xia
thank you for your advice!
batch size should be 25?
[phoneModel.txt](https://github.com/KHwang9883/MobileModels/files/5487158/phoneModel.txt) 应该是JSON文件的，但是因为只支持txt格式，其实都可以直接读取。 数据示例: ``` { "1501-A02": "360 手机 F4 全网通版", "1501-M02": "360 手机 F4 移动版", "1503-A01": "360 手机 N4 全网通版", "1503-M02": "360 手机 N4 移动版", "1505-A01": "360 手机 N4s", "1505-A02":...
没有冲突，看我前面提到的处理过程
@suvojit-0x55aa there should be 200k images in Celeba HQ,but your sharing are 30k of them.
sorry for my careless check,you're right.
Another question,how could i use the `list_attr_celaba.txt` namely attribution label for celaba-hq.Does the 30k images of celeba-hq are first 30k of 200k images in celaba dataset?
Got it ,there is a image list file https://raw.githubusercontent.com/nperraud/download-celebA-HQ/master/image_list.txt which releated celaba and celaba-hq files.
@gevorgter can you please list the lines that should be changed?I changed some lines but result in failed as well. line 105: ``` centroids[j] = centroid_sums[j] / (np.sum(assignments == j))...
Yes,the default code is ok to go. I want to make some deeper explore. If the dataset is not `mnist`, your code goes the route without any label(all images with...