, pred_labels_, scale_ = tsf( (ori_img, pred_bboxes_[0], pred_labels_[0])) #去除软标签和真值标签重叠过多的部分,去除错误的软标签 pred_bboxes_, pred_labels_, pred_scores_ = py_cpu_nms( gt_bboxes_[0], gt_labels_[0], pred_bboxes_, pred_labels_, pred_scores_[0]) #存储软标签,这样存储不会使得GPU占用过多 np.save('label/' + str(id_[0]) + '.npy', pred_labels_) np.save('bbox/' + str(id_[0]) + '.npy', pred_bboxes_) np.save('feature/' + str(id_[0]) + '.npy', features_) np.save('score/' + str(id_[0]) + '.npy', pred_scores_) opt.predict_socre = 0.05 t.cuda.empty_cache() # visdom 显示所有类别标签名 trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr for epoch in range(opt.epoch): print('epoch=%d' % epoch) # 重置混淆矩阵 trainer.reset_meters() # tqdm可以在长循环中添加一个进度提示信息,用户只需要封装任意的迭代器 tqdm(iterator), # 是一个快速、扩展性强 for ii, (img, sizes, bbox_, label_, scale, id_) in tqdm(enumerate(dataloader)): if len(bbox_) == 0: continue scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() # 训练的就这一步 下面的都是打印的信息 # 转化成pytorch能够计算的格式,转tensor格式 if opt.is_distillation == True: #读取软标签 teacher_pred_labels = np.load( 'label/' + str(id_[0]) + '.npy') teacher_pred_bboxes = np.load( 'bbox/' + str(id_[0]) + '.npy') teacher_pred_features_ = np.load( 'feature/' + str(id_[0]) + '.npy') teacher_pred_scores = np.load( 'score/' + str(id_[0]) + '.npy') #格式转换 teacher_pred_bboxes = teacher_pred_bboxes.astype(np.float32) teacher_pred_labels = teacher_pred_labels.astype(np.int32) teacher_pred_scores = teacher_pred_scores.astype(np.float32) #转成pytorch格式 teacher_pred_bboxes_ = at.totensor(teacher_pred_bboxes) teacher_pred_labels_ = at.totensor(teacher_pred_labels) teacher_pred_scores_ = at.totensor(teacher_pred_scores) teacher_pred_features_ = at.totensor(teacher_pred_features_) #使用GPU teacher_pred_bboxes_ = teacher_pred_bboxes_.cuda() teacher_pred_labels_ = teacher_pred_labels_.cuda() teacher_pred_scores_ = teacher_pred_scores_.cuda() teacher_pred_features_ = teacher_pred_features_.cuda() # 如果dataset.py 中的Transform 设置了图像翻转,就要使用这个判读软标签是否一起翻转 if(teacher_pred_bboxes_[0][1] != bbox[0][0][1]): _, o_C, o_H, o_W = img.shape teacher_pred_bboxes_ = flip_bbox( teacher_pred_bboxes_, (o_H, o_W), x_flip=True) losses = trainer.train_step(img, bbox, label, scale, epoch, teacher_pred_bboxes_, teacher_pred_labels_, teacher_pred_features_, teacher_pred_scores) else: trainer.train_step(img, bbox, label, scale, epoch) # visdom显示的信息 if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) gt_img = visdom_bbox(ori_img_, at.tonumpy(teacher_pred_bboxes_), at.tonumpy(teacher_pred_labels_), at.tonumpy(teacher_pred_scores_)) trainer.vis.img('gt_img_all', gt_img) # plot predicti bboxes _bboxes, _labels, _scores, _ = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # 混淆矩阵 # rpn confusion matrix(meter) trainer.vis.text( str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.text( str(trainer.roi_cm.value().tolist()), win='roi_cm') # trainer.vis.img('roi_cm', at.totensor( # trainer.roi_cm.value(), False).float()) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{},ap:{}, map:{},loss:{}'.format(str(lr_), str(eval_result['ap']), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) # 保存最好结果并记住路径 if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) if epoch == 20: trainer.save(best_map='20') result = eval(test_all_dataloader, trainer.faster_rcnn, test_num=5000) print('20result={}'.format(str(result))) # trainer.load(best_path) # result=eval(test_all_dataloader,trainer.faster_rcnn,test_num=5000) # print('bestmapresult={}'.format(str(result))) break # 每10轮加载前面最好权重,并且减少学习率 if epoch % 20 == 15: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay
def train(**kwargs): # *变量名, 表示任何多个无名参数, 它是一个tuple;**变量名, 表示关键字参数, 它是一个dict opt._parse(kwargs) # 识别参数,传递过来的是一个字典,用parse来解析 dataset = Dataset(opt) # 作者自定义的Dataset类 print('读取数据中...') # Dataloader 定义了一次获取批次数据的方法 dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) # PyTorch自带的DataLoader类,生成一个多线程迭代器来迭代dataset, 以供读取一个batch的数据 testset = TestDataset(opt, split='trainval') # 测试集loader test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16() # 网络定义 print('模型构建完毕!') trainer = FasterRCNNTrainer( faster_rcnn).cuda() # 定义一个训练器,返回loss, .cuda()表示把返回的Tensor存入GPU if opt.load_path: # 如果要加载预训练模型 trainer.load(opt.load_path) print('已加载预训练参数 %s' % opt.load_path) else: print("未引入预训练参数, 随机初始化网络参数") trainer.vis.text(dataset.db.label_names, win='labels') # 显示labels标题 best_map = 0 # 定义一个best_map for epoch in range(opt.epoch): # 对于每一个epoch trainer.reset_meters() # 重置测各种测量仪 # 对每一个数据 for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) # 转化为标量 img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda( ) # 存入GPU img, bbox, label = Variable(img), Variable(bbox), Variable( label) # 转换成变量以供自动微分器使用 # TODO trainer.train_step(img, bbox, label, scale) # 训练一步 if (ii + 1) % opt.plot_every == 0: # 如果到达"每多少次显示" if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) # 使用测试数据集来评价模型(此步里面包含预测信息) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save( best_map=best_map) # 好到一定程度就存储模型, 存储在checkpoint文件夹内 if epoch == 9: # 到第9轮的时候读取模型, 并调整学习率 trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{}, map:{},loss:{}'.format( str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) # if epoch == 13: # 到第14轮的时候停止训练 # break trainer.save(best_map=best_map)
def train(**kwargs): opt._parse(kwargs) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.is_distilltion == False: iteration_number = 10 path = opt.voc_data_dir + '/ImageSets/Main/trainval.txt' datatxt = 0 f = open(path, "r") for i in range(5000): if i % 500 == 0: datatxt = datatxt + 1 f2 = open( opt.voc_data_dir + '/ImageSets/Main/' + str(datatxt) + '.txt', "w") f2.write(f.readline()) else: iteration_number = 1 if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) for jj in range(iteration_number): t.cuda.empty_cache() if jj > 0: opt.datatxt = str(int(opt.datatxt) + 1) opt.load_path = best_path # 样本挖掘 print(opt.datatxt) if opt.is_example_mining == True and opt.load_path != None: if opt.example_type == 'mAP': example_mining_map(trainer, opt.datatxt) elif opt.example_type == 'loss': example_mining_loss(opt.datatxt) elif opt.example_type == 'diversity': example_mining_diversity(trainer, opt.datatxt) elif opt.example_type == 'mAP_diversity': example_mining_map_diversity(trainer, opt.datatxt) else: example_mining_map_loss(trainer, opt.datatxt) print('example mining completed') print('load data') dataset = Dataset(opt) dataloader = data_.DataLoader( dataset, batch_size=1, shuffle=True, # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, pin_memory=True) testset_all = TestDataset(opt, 'test') test_all_dataloader = data_.DataLoader( testset_all, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, pin_memory=True) # visdom 显示所有类别标签名 trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr # print(lr_) t.cuda.empty_cache() for epoch in range(opt.epoch): t.cuda.empty_cache() print('epoch=%d' % epoch) if opt.example_type != 'mAP': # 计算loss的数组初始化 loss = np.zeros(10000) ID = list() # 重置混淆矩阵 trainer.reset_meters() # tqdm可以在长循环中添加一个进度提示信息,用户只需要封装任意的迭代器 tqdm(iterator), # 是一个快速、扩展性强 for ii, (img, sizes, bbox_, label_, scale, id_) in enumerate(dataloader): if len(bbox_) == 0: