Location
Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
What data should you label to get the most value for your money?
Latest submissions
Machine Learning for detection of early onset of Alzheimers
Latest submissions
See Allfailed | 138427 |
3D Seismic Image Interpretation by Machine Learning
Latest submissions
See Allgraded | 83214 | ||
graded | 83131 | ||
failed | 83130 |
A benchmark for image-based food recognition
Latest submissions
See Allgraded | 113188 | ||
graded | 113184 | ||
graded | 113160 |
Predicting smell of molecular compounds
Latest submissions
See Allgraded | 85946 | ||
graded | 85945 | ||
graded | 85935 |
Classify images of snake species from around the world
Latest submissions
Find all the aircraft!
Latest submissions
Latest submissions
Participant | Rating |
---|
Participant | Rating |
---|
Seismic Facies Identification Challenge
Low accuracy Any help will be appreciated
Over 3 years agoHi everyone , i am receiving a very low accuracy of around 0.4 . I am attaching my code below . I have tried everything changing learning rate , different layers initlizers, augmentation, MSE loss, but this network does not learn anything.0.4 accuracy is because it keep predicting only class 2 and class 4 in each prediction, Kindly any tip will be appreciated.
I also have tried cropping different cubes from the cube trained them but that method still didnβt work. Code is attached below.
from segmentation_models import Unet, FPN
base_model = Unet(backbone_name=βresnet34β, encoder_weights=None, input_shape=(256, 224, 1))
base_model.layers.pop()
x1 = base_model.output
x1 = Conv2D(6, 5 ,strides=1, padding=βsameβ, activation=βreluβ)(x1)
out = Conv2D(6, kernel_size =5,strides=1,padding = βsameβ)(x1)
model = Model(base_model.input, out)
x= data_train.reshape(1006,782,590,1)
y = labels_train.reshape(1006,782,590,1).astype(βintβ)-1
def reshape_images(inputs, labels=None, shapess=(224,256)):
tmp = np.zeros((inputs.shape[0], 256,224))
for i,each_input in enumerate(inputs):
tmp[i] = cv2.resize(each_input, dsize=shapess)
if labels is not None:
tmp1 = np.zeros((labels.shape[0], 256,224))
for i,each_input in enumerate(labels):
tmp1[i] = cv2.resize(each_input.astype(βfloatβ), dsize=shapess)
return tmp,tmp1
return tmp
X,Y = reshape_images(x,y)
Y= Y.astype(βintβ)
X = X.reshape(-1,256,224,1)
Y = Y.reshape(-1,256,224,1).astype(βintβ)
data_gen_args = dict(
rotation_range=90.,
width_shift_range=0.5,
height_shift_range=0.5,
zoom_range=0.5, validation_split=0.25)
image_datagen = ImageDataGenerator(**data_gen_args)
mask_datagen = ImageDataGenerator(**data_gen_args)
seed = 1
image_datagen.fit(X, augment=True, seed=seed )
mask_datagen.fit(Y, augment=True, seed=seed)
image_generator = image_datagen.flow(X,seed=seed, subset=βtrainingβ, batch_size=2)
mask_generator = mask_datagen.flow(Y.astype(βintβ),seed=seed, subset=βtrainingβ, batch_size=2)
train_generator = zip(image_generator, mask_generator)
val_image_generator = image_datagen.flow(X,seed=seed, subset=βvalidationβ, batch_size=2)
val_mask_generator = mask_datagen.flow(Y.astype(βintβ),seed=seed, subset=βvalidationβ, batch_size=2)
val_train_generator = zip(val_image_generator, val_mask_generator)
optimizer = keras.optimizers.SGD(learning_rate=0.00001, clipvalue=0.5)
model.compile(optimizer=optimizer , loss= βsparse_categorical_crossentropyβ, metrics=[βaccuracyβ])
model.fit_generator(train_generator, validation_data=val_train_generator, steps_per_epoch=50, epochs =500, validation_steps=10)
Food Recognition Challenge
Mask RCNN score
About 4 years agoHi everyone,
Did anybody use mask rcnn and got a score greater than 0.4 ???.. Thanks
Regards,
Hannan
Submissions not finishing
About 4 years agoSame happened with me i submitted 4 but only 1 completed β¦
Progress very slow on submission?
About 4 years agoHi there i wanted to ask I submitted my work but its taking too long to process. its been 13 hours since i submitted but its still only 4%. Is it normal ?
Editing Docker file
About 4 years agoThanks alot guys its working now i hope my score is not shit after all this effort
Editing Docker file
About 4 years agoThanks alot for helping me out and sorry for bothering you again but it really helped me learning a lot about dockers β¦ Thing is with the current docker file i posted i used this docker file in #5996 and i already mentioned tensorflow_version==1.13.2 so placeholder error should not occur β¦ right? Thanks in advance
Editing Docker file
About 4 years agoThing is i wanted to do that because i keep getting error β¦ so i assumed that it could be because of Dockerfile and hence i wanted to edit it.
