Domain: forums.fast.ai

NotADirectoryError: [WinError 267] The directory name is invalid: data\\BTS\\valid\\features.npy'

NotADirectoryError: [WinError 267] The directory name is invalid: data\\BTS\\valid\\features.npy'

My complete code is as below: `import sys sys.path.append(“C:\Users\Anurag\github_pro\fastai”) from fastai.imports import * from fastai.transforms import * from fastai.conv_learner import * from fastai.model import * from fastai.dataset import * from fastai.sgdr import * from fastai.plots import * PATH = “C:\Users\Anurag\github_pro\fastai\courses\dl1\data\BTS\” sz=224 arch=resnet34 data = ImageClassifierData.from_paths(PATH, tfms=tfms_from_model(arch, sz)) learn = ConvLearner.pretr...

favicon
fast.ai
ImportError: DLL load failed: The specified module could not be found

ImportError: DLL load failed: The specified module could not be found

I went back to work on the first lesson and now I’m getting errors with PILL(pillow). I seem to be getting this error in a number of other notebooks as well. Things were working yesterday and I can’t remember what I changed. I uninstalled pillow and reinstalled. That didn’t seem to work. Ideas? Thank you. from fastai.imports import * ImportError Traceback (most recent call last) in () 1 # This file contains all the main external libs we’ll use ----> 2...

favicon
fast.ai
Cheap Effective GPUs?

Cheap Effective GPUs?

Hello, I’m looking to build my own DL rig. I don’t mind getting top hardware (with reasonable bang for the buck). One area that bothers me is GPUs. It seems like graphics cards are overpriced at the moment (e.g., 1080 Ti regularly goes for over $1k when in stock). Given this card is almost a year old and almost 2x original MSRP, does it still make sense to get? I’m thinking crypto mining craze may not go away soon, so what’s a good alternative in today’s environment to still get by and take fas...

favicon
fast.ai
Making your own server

Making your own server

Here are the components I chose. SSD Graphics Card Memory CPU Motherboard Cooler Power Supply Case

favicon
fast.ai
Making your own server

Making your own server

I am working on a project that aims to solve home inventory evaluations (that is to say what is your stuff worth helping with filing homeowners insurance claims, estate planning, etc.) in part with a neural net. Taking the initiative, a colleague and I are going to build our own servers since AWS has been a real stumbling block. My coworker (assuming this is the same buddy you refer to in the previous sentence? If so, carry whatever language you initially use to describe him to be consistent) ....

favicon
fast.ai
Weird test accuracy for VGG-like training - Deep Learning - Deep Learning Course Forums

Weird test accuracy for VGG-like training - Deep Learning - Deep Learning Course Forums

Check this out: It has almost the same divergence characteristics as yours, except that there are more randomness than yours. (And the cause is attributed to overfitting). But the trend of loss being constantly zero, really seemed like a software programming bug? May be some floating error truncation somewhere?

favicon
fast.ai
Weird test accuracy for VGG-like training

Weird test accuracy for VGG-like training

Hi Everyone, I have trained my model for many many times with 2900 images/class for 5 classes. I split data 80% for training and 20% for validation with shuffling. All the times, I get zero test accuracy as shown in this figure, although the training accuracy is improving. What do you think the problem is? In my opinion, I do not think this is an overfitting problem. Here is my code: import csv import cv2 import numpy as np import matplotlib.pyplot as plt import glob def plot_CNN(history...

favicon
fast.ai
CNN Regression

CNN Regression

As per the assertion error, I’m interested in creating a regression CNN. I’m of course willing to contribute to/make the initial solution, but it’s not clear to me exactly what additions need to be made. It looks like the only changes that would need to be made to get it working is to change the create_head function and make an RegressionLearner equivalent to the ClassificationLearner. The latter may be straight-forward, but the former (i.e., creating a default create_head function) is not so ....

favicon
fast.ai
DL Optimizers - Part 1 (2018) / Beginner (2018) - Deep Learning Course Forums

DL Optimizers - Part 1 (2018) / Beginner (2018) - Deep Learning Course Forums

Hello, After reading this great blog post http://ruder.io/optimizing-gradient-descent/ and seeing fascinating new optimizer implementations in Fast.ai. I wanted to give it a chance and started implementing them with PyTorch from scratch. I used MNIST dataset to benchmark different optimizers. So far, I’ve finished SGD, SGD Momentum and Nesterov. But Nesterov doesn’t converge faster than SGD Momentum as expected. There might be an issue about my code but I couldn’t find anyhing. Hope that someon.

favicon
fast.ai
Trying to run fastai library under virtualenv, hit bcolz error - Part 1 (2018) - Deep Learning Course Forums

Trying to run fastai library under virtualenv, hit bcolz error - Part 1 (2018) - Deep Learning Course Forums

I tried running fastai under python3 + virtualenv (as opposed to Anaconda), however I ran into errors trying to import bcolz. I documented the error on the bcolz repo: But I’m wondering if anyone here knows of a workaround? Or should I just use Anaconda?

favicon
fast.ai

Results

Notadirectoryerror: [winerror 267] the directory name is invalid:
Minimap

Notadirectoryerror: [winerror 267] the directory name is invalid:

I'm running the Bitnami Django Stack (installed on F: Hard disk Drive and not on C : ) and I want to collect static files and compress them into a single location by running python manage.py collectstatic --traceback, but when I run the command I get this error: WindowsError: [Error 267] The directory name is invalid I have read on Microsoft Support that I need to change the properties of the Command Prompt (cmd) by changing %HOMEDRIVE%%HOMEPATH% to %WINDIR% and I did the same for Bitname Con..

filter_none7