Closed vict0rsch closed 3 years ago
Main additions:
More comet logging:
comet: display_size: 20 rows_per_log: 5 # number of samples (rows) in a logged grid image. Number of total logged images: display_size // rows_per_log
Better s image logging with utils.get_display_indices:
s
utils.get_display_indices
... if domain == "s": with temp_np_seed(123): # deterministic random display_indices = np.random.permutation(length)[:dsize] ...
New SegmentationDecoder
SegmentationDecoder
New option: data.max_samples=n to limit the size of the dataset (for instance for dev purposes, n=-1 for no limitation)
data.max_samples=n
n=-1
Add tqdm logging
tqdm
Add self.G.eval() and self.D.eval() for the inference mode, especially for batch norm and dropout
self.G.eval()
self.D.eval()
v0 for an almost automatic resume.py
resume.py
hyper parameter search
Automatic comet experiment continuation:
... with comet_previous_path.open("r") as f: url = f.read().strip() comet_previous_id = comet_id_from_url(url) ... exp = ExistingExperiment(previous_experiment=comet_previous_id, **comet_kwargs) ...
@alexrey88 I refactored the evaluation as you pointed out, do you see any other weird things?
All seems good :)
Main additions:
More comet logging:
Better
s
image logging withutils.get_display_indices
:New
SegmentationDecoder
New option:
data.max_samples=n
to limit the size of the dataset (for instance for dev purposes,n=-1
for no limitation)Add
tqdm
loggingAdd
self.G.eval()
andself.D.eval()
for the inference mode, especially for batch norm and dropoutv0 for an almost automatic
resume.py
hyper parameter search
Automatic comet experiment continuation: