Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input shapes: [?,2,112,64]. #25
Comments
|
Did you find any solution for this? |
|
No it did not occur while i was using it
Sent from Outlook<http://aka.ms/weboutlook>
…________________________________
From: Alex Mihale <[email protected]>
Sent: Sunday, August 16, 2020 4:18 PM
To: foamliu/Car-Recognition <[email protected]>
Cc: Subscribed <[email protected]>
Subject: Re: [foamliu/Car-Recognition] Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input s...
Did you find any solution for this?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub<#25 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AO2V5MXHPCH572PCMMGEWL3SA66BBANCNFSM4PWQIIEQ>.
|
Can you give us some details about how did u set up the project? Versions of packages and stuffs like that? |
|
Python: 3.6.5
Tensorflow : 1.13.1
Tensorflow-gpu(if using gpu) : 1.13.1
Keras: 2.0.0
Sent from Outlook<http://aka.ms/weboutlook>
…________________________________
From: Alex Mihale <[email protected]>
Sent: Monday, August 17, 2020 2:16 PM
To: foamliu/Car-Recognition <[email protected]>
Cc: Usman-Ghani123 <[email protected]>; Comment <[email protected]>
Subject: Re: [foamliu/Car-Recognition] Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input s...
No it did not occur while i was using it
Can you give us some details about how did u set up the project? Versions of packages and stuffs like that?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#25 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AO2V5MQK6UPVNM6L7RGZCZDSBDYOHANCNFSM4PWQIIEQ>.
|
Do you had any problem on running this app with the specified versions? |
|
Not at all. It worked completely fine
you can try for numpy ==1.16.1 version as well with all these requirement i send you formerly
Sent from Outlook<http://aka.ms/weboutlook>
…________________________________
From: Alex Mihale <[email protected]>
Sent: Monday, August 17, 2020 7:49 PM
To: foamliu/Car-Recognition <[email protected]>
Cc: Usman-Ghani123 <[email protected]>; Comment <[email protected]>
Subject: Re: [foamliu/Car-Recognition] Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input s...
Python: 3.6.5 Tensorflow : 1.13.1 Tensorflow-gpu(if using gpu) : 1.13.1 Keras: 2.0.0
Do you had any problem on running this app with the specified versions?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#25 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AO2V5MRRYOG5PDDDBMLZ6YTSBE7QDANCNFSM4PWQIIEQ>.
|
do you have any idea if this project can run on Tensorflow 2+? |
|
No it can not work on tensorflow greater then 2.
Get Outlook for Android<https://aka.ms/ghei36>
…________________________________
From: Alex Mihale <[email protected]>
Sent: Thursday, August 27, 2020 12:17:27 PM
To: foamliu/Car-Recognition <[email protected]>
Cc: Syed Muhmmad Usman Ghani <[email protected]>; Comment <[email protected]>
Subject: Re: [foamliu/Car-Recognition] Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input s...
u can try f
do you have any idea if this project can run on Tensorflow 2+?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#25 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AO2V5MWPMGFYP6YQTICGV5DSCYCAPANCNFSM4PWQIIEQ>.
|
|
It can only work on tensorflow 1.13.1
Get Outlook for Android<https://aka.ms/ghei36>
…________________________________
From: Syed Muhammad Usman Ghani <[email protected]>
Sent: Thursday, August 27, 2020 1:11:29 PM
To: foamliu/Car-Recognition <[email protected]>
Subject: Re: [foamliu/Car-Recognition] Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input s...
No it can not work on tensorflow greater then 2.
Get Outlook for Android<https://aka.ms/ghei36>
________________________________
From: Alex Mihale <[email protected]>
Sent: Thursday, August 27, 2020 12:17:27 PM
To: foamliu/Car-Recognition <[email protected]>
Cc: Syed Muhmmad Usman Ghani <[email protected]>; Comment <[email protected]>
Subject: Re: [foamliu/Car-Recognition] Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input s...
u can try f
do you have any idea if this project can run on Tensorflow 2+?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#25 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AO2V5MWPMGFYP6YQTICGV5DSCYCAPANCNFSM4PWQIIEQ>.
|
do you know any car recognition project that works on tensorflow 2+? I need to run it on a raspberry pi for testing |
|
No, I do not know any car recognition project with TensorFlow 2+ |
|
Which code are you trying to run? |
|
i need only demo.py working on tensorflow 2+ ( the code that actually run the image ) |
|
If you want to use TensorFlow 2+ so then you have to do some code changes in the files according to the errors |
|
In pull request, a person has suggested some changes to make this compatible with Tensorflow 2.x . |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I have run the train.py, but it show me that:
ValueError: Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPoolT=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]' with input shapes: [?,2,112,64].
The text was updated successfully, but these errors were encountered: