kang sheng

```go var ( letterMap = []string{ " ", "", "abc", "def", "ghi", "jkl", "mno", "pqrs", "tuv", "wxyz", } res = []string{} final = 0 ) func letterCombinations(digits string) []string {...

```go func zigzagLevelOrder(root *TreeNode) [][]int { var res [][]int search(root, 0, &res) return res } func search(root *TreeNode, depth int, res *[][]int) { if root == nil { return }...

I have improved F1 measure to 71% by change deteval. You can change tr=0.8 and tp=0.4 in deteval just as the paper Object count/Area Graphs for the Evaluation of Object...

@princewang1994 I tried to run my code. It seems that the result is caused by postprocessing. I have the code which is written by Long Shangbang, who is the first...

I run some experiments and here is the result. These five experiments used the same model. exp_name| backbone| input_size | iter | post process | eval | tp | tr...

Eval means eval script. Long writes his own eval script according to det eval paper.

@princewang1994 What do you mean expand the boundary of text instance? Do you just multiply radius by 1.3 at line 110 in detection.py or you change the boundary of ground...

I'm sorry that I made a mistake about long's eval script. The correct p/r/f is 0.867/0.744/0.803, I modified the table above. Long said they expanded the boundary.

A simple implemention may be: 1. add `all_reduce(num_items_in_batch, op=SUM)` after: https://github.com/huggingface/transformers/blob/main/src/transformers/trainer.py#L2416 2. add `loss *= get_world_size()` after: https://github.com/huggingface/transformers/blob/main/src/transformers/loss/loss_utils.py#L26

I tested multi-gpu performance with or without all_reduce. First, with `num_items_in_batch = all_reduce(num_items_in_batch)`, all loss curves matched exactly.  Then, compared with the version without `all_reduce`, the loss curves mismatched:...