The pretrained resnet152 from torchvision doesn't work
firolololo opened this issue · 5 comments
Sorry to bother you, I train the model as you did. And i try to test the model using some images from the network. I use the pretrained resnet152 model from torchvision, but the model doesn't work. I would be appreciate if you could tell me more details about the resnet152 you used. thanks for your generosity to share the code, it really helps. With best wishes！
Please see https://github.com/eric-xw/AREL/tree/master/misc for more details of the resnet model.
It's my fault to miss the extract features script, thanks for your time!
Sorry to bother you again, i still don't know how to resize the original image to (256, 256) as you did in "/mnt/sshd/wenhuchen/VIST/images_256/{}/". I chose the image of 800 * 600 from the json file such as train.story-in-sequence.json, but i can't get the same fc_features as the loading of .npy file when i try the resize method in cv or Image library.
This is the script we used to extract the ResNet features from images: https://github.com/eric-xw/AREL/blob/master/scripts/extract_features.py
Hi, despite using this script the results for me varied , was there some pre-processing (resizing etc ) to the original image before doing this step ?
That is steps to get the resnet image features from say this raw image which is part of VIST -> https://ibb.co/qxjgTtZ
Would appreciate all inputs.