eeric
eeric
the speed of model pruned did not improve, how to your work?
how to obtain VGG16: flops = [3.1, 57.8,14.1, 28.9, 7:0, 14.5,14.5,3.5, 7.2,7.2, 1.8,1.8, 1.8, 1.8] according to FLOPs = 2HW(CinK2 + 1)Cout? for example, no.1 conv FLOPs(0) = 3.1, while...
Could it was pruned to ResNet model? If ResNet model loaded, it occured error to FilterPrunner.
when hundreds of classes, accuracy is nearly 0.0
On ImageNet set, it occured as following: File "train.py", line 245, in main() File "train.py", line 241, in main engine.train(h, train_loader, opt.epochs, optimizer) File "build/bdist.linux-x86_64/egg/torchnet/engine/engine.py", line 39, in train File...
some label format such as .txt, it exist '\n', so the 146th line in Yolo2Pascal-annotation-conversion/yolo2pascal/yolo_io.py, modified as following: classIndex, xcen, ycen, w, h, _ = bndBox.strip("\n").split(' ')
besides, is it minus to " - " in formula (1)? in paper.
Training: 412-Speed 556.82 samples/sec Loss 42.4856 LearningRate 0.001128 Epoch: 0 Global Step: 600 Fp16 Grad Scale: 256 Required: 426 hours >>> 2 gpu, bs=320, wf42m >>>num_workers=16, sample_rate=0.2 >>>dali_data_iter(..., num_threads=16, ...)...