Is there an implementation of Faster-RCNN with fastai2 (or even v1, but preferably v2).
No. I started looking at it but didnāt get far. If you search GitHub Iām pretty sure it was done in v1 before
@muellerzr did you get a chance to look at this ^
@barnacl I did not, apologies, itās crazy both here on the forums (with the new course) and at home so give me a few days and Iāll take a look 
1 Like
absolutely, thank you
[Lesson6 - CustomUnet]
Hi! I have a question according your custom UNET. After adding the new head to the model, you initialize the layers with apply_init(nn.Sequential(layers[3], layers[-2]), init)
Why do you pass in this new Sequential-model: nn.Sequential(layers[3], layers[-2])? I am a bit confused with the indices. Which layers do you address?
[Lesson6 - RetinaNet] - Inference
Hi! I walked through your functions for inference in the github repo. But I am not quite sure, what is stored in the output parameter of your functions and where does it come from?
`def process_output(output, i, scales, ratios, detect_thresh=0.25):``
def show_preds(img, output, idx, scales, ratios, detect_thresh=0.25, classes=None):
def get_predictions(output, idx, detect_thresh=0.05):
Which function should I use for inference get_predictions or process_output?
Thatās taken from the fastai source code. The simplest way to debug this is to simply add a line that prints them out in that __init__ function 
Output comes from the model., and if you notice get_predictions calls process output, so use get_predictions
1 Like
Thanks for your answer! Have tried this on your own? When I do learner.predict I get an error:
samples = [(s[0], *clip_remove_empty(*s[1:])) for s in samples]
TypeError: clip_remove_empty() missing 2 required positional arguments: 'bbox' and 'label'
learn.predict will not work. It (predict) is not setup for object detection yet, hence why we are doing this. You can read more from this discussion: Object detection using fastai v2
2 Likes
Thanks a lot!
this is a regression problem so using accuracy as the metric is not ideal. Say for a particular input if the predictions were 0.4, 0.3, 0.1 for three epochs the loss decreases but the accuracy remains same(Threshold being 0.5). Can take this of your to do list @muellerzr (I should have realised that accuracy and regression donāt go together)
1 Like
Thatās okay, itās easy to think the opposite (I didnāt even realize it reading whatās in front of me!) Great job investigating 
1 Like
Just a heads up, Iāve added a snippet into the Segmentation notebook discussing weight loss functions
1 Like
What is the reason for specifying size=224 for most of the datasets? Any particular study showing why itās effective?
Iād go watch last years course (first two lessons IIRC), Jeremy goes over it and why it ājust worksā
1 Like
I agree it just works. In recent BengaliAI kaggle competition, lot of people used that image size to get over 0.98 mark in public LB
In the the fastai book itās explained as follows:
Why 224 pixels? This is the standard size for historical reasons (old pretrained models require this size exactly), but you can pass pretty much anything. If you increase the size, youāll often get a model with better results (since it will be able to focus on more details) but at the price of speed and memory consumption; or vice versa if you decrease the size.
1 Like
stuck with the multimodal notebook because iām not able download/unzip the data.
The data seems to be downloaded but is throwing an error when i try to unzip it.
Thank you.
1 Like
Not actually the steps to do it 
Try to follow the steps in this notebook https://github.com/muellerzr/Practical-Deep-Learning-for-Coders-2.0/blob/master/Tabular%20Notebooks/02_Regression_and_Permutation_Importance.ipynb specifically the video linked, and if that doesnāt work download the zip and upload it to google drive