I following the faster rcnn tutorial, but I faced some error

Community Help
1

So I was following the Faster RCNN notebook, but then until the step download base model.
The codes is as follows (I uses the same code in the tutorial notebook)

#downloading the base model
%cd /kaggle/working/models/research

import os
import shutil
import glob
import urllib.request
import tarfile
MODEL_FILE = MODEL + ‘.tar.gz’
DOWNLOAD_BASE = ‘http://download.tensorflow.org/models/object_detection/’
DEST_DIR = ‘/kaggle/working/research/pretrained_model’

if not (os.path.exists(MODEL_FILE)):
urllib.request.urlretrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)

tar = tarfile.open(MODEL_FILE)
tar.extractall()
tar.close()

os.remove(MODEL_FILE)
if (os.path.exists(DEST_DIR)):
shutil.rmtree(DEST_DIR)
os.rename(MODEL, DEST_DIR)

It output the line as this:

image
image1292×233 14.9 KB

I search through the downloaded files in research directory, there is no pretrained_model files too. Why is this happens? For your information, I was using kaggle to do it.

2

Hi @MheadHero

Going by what you shared, this could have something to do with the way you have your directories structured. Looks like what it’s expecting is a structure of /content/models/research

Another possibility (which is our fault, and something that I’ll be fixing on our end) is the curl command sample code is !curl -L https://app.roboflow.ai/ds/REPLACE-THIS-LINK instead of !curl -L https://app.roboflow.com/ds/REPLACE-THIS-LINK

I’d also change this to .com after fixing the directories