continue t.cuda.empty_cache() scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda( ), label_.cuda() # 训练的就这一步 下面的都是打印的信息 # 转化成pytorch能够计算的格式,转tensor格式 if opt.is_distilltion == True: # inx = str(id_[0]) # inx = int(inx[-5:]) # teacher_pred_bboxes = pred_bboxes[int(index[inx])] # teacher_pred_labels = pred_labels[int(index[inx])] # teacher_pred_features_ = pred_features[int(index[inx])] teacher_pred_labels = np.load('label/' + str(id_[0]) + '.npy') teacher_pred_bboxes = np.load('bbox/' + str(id_[0]) + '.npy') teacher_pred_features_ = np.load('feature/' + str(id_[0]) + '.npy') teacher_pred_bboxes = teacher_pred_bboxes.astype( np.float32) teacher_pred_labels = teacher_pred_labels.astype(np.int32) teacher_pred_bboxes_ = at.totensor(teacher_pred_bboxes) teacher_pred_labels_ = at.totensor(teacher_pred_labels) teacher_pred_bboxes_ = teacher_pred_bboxes_.cuda() teacher_pred_labels_ = teacher_pred_labels_.cuda() teacher_pred_features_ = teacher_pred_features_.cuda() losses = trainer.train_step(img, bbox, label, scale, epoch, teacher_pred_bboxes_, teacher_pred_labels_, teacher_pred_features_) else: losses = trainer.train_step(img, bbox, label, scale, epoch) # 保存每一个样本的损失 if opt.example_type != 'mAP': ID += list(id_) loss[ii] = losses.total_loss # visdom显示的信息 if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores, _ = trainer.faster_rcnn.predict( [ori_img_], visualize=True) print(at.tonumpy(_bboxes[0]).reshape(-1).shape) print(at.tonumpy(_labels[0]).shape) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # 混淆矩阵 # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.text(str(trainer.roi_cm.value().tolist()), win='roi_cm') # trainer.vis.img('roi_cm', at.totensor( # trainer.roi_cm.value(), False).float()) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{},ap:{}, map:{},loss:{}'.format( str(lr_), str(eval_result['ap']), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) # 保存最好结果并记住路径 if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) if opt.example_type != 'mAP': order = loss.argsort()[::-1] f = open('loss.txt', "w") for i in range(len(ID)): f.write(ID[order[i]] + ' ' + str(loss[order[i]]) + '\n') f.close() if epoch == 20: #draw(test_dataloader, faster_rcnn, test_num=opt.test_num) save_name = trainer.save(best_map='20') f = open('result.txt', "a") result = eval(test_all_dataloader, trainer.faster_rcnn, test_num=5000) f.write(opt.datatxt + '\n') f.write(save_name + '\n') f.write(result + '\n') f.close print(result) trainer.faster_rcnn.scale_lr(10) lr_ = lr_ * 10 break # 每10轮加载前面最好权重,并且减少学习率 if epoch % 20 == 15: trainer.save(best_map='15') trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay
def train(**kwargs): opt.parse(kwargs) print('loading data...') trainset = TrainDataset(opt) train_dataloader = torch.utils.data.DataLoader(trainset, batch_size=1, shuffle=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = torch.utils.data.DataLoader( testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, pin_memory=True) print('constructing model...') if opt.model == 'vgg16': faster_rcnn = FasterRCNNVGG16() elif opt.model == 'resnet101': faster_rcnn = FasterRCNNResNet101() trainer = FasterRCNNTrainer(faster_rcnn).cuda() print('loading model...') if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) else: print('no pretrained model found') trainer.vis.text('<br/>'.join(trainset.db.label_names), win='labels') print('start training...') best_map = 0.0 lr_ = opt.lr for epoch in range(opt.epoch): print("epoch : %d training ..." % epoch) trainer.reset_meters() for ii, (imgs_, bboxes_, labels_, scales_) in tqdm(enumerate(train_dataloader)): scales = at.scalar(scales_) imgs, bboxes, labels = imgs_.cuda().float(), bboxes_.cuda( ), labels_.cuda() trainer.train_step(imgs, bboxes, labels, scales) if (ii + 1) % opt.plot_every == 0: # plot loss trainer.vis.plot_many(trainer.losses_data()) # generate plotted image img = inverse_normalize(at.tonumpy(imgs_[0])) # plot groud truth bboxes bbox = at.tonumpy(bboxes_[0]) label = at.tonumpy(labels_[0]) img_gt = visdom_bbox(img, bbox, label) trainer.vis.img('ground truth', img_gt) bboxes__, labels__, scores__ = trainer.faster_rcnn.predict( [img], visualize=True) # plot prediction bboxes bbox = at.tonumpy(bboxes__[0]) label = at.tonumpy(labels__[0]).reshape(-1) score = at.tonumpy(scores__[0]) img_pred = visdom_bbox(img, bbox, label, score) trainer.vis.img('prediction', img_pred) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) if ii + 1 == opt.train_num: break print("epoch : %d evaluating ..." % epoch) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = vis_dict( { 'epoch': '%s/%s' % (str(epoch), str(opt.epoch)), 'lr': lr_, 'map': float(eval_result['map']), }, trainer.losses_data()) trainer.vis.log(log_info) if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map="%.4f" % best_map) if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay
def train(**kwargs): opt._parse(kwargs) #获得config设置信息 dataset = Dataset(opt) #传入opt,利用设置的数据集参数来创建训练数据集 print('load data') dataloader = data_.DataLoader(dataset, \ #用创建的训练数据集创建训练DataLoader,代码仅支持batch_size=1 batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) #传入opt,利用设置的数据集参数来加载测试数据集 test_dataloader = data_.DataLoader(testset, #用创建的测试数据集创建训练DataLoader,代码仅支持batch_size=1 batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16() #创建以vgg为backbone的FasterRCNN网络 print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() #把创建好的FasterRCNN网络放入训练器 if opt.load_path: #若有FasterRCNN网络的预训练加载,则加载load_path权重 trainer.load(opt.load_path) #训练器加载权重 print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 #初始化best_map,训练时用于判断是否需要保存模型,类似打擂台后面用 lr_ = opt.lr #得到预设的学习率 for epoch in range(opt.epoch): #开始训练,训练次数为opt.epoch trainer.reset_meters() for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) #进行类别处理得到scale(待定) #bbox是gt_box坐标(ymin, xmin, ymax, xmax) #label是类别的下标VOC_BBOX_LABEL_NAMES #img是图片,代码仅支持batch_size=1的训练 img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() #使用gpu训练 trainer.train_step(img, bbox, label, scale) #预处理完毕,进入模型 if (ii + 1) % opt.plot_every == 0: #可视化内容,(跳过) if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) #训练一个epoch评估一次 trainer.vis.plot('test_map', eval_result['map']) #可视化内容,(跳过) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] #获得当前的学习率 log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), #日志输出学习率,map,loss str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) #可视化内容,(跳过) if eval_result['map'] > best_map: #若这次评估的map大于之前最大的map则保存模型 best_map = eval_result['map'] #保存模型的map信息 best_path = trainer.save(best_map=best_map) #调用保存模型函数 if epoch == 9: #若训练到第9个epoch则加载之前最好的模型并且减低学习率继续训练 trainer.load(best_path) #加载模型 trainer.faster_rcnn.scale_lr(opt.lr_decay) #降低学习率 lr_ = lr_ * opt.lr_decay #获得当前学习率 if epoch == 13: #13个epoch停止训练 break
