Lychee X

Results 63 issues of Lychee X

hi,dear 大佬 这是我的一些浅显的问题, 请指点下,多谢 1.能不能提供下[数据集](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/data_make/map_item_idx.py#L4)? 2.[这里面](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/data_make/map_item_idx.py#L6)的 `data.columns = ['UId', 'ItemId', 'BrandId', 'MiddlesortId', 'ClickTime', 'Date']` middlesortId是啥?Date呢? 3.[负采样](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/model/model.py#L24)是怎么做的啊? `self.sub_sample = tf.placeholder(tf.int32, [None, None]) # soft layer (pos_clict,neg_list)[B,sub_size]` 4.y是什么呢?怎么是2维的呢?是one-hot之前的吧?[link](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/model/model.py#L25) `self.y = tf.placeholder(tf.float32, [None,...

或者你们模型的同步升级。

hi,dear just the first line code `>>> from kandinsky2 import get_kandinsky2` then got the error

0.185 Traceback (most recent call last): 0.185 File "code-fix.py", line 27, in 0.185 save_file(basicsr_utils_misc, fix_version_check(read_file(basicsr_utils_misc))) 0.185 File "code-fix.py", line 4, in read_file 0.185 file = open(filepath, "r") 0.185 FileNotFoundError: [Errno...

hi,dear, could you supply the pretrained model for the eleven sound event detetion ? I want to test some data, thx

hi,dear, could i use batch_size in img2img ? thx

hi,dear, In your [codes](https://github.com/sebastianbk/finetuned-resnet50-keras/blob/master/resnet50_predict.py#L15),you directly use the raw data for predict without Norm such as x/255.0, or other fixed mean and std paras as [this](https://github.com/tensorflow/models/blob/master/official/vision/image_classification/resnet/imagenet_preprocessing.py#L57) and [this](https://github.com/tensorflow/models/blob/master/official/vision/image_classification/preprocessing.py#L130) why not ?...

as the title, LLM is always used for English very well , but not good for Chinese . So how about the performance of Chinese ?

hi,大佬,能够将输入的文本当做歌词来唱吗? 感谢,各位也看看,有没有实现这种的啊?