Closed alwc closed 4 years ago
Actually the negative examples are got from the L-CNN. I just copy the npy files from the L-CNN and integrate them info the json file.
Let me check the old file tomorrow.
Hi @alwc, I have checked the edges_negative with the L-CNN's ***_0_label.npz. The length of negative edges and the values are all the same. I did not run the L-CNN's script to generate negative examples. Did you try to compare the JSON file with the L-CNN's preprocessed data?
Hi @alwc, I have checked the edges_negative with the L-CNN's ***_0_label.npz. The length of negative edges and the values are all the same. I did not run the L-CNN's script to generate negative examples. Did you try to compare the JSON file with the L-CNN's preprocessed data?
Hi @cherubicXN , I checked the edges_negative
in L-CNN's ***_0_label.npz and HAWP's JSON file and they matched like what you've said.
An additional note: I tried to use my modified code above to generate the edges_negative
label and trained a new model with it. I ended up with sAP10.0 = 66.6
at epoch 27 and 28.
This could be due to 1) randomness 2) I got my negative samples from the (image_w / 2 × image_h / 2) low-resolution bitmap instead of "64 × 64 low-resolution bitmap"
Hi @alwc, I have checked the edges_negative with the L-CNN's ***_0_label.npz. The length of negative edges and the values are all the same. I did not run the L-CNN's script to generate negative examples. Did you try to compare the JSON file with the L-CNN's preprocessed data?
Hi @cherubicXN , I checked the
edges_negative
in L-CNN's ***_0_label.npz and HAWP's JSON file and they matched like what you've said.An additional note: I tried to use my modified code above to generate the
edges_negative
label and trained a new model with it. I ended up withsAP10.0 = 66.6
at epoch 27 and 28.This could be due to
- randomness
- I got my negative samples from the (image_w / 2 × image_h / 2) low-resolution bitmap instead of "64 × 64 low-resolution bitmap"
That's awesome! Let me try it as you said.
Hi @cherubicXN
I'm trying to pre-process the dataset from scratch using the
train.json
file from https://github.com/cherubicXN/afm_cvpr2019 and some modified code from https://github.com/zhou13/lcnnI can reproduce
edges_positive
andjuctions
correctly, but I can't seem to exactly match theedges_negative
numbers found in your provided json file.Here is my code modified from L-CNN's repo: