You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I keep getting this issue and have no progress at all, please help. I've already done a lot of searching on google, Tried reshape the 'x' in model.py predict().
The Conv2D op currently only supports the NHWC tensor format on the CPU. The op was given the format: NCHW
This is probably because you have the 'wrong' version of tensorflow for this project. For me this worked with tf 2.2.0. Whenever I went higher e.g. 2.4.0, I got the same error as you described.
TF2.2.0 didn't solve the issue for me. However TF1.6.0 did. All necessary packages are indicated in the requirements.txt files. Just pip install it in a new environment and it should work.
________________________________
From: Cyazd ***@***.***>
Sent: Tuesday, April 12, 2022 7:45:38 PM
To: AppliedDataSciencePartners/DeepReinforcementLearning ***@***.***>
Cc: jkjoos ***@***.***>; Comment ***@***.***>
Subject: Re: [AppliedDataSciencePartners/DeepReinforcementLearning] How to switch NHWC to NCHW (#56)
TF2.2.0 didn't solve the issue for me. However TF1.6.0 did. All necessary packages are indicated in the requirements.txt files. Just pip install it in a new environment and it should work.
—
Reply to this email directly, view it on GitHub<#56 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AKOJMW4FXITZW2GCSLQET5DVEWZEFANCNFSM427Q6BAA>.
You are receiving this because you commented.Message ID: ***@***.***>
Activity
jooskesters commentedon May 10, 2021
This is probably because you have the 'wrong' version of tensorflow for this project. For me this worked with tf 2.2.0. Whenever I went higher e.g. 2.4.0, I got the same error as you described.
Cyazd commentedon Apr 12, 2022
TF2.2.0 didn't solve the issue for me. However TF1.6.0 did. All necessary packages are indicated in the requirements.txt files. Just pip install it in a new environment and it should work.
jooskesters commentedon Apr 12, 2022