def train(**kwargs): opt._parse( kwargs ) #将调用函数时候附加的参数用,config.py文件里面的opt._parse()进行解释,然后获取其数据存储的路径,之后放到Dataset里面! dataset = Dataset(opt) print('load data') dataloader = data_.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader( testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, #pin_memory=True ) #pin_memory锁页内存,开启时使用显卡的内存,速度更快 faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() #判断opt.load_path是否存在,如果存在,直接从opt.load_path读取预训练模型,然后将训练数据的label进行可视化操作 if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.dataset.label_names, win='labels') best_map = 0 lr_ = opt.lr # 之后用一个for循环开始训练过程,而训练迭代的次数opt.epoch=14也在config.py文件中都预先定义好,属于超参数 for epoch in range(opt.epoch): print('epoch {}/{}'.format(epoch, opt.epoch)) trainer.reset_meters() #首先在可视化界面重设所有数据 for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = array_tool.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() trainer.train_step(img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() #可视化画出loss trainer.vis.plot_many(trainer.get_meter_data()) #可视化画出groudtruth bboxes ori_img_ = inverse_normalize(array_tool.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, array_tool.tonumpy(bbox_[0]), array_tool.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) #可视化画出预测bboxes # 调用faster_rcnn的predict函数进行预测,预测的结果保留在以_下划线开头的对象里面 _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox( ori_img_, array_tool.tonumpy(_bboxes[0]), array_tool.tonumpy(_labels[0]).reshape(-1), array_tool.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # 调用 trainer.vis.text将rpn_cm也就是RPN网络的混淆矩阵在可视化工具中显示出来 trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') #将roi_cm也就是roihead网络的混淆矩阵在可视化工具中显示出来 trainer.vis.img( 'roi_cm', array_tool.totensor(trainer.roi_cm.conf, False).float()) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{}, map:{}, loss{}'.format( str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) #将学习率以及map等信息及时显示更新 if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) if epoch == 9: #if判断语句如果学习的epoch达到了9就将学习率*0.1变成原来的十分之一 trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay if epoch == 13: break
def train(**kwargs): opt._parse(kwargs) # opt.caffe_pretrain = True TrainResume = False dataset = Dataset(opt) print('load dataset') dataloader = data_.DataLoader(dataset, batch_size=1, shuffle=True, pin_memory=True, num_workers=opt.num_workers) target_img_path = 'target_img.jpg' target_img = read_image(target_img_path) / 255 target_img = torch.from_numpy(pytorch_normalze(target_img)) target_img = torch.unsqueeze(target_img, 0).numpy() attacker = attacks.Blade_runner(train_BR=True) if TrainResume: attacker.load('checkpoints/attack_02152100_0.path') # attacker = attacks_no_target.Blade_runner(train_BR=True) faster_rcnn = FasterRCNNVGG16().eval() faster_rcnn.cuda() store(faster_rcnn) trainer = BRFasterRcnnTrainer(faster_rcnn, attacker, layer_idx=layer_idies, attack_mode=True).cuda() if opt.load_path: trainer.load(opt.load_path) print('from %s Load model parameters' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') target_features_list = list() img_feature = trainer.faster_rcnn(torch.from_numpy(target_img).cuda()) del img_feature target_features = trainer.faster_rcnn.feature_maps for target_feature_idx in target_features: target_features_list.append( target_features[target_feature_idx].cpu().detach().numpy()) del target_features for epoch in range(opt.epoch): trainer.reset_meters(BR=True) for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() img, bbox, label = Variable(img), Variable(bbox), Variable(label) rois, roi_scores = faster_rcnn(img, flag=True) if len(rois) != len(roi_scores): print( 'The generated ROI and ROI score lengths are inconsistent') trainer.train_step(img, bbox, label, scale, target_features_list, rois=rois, roi_scores=roi_scores) if (ii) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss # trainer.vis.plot_many(trainer.get_meter_data()) trainer.vis.plot_many(trainer.get_meter_data(BR=True)) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicted bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) if trainer.attacker is not None: adv_img = trainer.attacker.perturb(img, rois=rois, roi_scores=roi_scores) adv_img_ = inverse_normalize(at.tonumpy(adv_img[0])) _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [adv_img_], visualize=True) adv_pred_img = visdom_bbox( adv_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('adv_img', adv_pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) if ii % 500 == 0 and ii != 0: best_path = trainer.save(epochs=ii, save_rcnn=False) print('best path is %s' % best_path) if epoch % 2 == 0: best_path = trainer.save(epochs=epoch, save_rcnn=False)
def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) print('load data') dataloader = data_.DataLoader(dataset, batch_size=1, shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, pin_memory=True) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 best_ap = np.array([0.] * opt.label_number) lr_ = opt.lr vis = trainer.vis starttime = datetime.datetime.now() for epoch in range(opt.epoch): trainer.reset_meters() for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() trainer.train_step(img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix roi_cm = at.totensor(trainer.roi_cm.conf, False).float() trainer.vis.img('roi_cm', roi_cm) eval_result = eval(test_dataloader, faster_rcnn, vis=vis, test_num=opt.test_num) best_ap = dict(zip(opt.VOC_BBOX_LABEL_NAMES, eval_result['ap'])) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{}, map:{},loss:{}'.format( str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) if eval_result['map'] > best_map: print('roi_cm=\n', trainer.roi_cm.value()) plot_confusion_matrix(trainer.roi_cm.value(), classes=('animal', 'plant', 'rock', 'background'), normalize=False, title='Normalized Confusion Matrix') best_map = eval_result['map'] best_path = trainer.save(best_map=best_map, best_ap=best_ap) if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay # if epoch == 13: # break endtime = datetime.datetime.now() train_consum = (endtime - starttime).seconds print("train_consum=", train_consum)
def train(opt, faster_rcnn, dataloader, val_dataloader, test_dataloader, trainer, lr_, best_map, start_epoch): trainer.train() for epoch in range(start_epoch, start_epoch+opt.epoch): trainer.reset_meters() pbar = tqdm(enumerate(dataloader), total=len(dataloader)) for ii, (img, bbox_, label_, scale) in pbar: # Currently configured to predict (y_min, x_min, y_max, x_max) # bbox_tmp = bbox_.clone() # bbox_ = transform_bbox(bbox_) scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() losses = trainer.train_step(img, bbox, label, scale) if ii % 100 == 0: rpnloc = losses[0].cpu().data.numpy() rpncls = losses[1].cpu().data.numpy() roiloc = losses[2].cpu().data.numpy() roicls = losses[3].cpu().data.numpy() tot = losses[4].cpu().data.numpy() pbar.set_description(f"Epoch: {epoch} | Batch: {ii} | RPNLoc Loss: {rpnloc:.4f} | RPNclc Loss: {rpncls:.4f} | ROIloc Loss: {roiloc:.4f} | ROIclc Loss: {roicls:.4f} | Total Loss: {tot:.4f}") if (ii+1) % 1000 == 0: eval_result = eval(val_dataloader, faster_rcnn, test_num=1000) trainer.vis.plot('val_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] val_log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(val_log_info) print("Evaluation Results on Val Set ") print(val_log_info) print("\n\n") if (ii + 1) % 100 == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) print(trainer.get_meter_data()) try: ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) plt.show() # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) plt.show() trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) except: print("Cannot display images") if (ii + 1) % 100 == 0: eval_result = eval(val_dataloader, faster_rcnn, test_num=25) trainer.vis.plot('val_map', eval_result['map']) log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), str( eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) # Save after every epoch epoch_path = trainer.save(epoch, best_map=0) eval_result = eval(test_dataloader, faster_rcnn, test_num=1000) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] test_log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(test_log_info) print("Evaluation Results on Test Set ") print(test_log_info) print("\n\n") if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = epoch_path if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay if epoch == 13: break
