Michal Jamroz

Results 8 issues of Michal Jamroz

## Description ## To make sure training set image list contains at least one image of each class.Having all images of some class in `val` set makes a mess doing...

pr-awaiting-testing

Dear David, thanks a lot for great work! I've a question - since i am working with mtz image files, i've to convert it each time to ccp4 format. Do...

Is there any chance to implement torch `aten::scaled_dot_product_attention`? https://pytorch.org/docs/master/generated/torch.nn.functional.scaled_dot_product_attention.html says it could be done as ``` # Efficient implementation equivalent to the following: scale_factor = 1 / math.sqrt(Q.size(-1)) if scale...

enhancement
work/medium

Sometimes im getting `Missing key(s) in state_dict: "stem.conv1.c.weight", [...] Unexpected key(s) in state_dict: "_orig_mod.stem.conv1.c.weight", [...]` while trying to resume training from checkpoint of compiled (`--torchcompile=inductor`) model. This PR solves the...

in your examples, http://codepen.io/christianacca/pen/yNWeOP instead of ```javascript self.tableParams = new NgTableParams({}, { filterOptions: { filterFn: ageRangeFilter }, dataset: simpleList, filterLayout: "horizontal" }); ``` it should be ```javascript self.tableParams = new...

When im trying to use it on android 25, then i got the error as in the title. Is there any hope it will be working for the newest targets?...

| Questions | Answers | ------------- | ------------------------------------------------------- | Description? | Remove last name from response if anonymized name | Type? | bug fix | BC breaks? | no |...