ShuxunoO

api_server runs too slowly

2

when I use the api_server, I found that it runs too slowly. With the same hardware and environment, web_server is 3-5 times faster. What is the reason for this and...

Update reader.py

4

Try to fix the bug about KeyError: 'xxx_0.txt' when using “clip-retrieval inference” command. For more details please refer to：https://github.com/rom1504/clip-retrieval/issues/352

A possible solution to solve KeyError: 'xxx.txt' when using “clip-retrieval inference” command

5

I met the same error as https://github.com/rom1504/clip-retrieval/issues/345 when I used `clip-retrieval inference` command to extract images and corresponding texts features, my command is like following: ``` clip-retrieval inference \ --input_dataset...

How can I infer my single img?

5

I want to test the model with my demo img， how can I do this？

Faiss assertion 'blasStatus == CUBLAS_STATUS_SUCCESS' failed in virtual void faiss::gpu::StandardGpuResourcesImpl::initializeForDevice(int) at /project/faiss/faiss/gpu/StandardGpuResources.cpp:335

3

# Summary I used model to extract features and saved them in `.npy` format, but I encountered an exception when using `faiss-gpu` to create an index. It seemed to be...

Can I load the "pretrain_vitL" model with a local path?

4

When I try to laod the pretrained **blip2_pretrained_vitL.pth** model weights ``` device = torch.device("cuda:7" if torch.cuda.is_available() else "cpu") model, vis_processors, _ = load_model_and_preprocess("blip2_feature_extractor", model_type="pretrain_vitL", is_eval=True, device=device) ``` I met some...

`train_dataloader` must be implemented to be used with the Lightning Trainer

1

hello I am going to train CLIP with my own dataset, but I met a exception : > raise MisconfigurationException("`train_dataloader` must be implemented to be used with the Lightning Trainer")...