def train(**kwargs): opt._parse(kwargs) print('load data') dataset = Dataset(opt) dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16(n_fg_class=dataset.get_class_count(), anchor_scales=[1]) print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn, n_fg_class=dataset.get_class_count()) if opt.use_cuda: trainer = trainer.cuda() if opt.load_path: old_state = trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) if opt.validate_only: num_eval_images = len(testset) eval_result = eval(test_dataloader, faster_rcnn, test_num=num_eval_images) print('Evaluation finished, obtained {} using {} out of {} images'. format(eval_result, num_eval_images, len(testset))) return if opt.load_path and 'epoch' in old_state.keys(): starting_epoch = old_state['epoch'] + 1 print('Model was trained until epoch {}, continuing with epoch {}'.format(old_state['epoch'], starting_epoch)) else: starting_epoch = 0 #trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr global_step = 0 for epoch in range(starting_epoch, opt.num_epochs): lr_ = opt.lr * (opt.lr_decay ** (epoch // opt.epoch_decay)) trainer.faster_rcnn.set_lr(lr_) print('Starting epoch {} with learning rate {}'.format(epoch, lr_)) trainer.reset_meters() for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader), total=len(dataset)): global_step = global_step + 1 scale = at.scalar(scale) if opt.use_cuda: img, bbox, label = img.cuda().float(), bbox_.float().cuda(), label_.float().cuda() else: img, bbox, label = img.float(), bbox_.float(), label_.float() img, bbox, label = Variable(img), Variable(bbox), Variable(label) losses = trainer.train_step(img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss #trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0]), label_names=dataset.get_class_names()+['BG']) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0]), label_names=dataset.get_class_names()+['BG']) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) #trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix #trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) #print('Current total loss {}'.format(losses[-1].tolist())) trainer.vis.plot('train_total_loss', losses[-1].tolist()) if (global_step) % opt.snapshot_every == 0: snapshot_path = trainer.save(epoch=epoch) print("Snapshotted to {}".format(snapshot_path)) #snapshot_path = trainer.save(epoch=epoch) #print("After epoch {}: snapshotted to {}".format(epoch,snapshot_path)) eval_result = eval(test_dataloader, faster_rcnn, test_num=min(opt.test_num, len(testset))) print(eval_result) # TODO: this definitely is not good and will bias evaluation if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=eval_result['map'],epoch=epoch) print("After epoch {}: snapshotted to {}".format(epoch, best_path)) trainer.vis.plot('test_map', eval_result['map'])
tensor_img = tensor_img.cuda() # This preset filters bounding boxes with a score < 0.7 # and has to be set everytime before using predict() self.faster_rcnn.use_preset('visualize') pred_bboxes, pred_labels, pred_scores = self.faster_rcnn.predict( tensor_img, [(img.shape[1], img.shape[2])]) box_filter = np.array(pred_scores[0]) > 0.7 return pred_bboxes[0][box_filter], pred_labels[0][ box_filter], pred_scores[0][box_filter] if __name__ == '__main__': det = PlasticDetector('checkpoints/fasterrcnn_07122125_0.5273599762268979', True) print('Loaded model.') image_path = 'misc/demo.jpg' test_image = PIL.Image.open(image_path) print('Working on image {}'.format(image_path)) print(det.predict_image(test_image, 5)) pred_bboxes, pred_scores = det.predict_image(test_image, 1000) pred_img = visdom_bbox(np.array(test_image.convert('RGB')).transpose( (2, 0, 1)), at.tonumpy(pred_bboxes[:, [1, 0, 3, 2]]), at.tonumpy([1 for _ in pred_bboxes]), at.tonumpy(pred_scores), label_names=['Animal', 'BG']) PIL.Image.fromarray((255 * pred_img).transpose( (1, 2, 0)).astype(np.uint8)).save('output.jpg') det.annotate_image(test_image, 5).save('output-annotate.jpg')
def train(**kwargs): """ 训练 """ #解析命令行参数,设置配置文件参数 opt._parse(kwargs) #初始化Dataset参数 dataset = Dataset(opt) print('load data') #data_ 数据加载器(被重命名,pytorch方法) dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) #初始化TestDataset参数 testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) #新建一个FasterRCNNVGG16 faster_rcnn = FasterRCNNVGG16() print('model construct completed') #新建一个trainer,并将网络模型转移到GPU上 #将FasterRCNNVGG16模型传入 trainer = FasterRCNNTrainer(faster_rcnn).cuda() #如果存在,加载训练好的模型 if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) #可视化类别 vis为visdom加载器 trainer.vis.text(dataset.db.label_names, win='labels') #best_map存放的是 最优的mAP的网络参数 best_map = 0 lr_ = opt.lr for epoch in range(opt.epoch): #trainer方法 将平均精度的元组 和 混淆矩阵的值置0 trainer.reset_meters() for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): #调整数据的形状 scale:缩放倍数(输入图片尺寸 比上 输出数据的尺寸) #1.6左右 供模型训练之前将模型规范化 scale = at.scalar(scale) #将数据集转入到GPU上 #img 1x3x800x600 一张图片 三通道 大小800x600(不确定) #bbox 1x1x4 #label 1x1 img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() #将数据转为V 变量,以便进行自动反向传播 img, bbox, label = Variable(img), Variable(bbox), Variable(label) #训练并更新可学习参数(重点*****) 前向+反向,返回losses trainer.train_step(img, bbox, label, scale) #进行多个数据的可视化 if (ii + 1) % opt.plot_every == 0: #进入调试模式 if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss 画五个损失 trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes img[0],是压缩0位,形状变为[3x800x600] #反向归一化,将img反向还原为原始图像,以便用于显示 ori_img_ = inverse_normalize(at.tonumpy(img[0])) #通过原始图像,真实bbox,真实类别 进行显示 gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes #对原图进行预测,得到预测的bbox label scores _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True) #通过原始图像、预测的bbox,预测的类别 以及概率 进行显示 pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) #rpn混淆矩阵 trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix #roi混淆矩阵 trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) #使用验证集对当前的网络进行验证,返回一个字典,key值有AP,mAP eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) #如果当前的map值优于best_map,则将当前值赋给best_map。将当前模型保留 if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) #如果epoch到达9时,加载 当前的最优模型,并将学习率按lr_decay衰减调低 if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay #可视化验证集的test_map 和log信息 trainer.vis.plot('test_map', eval_result['map']) log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) if epoch == 13: break