Error βUnable to orchestrate submission, please contact Administrators.β I get this error after two or three days and it does not look normal .This error was generated when i did not change USERNAME and HOST_UID but i did change the pip install thing in docker file and added keras and tensor flow so my docker file would look like. i added tensorflow and keras manually because my requirements.txt file was not being read by this Dockerfile β¦
FROM nvidia/cuda:10.0-cudnn7-runtime-ubuntu18.04
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y
build-essential
bzip2
cmake
curl
git
g++
libboost-all-dev
pkg-config
rsync
software-properties-common
sudo
tar
timidity
unzip
wget
locales
zlib1g-dev
python3-dev
python3
python3-pip
python3-tk
libjpeg-dev
libpng-dev
Python3
RUN pip3 install pip --upgrade
RUN pip3 install cython aicrowd_api timeout_decorator
numpy
matplotlib
Keras==2.1.3
tensorflow==1.13.2
scikit-image==0.16.1 \
aicrowd-repo2docker
pillow
RUN pip3 install git+https://github.com/AIcrowd/coco.git#subdirectory=PythonAPI
RUN pip3 install tensorflow-gpu
Unicode support:
RUN locale-gen en_US.UTF-8
ENV LANG en_US.UTF-8
ENV LANGUAGE en_US:en
ENV LC_ALL en_US.UTF-8
Enables X11 sharing and creates user home directory
ENV USER_NAME aicrowd
ENV HOME_DIR /home/$USER_NAME
Replace HOST_UID/HOST_GUID with your user / group id (needed for X11)
ENV HOST_UID 1000
ENV HOST_GID 1000
RUN export uid={HOST_UID} gid={HOST_GID} &&
mkdir -p ${HOME_DIR} &&
echo βUSER_NAME:x:{uid}:${gid}:$USER_NAME,:$HOME_DIR:/bin/bashβ >> /etc/passwd &&
echo βUSER_NAME:x:{uid}:β >> /etc/group &&
echo β$USER_NAME ALL=(ALL) NOPASSWD: ALLβ > /etc/sudoers.d/$USER_NAME &&
chmod 0440 /etc/sudoers.d/USER_NAME && \
chown {uid}:{gid} -R {HOME_DIR}
USER {USER_NAME} WORKDIR {HOME_DIR}
COPY . .
RUN sudo chown {HOST_UID}:{HOST_GID} -R *
RUN sudo chmod 775 -R *
Editing Docker file
About 4 years agoHi guys i am editing Dokcer file.
Enables X11 sharing and creates user home directory
ENV USER_NAME aicrowd
ENV HOME_DIR /home/$USER_NAME
Replace HOST_UID/HOST_GUID with your user / group id (needed for X11)
ENV HOST_UID 1000
ENV HOST_GID 1000
Which of these 4 items should be changed . I have already added the necessay modules in my docker file. Help will be appreciated
Unable to orchestrate submission, please contact Administrators
About 4 years agoHi Shivam,
This is the ticket number #59996 β¦ But there is also another point to notice that i dont see any progress bar while its being run so i think timeout could be the problem here β¦
Unable to orchestrate submission, please contact Administrators
About 4 years agoI got this error after program kept running for a day β¦Anybody knows the errorβ¦ Thnaks?
Submission struck
About 4 years agoI think submissions are struck⦠kindly Anyone can look into it ??
Local Testing for submission error
About 4 years agoI am using Ubuntu and i think i will have to install docker first Thanks alot for help
Local Testing for submission error
About 4 years agoCan you tell me the command to see if the docker is running or not because i also thinks the same it could be the issue. i am using Python virtual_env enviornment β¦
Local Testing for submission error
About 4 years agoHi, Thanks @shivam for quick response )
aicrowd-repo2docker --no-run --user-id 1001 --user-name aicrowd --image-name sample_aicrowd_image_build --debug ./
I am currently in repository directory
Local Testing for submission error
About 4 years agoDockerException: Error while fetching server API version: (βConnection aborted.β, FileNotFoundError(2, βNo such file or directoryβ))
Does anybody knows this error while i run submission locally ? Although there is requirements.txt file availaible at current directory ?
Submission failed
About 4 years agoHi admin, i submitted my results yesterday but grading failed. Kindly can you tell me why is it so ? or where in issues section ask for logs ?
Regards,
Hannan
Cannot upload to the git even git lfs is checked ... windows using git tortoise
About 4 years agoThanks Shraddha, my clients was not compatible with git lfs so i had to install new client β¦ Thanks for the help though
Cannot upload to the git even git lfs is checked ... windows using git tortoise
About 4 years agogit.exe push --tags --progress βoriginβ master:master
Locking support detected on remote βoriginβ. Consider enabling it with:
git config lfs.https://gitlab.aicrowd.com/hannan4252/food_project.git/info/lfs.locksverify true
Locking support detected on remote "origin". Consider enabling it with:
git config lfs.https://gitlab.aicrowd.com/hannan4252/food_project.git/info/lfs.locksverify true
Enumerating objects: 56, done.
Counting objects: 100% (56/56), done.
Delta compression using up to 8 threads
Compressing objects: 100% (53/53), done.
remote: fatal: pack exceeds maximum allowed size
fatal: sha1 file ββ write error: Broken pipe
error: remote unpack failed: unpack-objects abnormal exit
error: failed to push some refs to βgit@gitlab.aicrowd.com:hannan4252/food_project.gitβ
Where to submit the repository link?
About 4 years agoI cant find the location of where to submit all the files from repository. Kindly anyone can help?
Regards,
Abdul Hannan
π Explained by the Community | Win 4 x DJI Mavic Drones
Over 3 years agoHi Thanks a lot for the notebook. I wanted to ask why have you first reshaped your samples into 2012, 782, 295. Thanks a lot