Yan Changwei

hi, bryanyzhu, thank you for your opensource code! I has some questions, why video sampling rate is 1 in training, however is 25 in inference, is it reasonable？ Look forward...

Segmentation fault (core dumped)

1

hi， The problem of Segmentation fault(core dumped) is appeared when I save binary test result in the line https://github.com/yjxiong/action-detection/blob/master/binary_test.py#L172 I have checked the pickle.dump function with data of model output...

hi, liming, have you provide repository by pytorch? if so, could you share me by email: [email protected]. thank you! I look forward to you reply!

@wzmsltw Can you please share the BSN in THUMOS code details at [email protected] ? Thanks!

执行推理报错！

5

您好，按照github上给的pretrain_model目录放置好文件后，执行推理时报错，是否需要git lfs 下载所有的文件而不是仅仅下载目录列出的文件呢？ 报错信息时加载stable-diffusion-v1-5 这个目录的模型时报错。报错信息如下： pretrained_base_model_path:./pretrained_model/stable-diffusion-v1-5 Traceback (most recent call last): File "/root/miniconda3/envs/aniport/lib/python3.10/site-packages/diffusers/models/modeling_utils.py", line 109, in load_state_dict return torch.load(checkpoint_file, map_location="cpu") File "/root/miniconda3/envs/aniport/lib/python3.10/site-packages/torch/serialization.py", line 815, in load return _legacy_load(opened_file, map_location, pickle_module,...

本地网页端输入内容，生成数字人区域无反应？

7

如标题，如何解决这个问题，其他配置一切正常！

执行python app.py报错

3

RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)` 详细报错信息如下： [INFO] warm up ASR live model, expected latency...

修改python/site-packages/werkzeug/routing/matcher.py，注释websocket_mismatch = True

7

修改python/site-packages/werkzeug/routing/matcher.py，注释websocket_mismatch = True _Originally posted by @lipku in https://github.com/lipku/metahuman-stream/issues/12#issuecomment-1893484105_ 您能细致描述一下吗，我看是两个条件判断都设置为True, 但是我尝试均不成功。