img, img_depth, bbox, label = img.cuda().float(), img_depth.cuda().float(), bbox_.cuda(), label_.cuda() img, img_depth, bbox, label = Variable(img), Variable(img_depth), Variable(bbox), Variable(label) trainer.train_step(img, img_depth, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) ori_img_depth_ = inverse_normalize_depth(at.tonumpy(img_depth[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes <<<<<<< HEAD _bboxes, _labels, _scores = trainer.faster_rcnn.predict(ori_img_,ori_img_depth_, visualize=True) ======= _bboxes, _labels, _scores = trainer.faster_rcnn.predict(ori_img_, visualize=True) >>>>>>> b43e1a358b5853ffb749ac931c9cd97a6dccf862 pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img)
def train(**kwargs): # opt._parse(kwargs) print('load data') dataloader = get_train_loader(opt.root_dir, batch_size=opt.batch_size, shuffle=opt.shuffle, num_workers=opt.num_workers, pin_memory=opt.pin_memory) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() # if opt.load_path: # trainer.load(opt.load_path) # print('load pretrained model from %s' % opt.load_path) # trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr for epoch in range(opt.epoch): trainer.reset_meters() for ii, sample in tqdm(enumerate(dataloader)): if len(sample.keys()) == 5: img_id, img, bbox_, scale, label_ = sample['img_id'], sample['image'], sample['bbox'], sample['scale'], \ sample['label'] img, bbox, label = img.cuda().float(), bbox_.cuda( ), label_.cuda() img, bbox, label = Variable(img), Variable(bbox), Variable( label) else: img_id, img, bbox, scale, label = sample['img_id'], sample['image'], np.zeros((1, 0, 4)), \ sample['scale'], np.zeros((1, 0, 1)) img = img.cuda().float() img = Variable(img) # if label.size == 0: # continue scale = at.scalar(scale) trainer.train_step(img_id, img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot ground truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicted bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) if epoch % 10 == 0: best_path = trainer.save(best_map=best_map)
def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) print('load data') dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr for epoch in range(opt.epoch): trainer.reset_meters() for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() trainer.train_step(img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{}, map:{},loss:{}'.format( str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay if epoch == 13: break
def train_val(): print('load data') train_loader, val_loader = get_train_val_loader( opt.root_dir, batch_size=opt.batch_size, val_ratio=0.1, shuffle=opt.shuffle, num_workers=opt.num_workers, pin_memory=opt.pin_memory) faster_rcnn = FasterRCNNVGG16() # faster_rcnn = FasterRCNNResNet50() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() # if opt.load_path: # trainer.load(opt.load_path) # print('load pretrained model from %s' % opt.load_path) # trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr for epoch in range(opt.epoch): trainer.reset_meters() tqdm.monitor_interval = 0 for ii, sample in tqdm(enumerate(train_loader)): if len(sample.keys()) == 5: img_id, img, bbox, scale, label = sample['img_id'], sample['image'], sample['bbox'], sample['scale'], \ sample['label'] img, bbox, label = img.cuda().float(), bbox.cuda(), label.cuda( ) img, bbox, label = Variable(img), Variable(bbox), Variable( label) else: img_id, img, bbox, scale, label = sample['img_id'], sample['image'], np.zeros((1, 0, 4)), \ sample['scale'], np.zeros((1, 0, 1)) img = img.cuda().float() img = Variable(img) if bbox.size == 0: continue scale = at.scalar(scale) trainer.train_step(img_id, img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot ground truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, img_id[0], at.tonumpy(bbox[0]), at.tonumpy(label[0])) trainer.vis.img('gt_img', gt_img) # plot predicted bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, img_id[0], at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) mAP = eval_mAP(trainer, val_loader) trainer.vis.plot('val_mAP', mAP) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{}, map:{},loss:{}'.format( str(lr_), str(mAP), str(trainer.get_meter_data())) trainer.vis.log(log_info) if mAP > best_map: best_map = mAP best_path = trainer.save(best_map=best_map) if epoch == opt.epoch - 1: best_path = trainer.save() if (epoch + 1) % 10 == 0: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay
def train(**kwargs): opt._parse(kwargs) # 全部的设置 dataset = Dataset(opt) # 数据集 print('load data') dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) # pin memory:锁页内存,内存为所欲为的时候为true,详情见:https://blog.csdn.net/yangwangnndd/article/details/95385628 # num worker:加载数据的线程数,默认为8。具体数值的选取由训练时间决定,当训练时间快于加载时间时则需要增加线程 # shuffle=True允许数据打乱排序 testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: #接下来判断opt.load_path是否存在,如果存在,直接从opt.load_path读取预训练模型,然后将训练数据的label进行可视化操作 trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr for epoch in range( opt.epoch): # 训练迭代的次数opt.epoch=14也在config.py文件中都预先定义好,属于超参数 trainer.reset_meters() # 首先在可视化界面重设所有数据 for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() # 然后从训练数据中枚举dataloader,设置好缩放范围,将img,bbox,label,scale全部设置为可gpu加速 trainer.train_step( img, bbox, label, scale ) # 调用trainer.py中的函数trainer.train_step(img,bbox,label,scale)进行一次参数迭代优化过程 # 判断数据读取次数是否能够整除plot_every(是否达到了画图次数) if (ii + 1) % opt.plot_every == 0: # 如果达到判断debug_file是否存在,用ipdb工具设置断点 if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss # 调用trainer中的trainer.vis.plot_many(trainer.get_meter_data())将训练数据读取并上传完成可视化 trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # 将每次迭代读取的图片用dataset文件里面的inverse_normalize()函数进行预处理,将处理后的图片调用Visdom_bbox # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) # 调用 trainer.vis.text将rpn_cm也就是RPN网络的混淆矩阵在可视化工具中显示出来 trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0][ 'lr'] # learning rate log_info = 'lr:{}, map:{},loss:{}'.format( str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) # 将损失学习率以及map等信息及时显示更新 if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) # 用if判断语句永远保存效果最好的map if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay # if判断语句如果学习的epoch达到了9就将学习率*0.1变成原来的十分之一 if epoch == 13: break
