FasterRCNN_KERAS
FasterRCNN_KERAS copied to clipboard
akshaylamba
what is the mAP of the model you trained on voc2007? I have trained the model but the mAP is 47.6 ?
Hi, i'd like to ask something regarding Faster R-CNN from the paper and the implementation here 1. Why the number of kernel/filter for rpn_classifer equals to num_of_anchor instead of num_of_anchor*2...
Hi I encounter the following error on line 265 of train_frcnn.py Exception generator has no attribute next due to X, Y, img_data = data_gen_train.next() on line 167 Could you please...
`inv_map = {v: k for k, v in class_mapping.iteritems()} ` 应该写成 `inv_map = {v: k for k, v in class_mapping.items()} `
What parameters of "faster rcnn" need to be adjusted when implementing small target detection?
It seems that when we use `train_on_batch` to train our Faster RCNN model, we couldn't change the batch_size directly as what in `model.fit( )`. So I just simply concatenated a...
After training all images, in my experiment, I have only one class except background, the loss also realize very low. But test other images, no object is detected. I am...
