BossunWang
BossunWang
Hi, experts That's a nice idea and work on cross domain I would like to know the performance on LFW, AGEDB, CFP-FP and compared with any STOA(e.g ArcFace, cosface) and...
Hi expert, How to guarantee cos(g,gPC) ≥ 1/2 subject to the inequality form? L(θ+)
Hi expert, I try to verify histogram with your "label.txt" on Figure 3(b) but I found large difference between Figure 3(b) and label.txt. The following statistics from "label.txt": data size:...
Hi expert, Nice work and novel view to use OT method. As you mentioned on your paper "The bias of a neuron is set to zero in all of the...
Hi, Expert, I am studying about pseudo labeling, and I read your code about generating pseudo labels by EMA prediction. But I would like to understand how to do update...
Hi expert, I install by pip as following: pip install salesforce-lavis or pip install -e . There are aborted to "corrupted size vs. prev_size" when I import lavis. And I...
There is a limit about maximum of recursion depth and I suggest this issue should be used approximation method rather than recursive. matched_patterns_start_indices_dict = pattern_matcher.get_matching_patterns(op_types_sliding_window) File "/usr/local/lib/python3.8/dist-packages/aimet_common/graph_pattern_matcher.py", line 180, in...
Hi expert, May you tell me where arithmetic weightings by each class on eq. 11? I study your code and find out exchange alpha and target alpha only. [dirichlet_reverse_kl_divergence](https://github.com/KaosEngineer/PriorNetworks/blob/d6f6ffb65bbd6cfddea9726725fe6eabd501827b/prior_networks/priornet/dpn_losses.py#L151)
Hi, expert The proposed attention mechanism using the weights of fc layer to generate an attention map. I would like to know setting bias is true whether to affect the...
Hi experts, I would like to know my onnx model test using C# and Barracuda 3.0.1. There is large precision discrepancies compared to onnxruntime using python which at 1e-1, and...