google-colaboratory

I have trained an object detector using tensorflow's object detection API on Google Colab. After researching on the internet for most of the day, I haven't been able to find a tutorial about how to run an evaluation for my model, so I can get metrics like mAP. I figured out that I have to use the eval.py from the models/research/object_detection folder, but I'm not sure which parameters should I pass to the script. Shortly, what I've done so far is, generated the labels for the test and train images and stored them under the object_detection/images folder. I have also generated the train

I've recently started to use Google Colab, and wanted to train my first Convolutional NN. I imported the images from my Google Drive thanks to the answer I got here . Then I pasted my code to create the CNN into Colab and started the process. Here is the complete code: Part 1: Setting up Colab to import picture from my Drive (part 1 is copied from here as it worked as exptected for me Step 1: !apt-get install -y -qq software-properties-common python-software-properties module-init-tools !add-apt-repository -y ppa:alessandro-strada/ppa 2>&1 > /dev/null !apt-get update -qq 2>&1 > /dev/null !apt

This may be a dumb question, but does a job stop running on a Colab instance when I close my browser? If not, is there a way to keep it running (i.e until it's complete) In that same vein of thought, if I were to give someone edit access to my Colab notebook, would it be running on my instance of Colab with all my installed libraries or on theirs? The current cell will continue executing once you close your browser, but the outputs will not end up in the notebook in Drive. (If you were to reconnect before your VM were considered idle and deleted, any values you'd computed would still be

I load some (not so) big data into it. A compressed file at 9GB. It can't decompress because the disk space is not enough. What's the current hardware spec? What's the disk size? Bob Smith You can see the disk information using a command like !df -h . To see CPU specs, !cat /proc/cpuinfo . For memory, !cat /proc/meminfo . Here's an example notebook: https://colab.research.google.com/notebook#fileId=1_x67fw9y5aBW72a8aGePFLlkPvKLpnBl Here I run some test. https://colab.research.google.com/notebook#fileId=1dint4ly-7h8Trw0XRJ1uhC_VKe_wDJfY In short: n1-highmem-2 instance 2vCPU @ 2.2GHz 13GB RAM

I need to install a library that is only compatible with Python 3.5, is there a way to change the Python version in Colab from 3.6 to 3.5? The only way to vary the python3 version is to connect to a local runtime . 来源： https://stackoverflow.com/questions/52467489/is-there-a-way-to-use-python-3-5-instead-of-3-6

I have a file named imutils.py that has just one definition namely abc() which returns the sum of 2 integers. Now I want to use this definition in a separate collab file but I am unable to. The method I used was to first upload the file imutils.py to drive and then importing it and using the definition. The error says module 'imutils' has no attribute 'abc' To upload I first used 2 methods : First I uploaded using the drive GUI and then I also tried the above using the code. Uploading in both cases was successful from google.colab import files files.upload() If your Python file is in Drive, it