Goofy

It doesn't work. After change input_shape to (28, 28, 1), got the following `Traceback (most recent call last): File "dcgan.py", line 167, in train(BATCH_SIZE=args.batch_size) File "dcgan.py", line 105, in train...

I found the latest version of connexion and flask that adapt to the current version of swagger editor is: - connexion==2.14.2 - flask==2.3.3 - Python==3.12.0

I solved this error by change > preds_sort = np.argsort(preds[0][0]) to > preds_sort = np.argsort(preds[0]) in file "imagenet_decoder.py"

最近太忙了，有时间我尽量

有的啊 在darknet的readme里

In my code, I use the code in [Deep-Model-Transfer/preprocessing/inception_preprocessing.py](https://github.com/MacwinWin/Deep-Model-Transfer/blob/9d3e148020911bae41b5876fb0c87427ec7f4ccd/preprocessing/inception_preprocessing.py#L235) to convert the image format. You forget to normalized the image to [-1,1], so the network can not recognize it correctly.

I'm sorry reply for you so late. The labels_file will generated automatically when you run the convert_data.py. So in set_train_env.sh, you only have to set labels_file path.