Multiclass RGB image dataset ValueError: a must be greater than 0 unless no samples are taken

Question

I am working an image dataset that consist of 2410 RGB image data and belongs to two classes, i.e., crops_class and another is grass_class. Crops class data contains 1210 and grass class contains 1200 image data. When I run the code I have faced an error that is

grass
(0, 2)

However when I run the data shape

df_data.shape

I find output

(2410, 2)

mtrand.pyx in numpy.random.mtrand.RandomState.choice()
ValueError: a must be greater than 0 unless no samples are taken

My code:

df_data is not None and isinstance(df_data, pd.DataFrame) and not df_data.empty
>True
df_data.isnull().any()
>image_id    False
target      False
dtype: bool


SAMPLE_SIZE = (1200)
# Get a list of classes
target_list = os.listdir('/content/PlantDataset/')

for target in target_list:
    print(target)

# Filter out a target and take a random sample
temp = df_data[df_data['target'] == target]
print(temp.shape)
df=temp.sample(SAMPLE_SIZE, random_state=101)
# if it's the first item in the list
if target == target_list[0]:
    df_sample = df
else:
    # Concat the dataframes
    df_sample = pd.concat([df_sample, df], axis=0).reset_index(drop=True)

Error:

grass
(0, 2)
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-26-7918c4242404> in <module>()
      8     temp = df_data[df_data['target'] == target]
      9     print(temp.shape)
---> 10     df=temp.sample(SAMPLE_SIZE, random_state=101)
     11     # if it's the first item in the list
     12     if target == target_list[0]:

/usr/local/lib/python3.7/dist-packages/pandas/core/generic.py in sample(self, n, frac, replace, weights, random_state, axis, ignore_index)
   5363             )
   5364 
-> 5365         locs = rs.choice(axis_length, size=n, replace=replace, p=weights)
   5366         result = self.take(locs, axis=axis)
   5367         if ignore_index:

mtrand.pyx in numpy.random.mtrand.RandomState.choice()

ValueError: a must be greater than 0 unless no samples are taken

How may I solve this error ?