chenguitao
chenguitao
文本框未合并的效果  合并文本框之后的效果,水平框距离多远需要合并,根据阈值操作 
> 请问一下你是怎样实现矩形框合并的 @chen849157649 @mayidu ,点击[https://github.com/xiaomaxiao/PSENET/blob/master/predict.py#L64](url),这个项目中写了文本框合并操作。你参考看看
> @chen849157649 大神你好,你发的那个合并框的链接过期啦,能否再发一个,想了解一下怎么做的 @jiangzz1628 复制链接到浏览器再打开
@nbei , Watermark Removal in YouTube video
features.py中,embedding_name = group_name + '/' + feat_meta.name + '_d' + str(feat_meta.dim) + '_to_d' + str( embedding_dim)若是执行if slot_name in self.dense_feats_slots:这句会报错 'DenseFeature' object has no attribute 'one_hot_dim',所以embedding_name应该放到判断语句内部,分别计算embedding_name
add a line code: multiprocessing.set_start_method('spawn') as follow: def parallel_greenscreen(file_path, worker_nodes, gpu_batchsize, model_name, frame_limit=-1, prefetched_batches=4, framerate=-1): multiprocessing.set_start_method('spawn') manager = multiprocessing.Manager()
sudo apt-get install ffmpeg
@erhuodaosi loss function error, modify : def total_variation_loss(image): # shift one pixel and get difference (for both x and y direction) loss = torch.mean(torch.abs(image[:, :, :, :-1] - image[:, :,...