alimeituan

bug 0.5.4

1

Traceback (most recent call last): File "/bin/image2text.py", line 5, in from clip_interrogator import Config, Interrogator, list_caption_models, list_clip_models File "/lib/python3.9/site-packages/clip_interrogator/__init__.py", line 1, in from .clip_interrogator import Interrogator, Config File "python3.9/site-packages/clip_interrogator/clip_interrogator.py", line...

slim里面是啥？

1

哈喽，大佬你好 我看到slim，不知道是干啥的，我记得tf中有slim啊，不一回事？

About the datasets

5

Hi, Glad to see the source codes. Now I find the signals in the [link](http://spandh.dcs.shef.ac.uk/gridcorpus/#downloads) Should I download the first two columns ? And then put them at the AudioData/...

hi, want to use the trained model to have a test, could u please provide the model ? thx Lychee

How to use in Language C?

2

Dear, What's the API of C ? I just want to test the project in C. Thx

When I make,it ups bug

1

Dear, After I install all dependencies, I make just as the pic down `make`  If I ignore the question,when I use Python3.6 it also ups bug as follows ...

Could You please update the project ?

1

Dear, Thanks for your share, you know the tensorflow update all the time, some functions in tf maybe cause warnings. when I run train_tfrecord.py `WARNING:tensorflow:From D:\python\kws\KeywordSpotting-master\train_tfrecord.py:128: string_input_producer (from tensorflow.python.training.input) is...

RuntimeError: "exp_vml_cpu" not implemented for 'Half'

7

hi，dear 大佬，这个是啥问题啊， ``` >>> video = pipe( ... input_image=image.resize((512, 512)), ... num_frames=128, fps=30, height=512, width=512, ... motion_bucket_id=127, ... num_inference_steps=50, ... min_cfg_scale=2, max_cfg_scale=2, contrast_enhance_scale=1.2 ... ) Traceback (most recent call last):...