def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) # 300w_dataset = FaceLandmarksDataset() print('load data') dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ pin_memory=True,\ num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16() print('model construct completed') attacker = attacks.DCGAN(train_adv=False) if opt.load_attacker: attacker.load(opt.load_attacker) print('load attacker model from %s' % opt.load_attacker) trainer = VictimFasterRCNNTrainer(faster_rcnn, attacker, attack_mode=True).cuda() # trainer = VictimFasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') # eval_result = eval(test_dataloader, faster_rcnn, test_num=2000) best_map = 0 for epoch in range(opt.epoch): trainer.reset_meters(adv=True) for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): ipdb.set_trace() scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() img, bbox, label = Variable(img), Variable(bbox), Variable(label) trainer.train_step(img, bbox, label, scale) if (ii) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) trainer.vis.plot_many(trainer.get_meter_data(adv=True)) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicted bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) if trainer.attacker is not None: adv_img = trainer.attacker.perturb(img) adv_img_ = inverse_normalize(at.tonumpy(adv_img[0])) _bboxes, _labels, _scores = trainer.faster_rcnn.predict( [adv_img_], visualize=True) adv_pred_img = visdom_bbox( adv_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('adv_img', adv_pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img( 'roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) if (ii) % 500 == 0: best_path = trainer.save(epochs=epoch, save_rcnn=True) if epoch % 2 == 0: best_path = trainer.save(epochs=epoch)
def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) print('load data') dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 for epoch in range(opt.epoch): trainer.reset_meters() for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() img, bbox, label = Variable(img), Variable(bbox), Variable(label) trainer.train_step(img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) trainer.vis.plot('test_map', eval_result['map']) lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) trainer.vis.log(log_info) if epoch == 13: break
def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) print('load data') dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) faster_rcnn = FasterRCNNVGG16() print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from {}'.format(opt.load_path)) # trainer.vis.text(dataset.db.label_names, win='labels') adversary = None if opt.flagadvtrain: print("flagadvtrain turned: Adversarial training!") atk = PGD.PGD(trainer, eps=16/255, alpha=3/255, steps=4) # atk = torchattacks.PGD(trainer.faster_rcnn, eps=16, alpha=3, steps=4) # adversary = PGDAttack(trainer.faster_rcnn, loss_fn=nn.CrossEntropyLoss(), eps=16, nb_iter=4, eps_iter=3, # rand_init=True, clip_min=0.0, clip_max=1.0, targeted=False) best_map = 0 lr_ = opt.lr normal_total_loss = [] adv_total_loss = [] total_time = 0.0 total_imgs = 0 true_imgs = 0 for epoch in range(opt.epoch): trainer.reset_meters() once = True for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) temp_img = copy.deepcopy(img).cuda() img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() if opt.flagadvtrain: before_time = time.time() img = atk(img, bbox, label, scale) after_time = time.time() # with ctx_noparamgrad_and_eval(trainer.faster_rcnn): # img = adversary.perturb(img, label) # print("Adversarial training done!") total_time += after_time - before_time # print("Normal training starts\n") # trainer.train_step(img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: # adv_total_loss.append(trainer.get_meter_data()["total_loss"]) if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss # trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes temp_ori_img_ = inverse_normalize(at.tonumpy(temp_img[0])) # img2jpg(temp_ori_img_, "imgs/orig_images/", "gt_img{}".format(ii)) # temp_gt_img = visdom_bbox(temp_ori_img_, # at.tonumpy(bbox_[0]), # at.tonumpy(label_[0])) # plt.figure() # c, h, w = temp_gt_img.shape # plt.imshow(np.reshape(temp_gt_img, (h, w, c))) # plt.savefig("imgs/temp_orig_images/temp_gt_img{}".format(ii)) # plt.close() ori_img_ = inverse_normalize(at.tonumpy(img[0])) # print("GT Label is {} and pred_label is {}".format(label_[0],)) # img2jpg(ori_img_, "imgs/adv_images/", "adv_img{}".format(ii)) # gt_img = visdom_bbox(ori_img_, # at.tonumpy(bbox_[0]), # at.tonumpy(label_[0])) # plt.figure() # c, h, w = gt_img.shape # plt.imshow(np.reshape(gt_img, (h, w, c))) # plt.savefig("imgs/orig_images/gt_img{}".format(ii)) # plt.close() # trainer.vis.img('gt_img', gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True) fig1 = plt.figure() ax1 = fig1.add_subplot(1,1,1) # final1 = (at.tonumpy(img[0].cpu()).transpose(1,2,0).astype(np.uint8)) final1 = (ori_img_.transpose(1, 2, 0).astype(np.uint8)) ax1.imshow(final1) gt_img = visdom_bbox(ax1,at.tonumpy(_bboxes[0]),at.tonumpy(_labels[0])) fig1.savefig("imgs/adv_images/adv_img{}".format(ii)) plt.close() _temp_bboxes, _temp_labels, _temp_scores = trainer.faster_rcnn.predict([temp_ori_img_], visualize=True) fig2 = plt.figure() ax2 = fig2.add_subplot(1, 1, 1) final2 = (temp_ori_img_.transpose(1, 2, 0).astype(np.uint8)) # final2 = (at.tonumpy(temp_img[0].cpu()).transpose(1, 2, 0).astype(np.uint8)) ax2.imshow(final2) gt_img = visdom_bbox(ax2, at.tonumpy(_temp_bboxes[0]), at.tonumpy(_temp_labels[0])) fig2.savefig("imgs/orig_images/gt_img{}".format(ii)) plt.close() # img2jpg(temp_gt_img, "imgs/orig_images/", "gt_img{}".format(ii)) # print("gt labels is {}, pred_orig_labels is {} and pred_adv_labels is {}".format(label_, _labels, _temp_labels)) total_imgs += 1 if len(_temp_labels) == 0: continue if _labels[0].shape[0] == _temp_labels[0].shape[0] and (_labels[0] == _temp_labels[0]).all() is True: true_imgs += 1 # pred_img = visdom_bbox(ori_img_, # at.tonumpy(_bboxes[0]), # at.tonumpy(_labels[0]).reshape(-1), # at.tonumpy(_scores[0])) # # print("Shape of temp_orig_img_ is {}".format(temp_ori_img_.shape)) # temp_pred_img = visdom_bbox(temp_ori_img_, # at.tonumpy(_temp_bboxes[0]), # at.tonumpy(_temp_labels[0]).reshape(-1), # at.tonumpy(_temp_scores[0])) # # trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) # trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix # trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) # fig = plt.figure() # ax1 = fig.add_subplot(2,1,1) # ax1.plot(normal_total_loss) # ax2 = fig.add_subplot(2,1,2) # ax2.plot(adv_total_loss) # fig.savefig("losses/both_loss{}".format(epoch)) # eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num, # flagadvtrain=opt.flagadvtrain, adversary=atk)# adversary=adversary) # trainer.vis.plot('test_map', eval_result['map']) # lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] # log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), # str(eval_result['map']), # str(trainer.get_meter_data())) # print(log_info) # # trainer.vis.log(log_info) # # if eval_result['map'] > best_map: # best_map = eval_result['map'] # best_path = trainer.save(best_map=best_map) # if epoch == 9: # trainer.load(best_path) # trainer.faster_rcnn.scale_lr(opt.lr_decay) # lr_ = lr_ * opt.lr_decay if epoch == 0: break if epoch == 13: break print("Total number of images is {}".format(total_imgs)) print("True images is {}".format(true_imgs)) print("Total time is {}".format(total_time)) print("Avg time is {}".format(total_time/total_imgs))
