StawEndl

Results 4 issues of StawEndl

as title, ![img_v2_047d47ce-fbd3-4b72-ac2b-a7a2137154ag](https://user-images.githubusercontent.com/55580043/217997379-9806c09b-ad27-4aec-8b57-993f86453520.jpg) ![img_v2_fbe67f30-f95a-4b9d-bd40-776524b7761g](https://user-images.githubusercontent.com/55580043/217997403-4d72b603-ca18-41b1-b5e9-1ac6605f30ab.jpg) ![img_v2_281ee42a-f2c2-4367-8925-f2298aa66f8g](https://user-images.githubusercontent.com/55580043/217997416-aae3ab99-7df9-4277-a681-a0a01a0fd560.jpg) the error is : Traceback (most recent call last): File "/ai/home/project/sd-scripts-main/train_network.py", line 538, in train(args) File "/ai/home/project/sd-scripts-main/train_network.py", line 408, in train noise_pred = unet(noisy_latents, timesteps,...

do you have a pSp pretrained weight file? I predict a photo of a asian person with e4e, the person of result image is more like westerner.

what you are talking about, the meta_expressions.json, is rename from meta_valid.json? i rename meta_valid.json to meta_expressions.json, however, the code throw this exception: File "/ai/home/project/MeViS-main/lmpm/data/datasets/mevis.py", line 66, in load_mevis_json for exp_id,...

我现在是可以调用预测的engine文件了(根据你之前的加速模型预测那部分github的代码),但是deepsort部分的engine文件不会调用,是跟预测那部分一样吗?如果是,cuda.memcpy_htod_async(cuda_inputs[0], host_inputs[0], stream)中的host_inputs格式应该怎么写?因为模型预测只传图片,但是deepsort要传多个变量。。