Dan Erez

get all inf?

5

ExtraTreesClassifier ============================================================ Model accuracy Time/clf (s) --------------------------- ---------- -------------- SGDClassifier -inf inf LogisticRegression -inf inf Perceptron -inf inf PassiveAggressiveClassifier -inf inf MLPClassifier -inf inf KMeans -inf inf KNeighborsClassifier -inf inf...

Implemented as in the article?

1

First of all thank you for implementing the v2 of this paper and maintaining. ** warning - I am mainly a keras/tf user ** If I am reading this correctly...

training procedure

8

Hi , First of all thanks for this great work ! I would like to replicate your system for a custom object detector. What were the steps you took to...

how to calculate taxes?

4

Hi - I'd like to incorporate simple taxes rules - loss of 25% on any actualized profit ``` def commissions(quantity, price): return max(0, price * quantity * .25) ``` I...

Hi, Thanks for this amazing wrapper. It is so much better than google's api. using the following code : ``` query_result = google_places.text_search( query="random place", lat_lng={"lat": 33.5, "lng": -86.8}, radius=100)...

clarification : gram ctc - alphabet_size ? "a","b" or "ab" single logits output?

3

Thank you very much for your implementation of ctc varients. To be frank I think that is the main value of this repo and I would change its name to...

how can I use this?

13

It's awesome you implemented this in pytorch. I am really not sure how I can use this on my net. I see there's a demo.py but unless I'm missing something...

LSTMS are nice but they are super heavy. Recently there was a lot of work on convolutional networks for sequence tasks - the highlight is conv seq to seq and...

python 3 error all over the place

5

a small portion of the errors : compile options: '-DENABLE_PYTHON_MODULE -D__PYTHRAN__=3 -DPYTHRAN_BLAS_BLAS -I/usr/local/lib/python3.5/dist-packages/pythran -I/usr/local/lib/python3.5/dist-packages/numpy/core/include -I/usr/local/include -I/usr/include -I/usr/include/python3.5m -c' extra options: '-std=c++11 -fno-math-errno -w -fno-wrapv' arm-linux-gnueabihf-gcc: build/pyeyeengine/calibration/auto_calibrator.cpp cc1plus: warning: command line...

I would love to skip over the training if you have a pretrained net on hand. Do you? Thanks, Dan