Qian Li

同问，我也想知道

> 碰到一样的问题 怎么解决的呢，感谢

I solved this problem, /linear_cos/architecture.py is on line 87, Converting"return tf.sqrt(tf.reduce_sum(filt*filt, [0, 1,2], keep_dims=True)+eps)"   To "return tf.sqrt(tf.reduce_sum(filt*filt, [0, 1], keep_dims=True)+eps)"

> As for me, I train the model from scratch and DB works very well on long texts. Texts in the public scene text datasets are mostly short english words....

> > @ahsdx 那icdar2015的实验结果你跑出来了吗 > > 没有 我调整了一下参数，shortsize为480，然后box threshold调整为了0.5，让网络训练得分低的框，让它变大，精确度达到了98%左右，但是召回只有90%，真实场景数据还需要改配置

> 使用TensorRT8.2版本会存在内存泄露的问题，内存会一直消耗增加，且显卡有占显存，但看不出在计算 请问解决了嘛，我也遇到了相同的问题

I also encountered the same problem, but I loaded two trt models at the same time. My method is: first, mapping the torch2trt inc and lib paths to the include...

> I've converted the coco_dataset into the voc style, the flag txt in ImageSets for each class and rewrite the label and label_1c for coco which generates labels' txt. >...

> Hello, I have trained a Bert with vocab_size 21128, and I noticed that in BLIP the vocab_size should be 21130 (including 2 additional tokens:DEC,ENC). However, this difference caused a...

> @futureisatyourhand Hi~How did you evaluate the base model？Did you execute `python valid_ensemble.py cfg/metayolo_novel0.data cfg/darknet_dynamic.cfg cfg/reweighting_net.cfg path/toweightfile` ？ Hello, I have solved the problem, but the AP is much higher...