def eval(dataloader, faster_rcnn, trainer, dataset, test_num=10000): with torch.no_grad(): print('Running validation') # Each predicted box is organized as :`(y_{min}, x_{min}, y_{max}, x_{max}), # Where y corresponds to the height and x to the width pred_bboxes, pred_labels, pred_scores = list(), list(), list() gt_bboxes, gt_labels, gt_difficults = list(), list(), list() image_ids = list() for ii, (imgs, sizes, gt_bboxes_, gt_labels_, gt_difficults_, image_ids_) in tqdm(enumerate(dataloader), total=test_num): sizes = [ sizes[0].detach().numpy().tolist()[0], sizes[1].detach().numpy().tolist()[0] ] pred_bboxes_, pred_labels_, pred_scores_ = faster_rcnn.predict( imgs, [sizes]) # We have to add .copy() here to allow for the loaded image to be released after each iteration gt_bboxes += list(gt_bboxes_.numpy().copy()) gt_labels += list(gt_labels_.numpy().copy()) gt_difficults += list(gt_difficults_.numpy().copy()) image_ids += list(image_ids_.numpy().copy()) pred_bboxes += [pp.copy() for pp in pred_bboxes_] pred_labels += [pp.copy() for pp in pred_labels_] pred_scores += [pp.copy() for pp in pred_scores_] if ii == test_num: break result = eval_detection_voc(pred_bboxes, pred_labels, pred_scores, gt_bboxes, gt_labels, gt_difficults, use_07_metric=True) if opt.validate_only: save_path = '{}_detections.npz'.format(opt.load_path) np.savez(save_path, pred_bboxes=pred_bboxes, pred_labels=pred_labels, pred_scores=pred_scores, gt_bboxes=gt_bboxes, gt_labels=gt_labels, gt_difficults=gt_difficults, image_ids=image_ids, result=result) else: ori_img_ = inverse_normalize(at.tonumpy(imgs[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(gt_bboxes[-1]), at.tonumpy(gt_labels[-1]), label_names=dataset.get_class_names() + ['BG']) trainer.vis.img('test_gt_img', gt_img) # plot predicti bboxes pred_img = visdom_bbox(ori_img_, at.tonumpy(pred_bboxes[-1]), at.tonumpy(pred_labels[-1]).reshape(-1), at.tonumpy(pred_scores[-1]), label_names=dataset.get_class_names() + ['BG']) trainer.vis.img('test_pred_img', pred_img) del imgs, gt_bboxes_, gt_labels_, gt_difficults_, image_ids_, pred_bboxes_, pred_labels_, pred_scores_ torch.cuda.empty_cache() return result
def train(**kwargs): opt._parse(kwargs) carrada = download('Carrada') train_set = Carrada().get('Train') val_set = Carrada().get('Validation') test_set = Carrada().get('Test') train_seqs = SequenceCarradaDataset(train_set) val_seqs = SequenceCarradaDataset(val_set) test_seqs = SequenceCarradaDataset(test_set) train_seqs_loader = data_.DataLoader(train_seqs, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) val_seqs_loader = data_.DataLoader(val_seqs, batch_size=1, shuffle=False, # pin_memory=True, num_workers=opt.num_workers) test_seqs_loader = data_.DataLoader(test_seqs, batch_size=1, shuffle=False, # pin_memory=True, num_workers=opt.num_workers) # faster_rcnn = FasterRCNNVGG16(n_fg_class=3) # faster_rcnn = FasterRCNNRESNET101(n_fg_class=3) faster_rcnn = FasterRCNNRESNET18(n_fg_class=3) print('model construct completed') trainer = FasterRCNNTrainer(faster_rcnn).cuda() scheduler = ExponentialLR(trainer.faster_rcnn.optimizer, gamma=0.9) if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) writer_path = os.path.join(opt.logs_path, opt.model_name) os.makedirs(writer_path, exist_ok=True) writer = SummaryWriter(writer_path) iteration = 0 best_map = 0 lr_ = opt.lr for epoch in range(opt.epoch): print('Processing epoch: {}/{}'.format(epoch, opt.epoch)) trainer.reset_meters() for n_seq, sequence_data in tqdm(enumerate(train_seqs_loader)): seq_name, seq = sequence_data path_to_frames = os.path.join(carrada, seq_name[0]) train_frame_set = CarradaDataset(opt, seq, 'box', opt.signal_type, path_to_frames) train_frame_loader = data_.DataLoader(train_frame_set, batch_size=1, shuffle=False, num_workers=opt.num_workers) for ii, (img, bbox_, label_, scale) in tqdm(enumerate(train_frame_loader)): iteration += 1 scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() img = normalize(img) if opt.debug_step and (iteration+1) % opt.debug_step == 0: trainer.train_step(img, bbox, label, scale, stop=True) else: trainer.train_step(img, bbox, label, scale) if (iteration + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() train_results = trainer.get_meter_data() writer.add_scalar('Losses/rpn_loc', train_results['rpn_loc_loss'], iteration) writer.add_scalar('Losses/rpn_cls', train_results['rpn_cls_loss'], iteration) writer.add_scalar('Losses/roi_loc', train_results['roi_loc_loss'], iteration) writer.add_scalar('Losses/roi_cls', train_results['roi_cls_loss'], iteration) writer.add_scalar('Losses/total', train_results['total_loss'], iteration) if (iteration + 1) % opt.img_every == 0: ori_img_ = at.tonumpy(img[0]) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) gt_img_grid = make_grid(torch.from_numpy(gt_img)) writer.add_image('Ground_truth_img', gt_img_grid, iteration) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], opt.signal_type, visualize=True) # FLAG: vis pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) pred_img_grid = make_grid(torch.from_numpy(pred_img)) writer.add_image('Predicted_img', pred_img_grid, iteration) if opt.train_eval and (iteration + 1) % opt.train_eval == 0: train_eval_result, train_best_iou = eval(train_seqs_loader, faster_rcnn, opt.signal_type) writer.add_scalar('Train/mAP', train_eval_result['map'], iteration) writer.add_scalar('Train/Best_IoU', train_best_iou, iteration) eval_result, best_val_iou = eval(val_seqs_loader, faster_rcnn, opt.signal_type, test_num=opt.test_num) writer.add_scalar('Validation/mAP', eval_result['map'], iteration) writer.add_scalar('Validation/Best_IoU', best_val_iou, iteration) lr_ = scheduler.get_lr()[0] writer.add_scalar('learning_rate', lr_, iteration) log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) print(log_info) if eval_result['map'] > best_map: test_result, test_best_iou = eval(test_seqs_loader, faster_rcnn, opt.signal_type, test_num=opt.test_num) writer.add_scalar('Test/mAP', test_result['map'], iteration) writer.add_scalar('Test/Best_IoU', test_best_iou, iteration) best_map = eval_result['map'] best_test_map = test_result['map'] best_path = trainer.save(best_val_map=best_map, best_test_map=best_test_map) # best_path = trainer.save(best_map=best_map) if (epoch + 1) % opt.lr_step == 0: scheduler.step()
def train(**kwargs): # opt._parse(kwargs)#将调用函数时候附加的参数用, # config.py文件里面的opt._parse()进行解释,然后 # 获取其数据存储的路径,之后放到Dataset里面! opt._parse(kwargs) dataset = Dataset(opt) print('load data') # #Dataset完成的任务见第二次推文数据预处理部分, # 这里简单解释一下,就是用VOCBboxDataset作为数据 # 集,然后依次从样例数据库中读取图片出来,还调用了 # Transform(object)函数,完成图像的调整和随机翻转工作 dataloader = data_.DataLoader(dataset, \ batch_size=1, \ shuffle=True, \ # pin_memory=True, num_workers=opt.num_workers) testset = TestDataset(opt) # 将数据装载到dataloader中,shuffle=True允许数据打乱排序, # num_workers是设置数据分为几批处理,同样的将测试数据集也 # 进行同样的处理,然后装载到test_dataloader中 test_dataloader = data_.DataLoader(testset, batch_size=1, num_workers=opt.test_num_workers, shuffle=False, \ pin_memory=True ) # 定义faster_rcnn=FasterRCNNVGG16()训练模型 faster_rcnn = FasterRCNNVGG16() print('model construct completed') # 设置trainer = FasterRCNNTrainer(faster_rcnn).cuda()将 # FasterRCNNVGG16作为fasterrcnn的模型送入到FasterRCNNTrainer # 中并设置好GPU加速 trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: trainer.load(opt.load_path) print('load pretrained model from %s' % opt.load_path) trainer.vis.text(dataset.db.label_names, win='labels') best_map = 0 lr_ = opt.lr # 用一个for循环开始训练过程,而训练迭代的次数 # opt.epoch=14也在config.py文件中预先定义好,属于超参数 