rishabh-akridata

Evaluation code for LVIS Dataset

1

Hello, Can you please provide the evaluation code for the LVIS dataset? Thanks

y_true==1 in PadimSVDD

2

Hi @Pangoraw, What is y_true ==1 in PadimSVDD? Does 1 mean normal image and 0 means anomalous? ``` pbar = tqdm(range(n_epochs)) for epoch in pbar: loss_epoch = 0 n_batches =...

Inference on Batches

1

Hi @Pangoraw, Is there any way to inference the model on larger batches such as 32 or 64 instead of 1? Thanks.

Question: EfficientAD Pred Scores are very low.

10

Hi, The pred scores of the efficient AD model are coming very low. Any idea, what is the reason behind this? ``` [0.5111125114597613, 0.5133660426906085, 0.5584840866012671, 0.5097309616622074, 0.5100746147399043, 0.5101457543058581, 0.5078011069118742, 0.49999999867182765,...

Similarity Scores coming very low between the video and the text features.

2

Hi @leexinhao, I am trying the text to video retrieval on my dataset using this https://github.com/OpenGVLab/InternVideo/blob/main/InternVideo2/multi_modality/demo_video_text_retrieval.ipynb, but the similarity scores are coming in very low between the text_features and the...

Hello @wudongming97, Thanks for the amazing work. Can we use this for the driving video dataset? Is the cam front, back, etc, mandatory? Thanks.

Hello, How to get the deployment ID for the custom finetuned object detection model support that we have in the vision agent? Thanks.