ValueError: operands could not be broadcast together with shapes $(1,3)(20,)$

####################################

# DO NOT MODIFY THE DECODEE PART BELOW BUT PROVIDE A SOLUTION BY FIXING THE CLASSES ABOVE LIKE SELFATTENTION ETCETERA#

####################################

def decode$($model: Transformer, dev$\_$examples: List$[$LetterCountingExample$],$ do$\_$print$=$False, do$\_$plot$\_$attn$=$False$)$:

$"""$

Decodes the given dataset, does plotting and printing of examples, and prints the final accuracy.

:param model: your Transformer that returns log probabilities at each position in the input

:param dev$\_$examples: the list of LetterCountingExample

:param do$\_$print: True if you want to print the input$/$gold$/$predictions for the examples, false otherwise

:param do$\_$plot$\_$attn: True if you want to write out plots for each example, false otherwise

:return:

$"""$

num$\_$correct $=0$

num$\_$total $=0$

if len$($dev$\_$examples$)>100$:

print$("$Decoding on a large number of examples $(\%$i$)$; not printing or plotting" $\%$ len$($dev$\_$examples$))$

do$\_$print $=$ False

do$\_$plot$\_$attn $=$ False

for i in range$(0,$ len$($dev$\_$examples$))$:

ex $=$ dev$\_$examples$[$i$]$

$($log$\_$probs, attn$\_$maps$)=$ model.forward$($ex$.$input$\_$tensor$)$

predictions $=$ np$.$argmax$($log$\_$probs.detach$().$numpy$(),$ axis$=1)$

if do$\_$print:

print$("$INPUT $\%$i: $\%$s$"\%($i$,$ ex$.$input$))$

print$("$GOLD $\%$i: $\%$s$"\%($i$,$ repr$($ex$.$output.astype$($dtype$=$int$))))$

print$("$PRED $\%$i: $\%$s$"\%($i$,$ repr$($predictions$)))$

if do$\_$plot$\_$attn:

for j in range$(0,$ len$($attn$\_$maps$))$:

attn$\_$map $=$ attn$\_$maps$[$j$]$

fig, ax $=$ plt$.$subplots$()$

im $=$ ax$.$imshow$($attn$\_$map.detach$().$numpy$(),$ cmap$=$'hot', interpolation$=$'nearest'$)$

ax$.$set$\_$xticks$($np$.$arange$($len$($ex$.$input$)),$ labels$=$ex$.$input$)$

ax$.$set$\_$yticks$($np$.$arange$($len$($ex$.$input$)),$ labels$=$ex$.$input$)$

ax$.$xaxis.tick$\_$top$()$

# plt$.$show$()$

plt$.$savefig$("$plots$/\%$i$\_$attns$\%$i$.$png$"\%($i$,$ j$))$

acc $=$ sum$([$predictions$[$i$]==$ ex$.$output$[$i$]$ for i in range$(0,$ len$($predictions$))])$

num$\_$correct $+=$ acc

num$\_$total $+=$ len$($predictions$)$

print$("$Accuracy: $\%$i $/\%$i $=\%$f$"\%($num$\_$correct, num$\_$total, float$($num$\_$correct$)/$ num$\_$total$))$