Potential bug

[adnan1306]

In line286 of main.py, it should be:
new_mask = np.where(abs(tensor) > percentile_value, 0, mask[step])
so that smaller weights are set to zero.

Lottery-Ticket-Hypothesis-in-Pytorch/main.py

Line 286 in 34a8c96

new_mask = np.where(abs(tensor) < percentile_value, 0, mask[step])

[wanxinran]

No the code is correct, check the np.where docs. 0 is set when tensor is smaller than the cutoff value.