dvorst

Added support for Jinja2 3.1.2 and scikit-learn 1.0.2

2

When using Jinja2 3.1.2 and scikit-learn 1.0.2, the following errors occurred: - AttributeError: module 'jinja2.ext' has no attribute 'with_' - ModuleNotFoundError: No module named 'sklearn.metrics.scorer' - ModuleNotFoundError: No module named...

When importing eli5, I receive the error shown below. I have version 0.11.0 installed and use Python 3.10 ``` Traceback (most recent call last): File "C:\Users\user\PycharmProjects\resume keywords\main.py", line 2, in...

In Up3, the tranpose conv has kernel size (1,1). From what i know this is quite uncommon, is there a reason why this isn't (2,2) or (4,4) ? https://github.com/NoviceMAn-prog/MSRF-Net/blob/60e23734d94d340b9d89b64e7f9e2636b6f96c0f/model.py#L121

Fig.2a of your paper shows that the top MSRF-subnet output (n13 in your code) is used in the shape stream. However, this is currently not implemented in your code, only...

In resblock, the bias of both convolutions can be set to False, since batch normalization is applied afterwards. https://github.com/NoviceMAn-prog/MSRF-Net/blob/60e23734d94d340b9d89b64e7f9e2636b6f96c0f/model.py#L50-L51 https://github.com/NoviceMAn-prog/MSRF-Net/blob/60e23734d94d340b9d89b64e7f9e2636b6f96c0f/model.py#L53-L54

The bias of the convolutional layer below can be set to False, since batch normalization is applied afterwards. https://github.com/NoviceMAn-prog/MSRF-Net/blob/60e23734d94d340b9d89b64e7f9e2636b6f96c0f/model.py#L39-L40

Concerning the DSDF (RDDB) block In the code, there are skip connections from x,y to each "conv+leaky relu" block (see all the lines below). However, Fig.1 a) of your paper...

Concerning the DSDF (RDDB) block Shouldn't "y1t" (line 333) use "y1" as input? Since y3t uses y3 as input (line 362) and y4t uses y4 as input (line 378) https://github.com/NoviceMAn-prog/MSRF-Net/blob/60e23734d94d340b9d89b64e7f9e2636b6f96c0f/model.py#L333...

Concerning the DSDF (RDDB) block Shouldn't "x1c" (line 331) use "x1" as input? Since x3c uses x3 as input (line 360) and x4c uses x4 as input (line 376) https://github.com/NoviceMAn-prog/MSRF-Net/blob/60e23734d94d340b9d89b64e7f9e2636b6f96c0f/model.py#L331...

Concerning the DSDF (RDDB) block Shouldn't x2c (line 345) use x2 as input? Since x3c uses x3 as input (line 360) and x4c uses x4 as input (line 376) https://github.com/NoviceMAn-prog/MSRF-Net/blob/60e23734d94d340b9d89b64e7f9e2636b6f96c0f/model.py#L345...