for epoch in range(opt.epoch): # 首先在可视化界面重设所有数据 trainer.reset_meters() for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) # 然后从训练数据中枚举dataloader,设置好缩放范围, # 将img,bbox,label,scale全部设置为可gpu加速 img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() # 调用trainer.py中的函数trainer.train_step # (img,bbox,label,scale)进行一次参数迭代优化过程 trainer.train_step(img, bbox, label, scale) # 判断数据读取次数是否能够整除plot_every # (是否达到了画图次数),如果达到判断debug_file是否存在, # 用ipdb工具设置断点,调用trainer中的trainer.vis. # plot_many(trainer.get_meter_data())将训练数据读取并 # 上传完成可视化 if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = inverse_normalize(at.tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])) # 将每次迭代读取的图片用dataset文件里面的inverse_normalize() # 函数进行预处理,将处理后的图片调用Visdom_bbox可视化 trainer.vis.img('gt_img', gt_img) # plot predicti bboxes # 调用faster_rcnn的predict函数进行预测, # 预测的结果保留在以_下划线开头的对象里面 _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0])) # 利用同样的方法将原始图片以及边框类别的 # 预测结果同样在可视化工具中显示出来 trainer.vis.img('pred_img', pred_img) # rpn confusion matrix(meter) # 调用trainer.vis.text将rpn_cm也就是 # RPN网络的混淆矩阵在可视化工具中显示出来 trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix # 可视化ROI head的混淆矩阵 trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float()) # 调用eval函数计算map等指标 eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) # 可视化map trainer.vis.plot('test_map', eval_result['map']) # 设置学习的learning rate lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), str(eval_result['map']), str(trainer.get_meter_data())) # 将损失学习率以及map等信息及时显示更新 trainer.vis.log(log_info) # 用if判断语句永远保存效果最好的map if eval_result['map'] > best_map: best_map = eval_result['map'] best_path = trainer.save(best_map=best_map) if epoch == 9: # if判断语句如果学习的epoch达到了9就将学习率*0.1 # 变成原来的十分之一 trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay # 判断epoch==13结束训练验证过程 if epoch == 13: break
def train(**kwargs): opt._parse(kwargs) dataset = Dataset(opt) print("load data") dataloader = data_.DataLoader( dataset, batch_size=1, shuffle=True, # pin_memory=True, num_workers=opt.num_workers, ) testset = TestDataset(opt) test_dataloader = data_.DataLoader( testset, batch_size=1, num_workers=2, shuffle=False, # pin_memory=True ) faster_rcnn = FasterRCNNVGG16() print("model construct completed") trainer = FasterRCNNTrainer(faster_rcnn).cuda() if opt.load_path: trainer.load(opt.load_path) print("load pretrained model from %s" % opt.load_path) trainer.vis.text(dataset.db.label_names, win="labels") best_map = 0 for epoch in range(7): trainer.reset_meters() for ii, (img, bbox_, label_, scale, ori_img) in tqdm(enumerate(dataloader)): scale = at.scalar(scale) img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() losses = trainer.train_step(img, bbox, label, scale) if (ii + 1) % opt.plot_every == 0: if os.path.exists(opt.debug_file): ipdb.set_trace() # plot loss trainer.vis.plot_many(trainer.get_meter_data()) # plot groud truth bboxes ori_img_ = (img * 0.225 + 0.45).clamp(min=0, max=1) * 255 gt_img = visdom_bbox( at.tonumpy(ori_img_)[0], at.tonumpy(bbox_)[0], label_[0].numpy()) trainer.vis.img("gt_img", gt_img) # plot predicti bboxes _bboxes, _labels, _scores = trainer.faster_rcnn.predict( ori_img, visualize=True) pred_img = visdom_bbox( at.tonumpy(ori_img[0]), at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0]), ) trainer.vis.img("pred_img", pred_img) # rpn confusion matrix(meter) trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win="rpn_cm") # roi confusion matrix trainer.vis.img( "roi_cm", at.totensor(trainer.roi_cm.conf, False).float()) if epoch == 4: trainer.faster_rcnn.scale_lr(opt.lr_decay) eval_result = eval(test_dataloader, faster_rcnn, test_num=1e100) print("eval_result") trainer.save(mAP=eval_result["map"])
def RFCN_train(**kwargs): """ python train.py RFCN_train """ """parse params""" opt.parse(kwargs) opt.batch_size = 1 # force set batch_size to 1 """load train & test dataset""" print('load data') train_db = TrainDataset() train_dataloader = DataLoader(train_db, shuffle=True, batch_size=opt.batch_size, num_workers=opt.num_workers, pin_memory=False) test_db = TestDataset() if opt.test_num < len(test_db): test_db = torch.utils.data.Subset(test_db, indices=torch.arange(opt.test_num)) test_dataloader = DataLoader(test_db, shuffle=False, batch_size=opt.test_batch_size, num_workers=opt.test_num_workers, pin_memory=False) """create model""" rfcn_md = RFCN_ResNet101() print('model construct completed') rfcn_trainer = RFCN_Trainer(rfcn_md).cuda() if opt.load_path: rfcn_trainer.load(opt.load_path, load_viz_idx=opt.load_viz_x) print('load pretrained model parameters from %s' % opt.load_path) print("lr is:", rfcn_trainer.optimizer.param_groups[0]['lr']) rfcn_trainer.train() rfcn_trainer.viz.text(train_db.db.CLASS_NAME, win='labels') best_map = 0 """training""" for epoch in range(opt.epoch_begin, opt.total_epoch): rfcn_trainer.reset_meters() step = -1 for (img, bbox_, label_, scale) in tqdm(train_dataloader): step += 1 img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() scale = scale.item() rfcn_trainer.train_step(img, bbox, label, scale) if (step + 1) % opt.print_interval_steps == 0: # plot loss for k, v in rfcn_trainer.get_meter_data().items(): rfcn_trainer.viz.line(Y=np.array([v]), X=np.array([rfcn_trainer.viz_index]), win=k, opts=dict(title=k, xlabel='px', ylable='loss'), update=None if rfcn_trainer.viz_index == 0 else 'append') rfcn_trainer.viz_index += 1 # plot ground truth bboxes ori_img_ = inverse_normalize(tonumpy(img[0])) gt_img = visdom_bbox(ori_img_, tonumpy(bbox_[0]), tonumpy(label_[0])) rfcn_trainer.viz.image(gt_img, win='gt_img', opts={'title': 'gt_img'}) # plot predict bboxes b_bboxes, b_labels, b_scores = rfcn_trainer.r_fcn.predict( [ori_img_], visualize=True) pred_img = visdom_bbox(ori_img_, tonumpy(b_bboxes[0]), tonumpy(b_labels[0]).reshape(-1), tonumpy(b_scores[0])) rfcn_trainer.viz.image(pred_img, win='pred_img', opts={'title': 'predict image'}) # rpn confusion matrix(meter) rfcn_trainer.viz.text(str( rfcn_trainer.rpn_cm.value().tolist()), win='rpn_cm') # roi confusion matrix rfcn_trainer.viz.image(rfcn_trainer.roi_cm.value().astype( np.uint8), win='roi_cm', opts={'title': 'roi_cm'}) # get mAP eval_result = rfcn_md_eval(test_dataloader, rfcn_md, test_num=opt.test_num) lr_ = rfcn_trainer.optimizer.param_groups[0]['lr'] log_info = 'epoch:{}, lr:{}, map:{},loss:{}'.format( str(epoch), str(lr_), str(eval_result['map']), str(rfcn_trainer.get_meter_data())) # plot mAP rfcn_trainer.viz.line(Y=np.array([eval_result['map']]), X=np.array([epoch]), win='test_map', opts=dict(title='test_map', xlabel='px', ylable='mAP'), update=None if epoch == 0 else 'append') # plot log text rfcn_trainer.log(log_info) print(log_info) # if eval_result['map'].item() > best_map: cur_map = eval_result['map'] cur_path = rfcn_trainer.save(best_map=cur_map) if cur_map > best_map: best_map = cur_map best_path = cur_path print("save model parameters to path: {}".format(cur_path)) # update learning rate if (epoch + 1) in opt.LrMilestones: rfcn_trainer.load(best_path) print('update trainer weights from ', best_path, ' epoch is:', epoch) rfcn_trainer.scale_lr(epoch=epoch, gamma=opt.lr_gamma)