Mahmood Hussain Bhat

Negative results -1 everywhere

3

I tried to train for 10000 iterations but results are -1 2021-07-02 11:05:55,223 fcos_core INFO: Using 2 GPUs 2021-07-02 11:05:55,223 fcos_core INFO: Namespace(config_file='configs/fcos/fcos_R_50_FPN_1x.yaml', distributed=True, local_rank=0, opts=['DATALOADER.NUM_WORKERS', '2', 'OUTPUT_DIR', 'training_dir/fcos_R__50_FPN_1x_logs'], skip_test=False)...

Thanks for your nice work. If I change the alpha during the testing time it produces false results. It generates black images instead of stylized imaged. what could be the...

Loss and Validation loss is nan

7

nms iou: 0.413 score: 0.3 Epoch 1/50 1125/1125 [==============================] - 408s 349ms/step - loss: 1367.1504 - val_loss: nan What can be the possible reason for val_loss becoming nan and after...

I have a few questions 1. Why model is not saved after training 2. How to calculate mAP for each class 3. How to run test on trained model

### Motivation - What is the use case for this feature? When trained Yolo(x) models on a different dataset and when we want to test those on another dataset but...

how to take some values as integers ? and also array as empty. Currently array contains atleast ""

Can you add a bit on how to use this? Installation and Usage

Thanks for your work! I would like to know how to train your model for paired iamge to image translation label to rgb image?

This helps users to quickly test algorithms, it also supports tests multiple algorithms at the same time on different data.

[Docs] add module config info to hitl

1

### Solved Problem Information on setting parameters to enable HITL Information on HITL not receiving motor commands Fixes #22625 ### Solution - Add docs to set parameters to get HITL...