search

sunnyxiaohu / R-C3D.pytorch

R-C3D pytorch implementation
248 stars 67 forks source link

Why your model has such impressive performance? #57

Open mlii0117 opened 4 years ago

mlii0117 commented 4 years ago

I downloaded your trained model (C3D on THMOUS14) and tested, I got mAP 37 for threshold 0.5. It is higher than SOTA. But I noticed that the Len(dataloader) is 8355, which should be 13000+. Could you share more training details? Really appreciate for that

mlii0117 commented 4 years ago

Well, I understood why it was 6855, but still be confused to the THUMOS14 performance.

jafar-pivotchain commented 4 years ago

Hi Draven, I am trying to run this code for the CPU by customizing it a little. I am however facing some issues in the roi_temporal_pooling module. While running this block my code is unable to find the file roi_temporal_pool in the R-C3D.pytorch/lib/model/roi_temporal_pooling/_ext/roi_temporal_pooling folder. there just has a init.py file which imports this from ._roi_temporal_pooling import lib as _lib, ffi as _ffi. I am stuck on this error ModuleNotFoundError: No module named 'model.roi_temporal_pooling._ext.roi_temporal_pooling._roi_temporal_pooling'. I see you have successfully run the code. It would be great if you share the same with me.

mlii0117 commented 4 years ago

Hi,

I run the code on GPU, I never try it on CPU. Its a important step to make the layer, and I thought the make.sh is related to your GPU. So if you use GPU and follow the instructions, the training will be easier.

qinguoyi commented 4 years ago

hi, the reason was mentioned in author's master's thesis. The author thought it was mainly due to the adoption of better hyperparameters and the difference between framework execution, Pytorch vs Caffe.