Are these kinds of architectures useful for classification as well?
Do we have pretrained models for Densenet (trained on imagenet for example)?
The tiramisu model scores seems to indicate overfitting, is it a problem ?
Sorry! something weird was happening with my streaming video. I had to refresh my page !!
re Densnet Tiramisu: If no hand annotated segmentation maps are available - is there another way to create rasonable performance using e.g. some unupervised segmentation and using this to train the model
@jeremy and @rachel thank you both for this wonderful well thought out course. I have benefited a lot from the course and thanks for doing the remote international fellowship and selecting me for this group.
I don’t think I made a strong recommendation one way or the other. GRU is a somewhat simpler architecture and therefore may be a little faster. But either one is fine really.
Hi there,
I am trying to understand the def statements. Which one removes the log transformations on the predictions?
-
def log_max_inv(preds, mx = max_log_y):
return np.exp(preds * mx) -
def normalize_inv(preds):
return preds * ystd + ymean
Given other code in the notebook it makes me think it is (1) def log_max_in
preds = np.squeeze(model_pkl.predict(map_valid_pkl, 1024))
y_orig_pkl_val = log_max_inv(y_pkl_val, max_log_y_pkl)
If I am correct then what does normalize_inv even do?
are you able to call model.predict with the code from the rossman lesson using the xgboost model? i tried and all the predictions are the same.
pred=model.predict(Xdata_val