Ajith

u can use torch == 0.4.0 , but if u r GPU gene code is of higher extend or cuda is =/+ 10 like that u may face issue there...

@aeviar you can use this code , just remove image.cuda() and use image https://github.com/yhenon/pytorch-retinanet/issues/200#issuecomment-748992020

@crystal0523 if it helps please close the issue Use below command to run the file and code as visuvalize_single_image.py !python visualize_single_image.py --image_dir="frames" --model_path="../coco_resnet_50_map_0_335_state_dict.pt" ``` import torch import numpy as np...

@aditjha convert you video to frames and place it in folder use below code for inference. https://github.com/yhenon/pytorch-retinanet/issues/200#issuecomment-748992020 code to split video to frames ``` import cv2 vidcap = cv2.VideoCapture('sample2.mp4') success,image...

@Karthik-U-94 you can use this https://github.com/yhenon/pytorch-retinanet/issues/200#issuecomment-748992020

@Nico31415 could you provide the dataset link please

request.json() is returning none @Abhijit5676 thats the cause of this error

@Abhijit5676 try this it works `curl -i -X POST -H "Content-Type:application/json" -d "[5.9,3.0,5.1,1.8]" http://localhost:5000/predict`

@BigPig117 were you able to solve it

try to print the path and see ``` def create_tf_example(group, path): print(path) print(os.path.join(path, '{}'.format(group.filename))) ``` whether the path is correct or not