David Solomon

add this code at evaluate_net.py:92 results = mod.score(eval_iter, metric, num_batch=None, batch_end_callback=mx.callback.Speedometer(batch_size, frequent=10, auto_reset=False)) The simple answer: Now You will get the forward time. The complicated one: As far as I...

I tried but had no luck.. Aside from casting inputs I ran into some errors that I didn't handle Did you try yourself? On Feb 21, 2018 6:20 AM, "kaishijeng"...

Look at symbol/symbol_builder.py it calls the next function which is the answer for all your questions ******* mx.contrib.symbol.MultiBoxTarget( *[anchor_boxes, label, cls_preds], overlap_threshold=.5, \ ignore_label=-1, negative_mining_ratio=3, minimum_negative_samples=0, \ negative_mining_thresh=.5, variances=(0.1, 0.1,...

Adding to this list, the new mobileNet512x512 gives 67.5 mAP

You are right, I discovered a bug in my code and when I fixed it, the results were the same as reported On Nov 7, 2017 8:51 AM, "jyuan" wrote:...

I automated the scales of the anchors, and my calculations were wrong. This resulted with a model that learned on certain scales, and was evaluated on others. Working on a...

Is there anythink new?